Claude Skill

refine-pr-review

Triage a fetched PR review with the user, comment by comment, drafting each reply and producing a REQUIREMENTS file for the accepted code changes. Takes the PR-REVIEW file produced by fetch-pr-review. Invoke manually only.

LLM Mart · 0 points · 13 views 2 listing impressions 0 install-command copies
Download eai-org-agent-toolkit-skills_refine-pr-review-d79feee.zip · 6 KB

Install

skills CLI npx skills add https://github.com/eai-org/agent-toolkit/tree/main/skills/refine-pr-review
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install eai-org-agent-toolkit@llmmart
Git git clone https://github.com/eai-org/agent-toolkit.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole eai-org/agent-toolkit collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Refine PR review

The Refine phase for review feedback: turn a .PR-REVIEW.md (from /fetch-pr-review; ask if the path is ambiguous) into user-settled per-comment verdicts, drafted replies, and a REQUIREMENTS file covering the accepted code changes. Triage and replies are settled here; the plan and execute phases see only code changes.

A PR URL instead: when the harness has subagents and fetch-pr-review is available (../fetch-pr-review/SKILL.md beside this skill), a subagent fetches it first per its delegate.md and the file it returns is the input. Not available → say so and ask for the fetched file; available but no subagents → hand off /fetch-pr-review <url> to a fresh session and stop.

A trailing head=<sha> token (fetch-pr-review's refresh hand-off) is the head a refresh just confirmed: Phase 1's moved-head check uses it in place of the file's Head line.

Its own .PR-REVIEW.REQUIREMENTS.md instead, once a blocking answer is in: run Phase 1's checkout and remote-head check first — a checkout differing from the ANSWERS Head, or a dirty tree, is reported and the user decides, never a branch switch; a moved PR head is reported with the re-fetch offer and the user decides whether to finish this round first. Verdicts, replies and Lessons stand as its .PR-REVIEW.ANSWERS.md records them. Apply the answer: every reply whose described change it alters is re-drafted under Phase 1's voice rule, confirmed, and updated in place; a verdict changes only as an explicit, user-confirmed exception to Phase 2's "Scope is settled in Phase 1"; a lesson whose source rows are no longer all accepted is put to the user; no row affected → the ANSWERS file is not rewritten. Then Phase 2 on that file, then Next step.

Verdicts

  • address: the change enters the requirements in full; the reply stays a canned one-liner ("fixed", "good catch, thanks").
  • partial: part of the change is accepted into the requirements, and the reply explains what was done and what was kept and why.
  • push back: no code change; the reply carries the reason.
  • no action: no code change; a reply is optional (a question answered, an outdated concern the current code settles, an approval with no ask, the author's own comment) — when written, it is drafted and shown like any other.

Bot findings take bot: included (reply "fixed"), bot: partial (Notes say which part; the reply names what was fixed and why the rest was not) or bot: ignored (reply: the reason, one short factual sentence, no thanks or hedging).

Naming a comment

Never refer to a comment by index or position, anywhere — questions, batch lists, hand-off text. Quote its opening words instead, truncated to the shortest unique prefix — the comment "the null check here misses …". Always verbatim, never translated or corrected, so the quote can be searched on the page. Only the ANSWERS table's own row numbers stay, for in-file cross-references.

Phase 1 — triage every comment with the user

Before the first code check, compare the checkout with the PR-REVIEW head: a different commit or branch, or a dirty tree, is reported and the user decides; never switch branches yourself. A PR head that moved since the fetch (the remote compared with the file's Head, or with the head=<sha> token when given) → offer a re-fetch before triage; a refresh (no new activity) keeps the file, the checkout still compared with the current head, and a refresh the URL path's fetch just reported needs no re-fetch. The URL path gets the same check — the subagent's fetch is seconds old, the checkout is still the user's.

On a -N file, read the earlier rounds' ANSWERS first: a comment re-raising one already triaged keeps its verdict and reply unless it brings evidence the earlier one lacked, and its Notes say kept from round K, row M; a kept row's work and lessons stay with round K, never counted as accepted below. An earlier round without ANSWERS was never triaged: its comments join this triage, each row's Notes saying joined from round K, its status read from the latest ## Since round block listing it. A -N file with no touched thread (a Since block only) → say there is nothing to triage, list the status changes, write no ANSWERS or REQUIREMENTS file, print no launch command, stop. This round's ANSWERS file or REQUIREMENTS file already exists (and the REQUIREMENTS file is not the input) → one question before triage, covering both: update in place (recommended — existing rows stand, their verdicts and replies kept unless the user changes them or a comment brings new evidence; only new or changed comments are triaged) or start over (every comment re-triaged, both files replaced at write time). Never a second ANSWERS sheet; nothing overwritten without this answer.

Read the code behind each comment first: verify its premise against the checkout, never judging from the quoted hunk alone. Then form a recommendation — verdict, reasoning, and a draft reply for every verdict but address: partial, push back, and a no action reply that answers or explains, a courtesy reply on an outdated thread included. Before the first such draft in a round (even one with no partial or push-back row), actually invoke use-conversational-language (Developer conversations, author replies) and follow it; reciting its rules from memory does not count. Not installed: plain prose, no dashes and no AI tells. Every reply other than address's canned one-liner is shown to the user before it is written. Nothing is decided silently, and every question to the user is worded via explain-in-simple-language when available, the draft reply it carries excepted:

  • Contentious ones one at a time: every comment recommended partial or push back, or uncertain, is its own question carrying recommendation, reasoning, and draft reply.
  • Obvious ones as one batch: then list the comments recommended address or no action, each no action item with its draft reply, for a single confirmation; the user can pull any item out for individual discussion.

Per comment type:

  • Open/active human threads → full triage.
  • Outdated → code check first; when the concern is moot in the current code, recommend "no action, optional courtesy reply".
  • Unclear (a status the fetch could not settle) → ask the user its status first, then triage it as that status.
  • Resolved → no questions; table row marked "resolved earlier"; closed as won't-fix → Notes say so.
  • Review verdict summaries and general comments → each actionable ask inside them is triaged like a thread. An (author) comment → no action unless it carries an ask worth tracking.
  • Bot comments → present the actionable findings as one batch include-or-ignore question, each ignore or partial recommendation carrying its draft reply; a bot comment with no finding (a passing quality gate, a change summary) gets no reply. A bot thread flagged human reply is triaged as a human thread, the reply addressed to that person.

Phase 1 is complete only when every comment in the PR-REVIEW file has a user-confirmed verdict. Write the ANSWERS file now, before Phase 2.

Phase 2 — requirements via /refine-ticket

Treat the accepted work (address, the accepted part of each partial and bot: partial, and included bot findings) as a settled-scope ticket and follow /refine-ticket (load and follow its SKILL.md): code verification, blocking vs non-blocking, the REQUIREMENTS structure, location and naming — all as written, with these overrides:

  • Scope is settled in Phase 1 — never re-ask whether to address a comment; grilling covers only residual requirement-level gaps.
  • The PR-REVIEW file is the local input, so the output lands next to it per its naming rule (1234-task.PR-REVIEW.md → 1234-task.PR-REVIEW.REQUIREMENTS.md); later review rounds carry their suffix through (…PR-REVIEW-2.REQUIREMENTS.md).
  • The existing-file question was asked before triage: never ask again at write time; update in place or replace as answered.
  • A requirement's source tag is the comment's opening words and its path:line (threadless: its Location label), e.g. ("Validate both new option arguments", install.sh:88) — never a row number.
  • Nothing about replies or verdicts enters the REQUIREMENTS file.
  • Ignore its hand-off commands, the blocking-question one included — this skill owns the hand-off.

When nothing is accepted (no address, partial, bot: included or bot: partial), skip this phase: no REQUIREMENTS file, nothing to plan or execute.

The ANSWERS file

<input name>.ANSWERS.md next to the input (1234-task.PR-REVIEW.md → 1234-task.PR-REVIEW.ANSWERS.md) — the user's copy-paste sheet and the durable record of what was pushed back. Header: # Answers: <PR title>, then > **Source** [<PR id>](<url>), > **Head** <sha> (the head the verdicts were settled against), > **Triaged** YYYY-MM-DD; round and requirements file follow from the file name. Then one table row per comment, resolved and bot rows included for completeness:

| # | Original comment | Location | Verdict | Reply | Notes |

  • Original comment — its opening words verbatim, truncated to the shortest unique prefix.
  • Location — the thread's permalink from the PR-REVIEW file, with path:line as the readable label; a reply goes inside its thread, never as a top-level comment. A review summary or general comment has no thread: labelled review summary or general comment, linked to its permalink when the fetch has one, its reply a top-level comment quoting the ask.
  • Verdict — address / partial / push back / no action, or resolved earlier / bot: included / bot: partial / bot: ignored.
  • Reply — canned one-liner for address and bot: included. Post-fix stance: written as if the accepted changes are already made ("did X, kept Y as is because …") — the sheet is pasted after the fixes land. A reply too long for a cell goes below the table under a ## Reply <row #> heading that opens with the original comment quoted in full as a blockquote, so each reply is checkable against its question without scrolling back to the table.
  • Notes — the reasoning in a few words, for future review rounds.

Lessons

During Phase 1, note accepted comments (address, the accepted part of partial, bot: included, bot: partial) whose lesson generalizes — would a fresh agent on another task here plausibly repeat the mistake? A one-off slip fails; a convention or recurring pattern passes. After Phase 2, present them as one batch for the user to strike or add to, each phrased as the general rule, not the incident ("Mock external HTTP in unit tests", not "the null check on line 42"). Append the survivors as a ## Lessons section at the end of the ANSWERS file, one line each with its source row numbers; none → no section.

Boundaries

  • Never touch the PR: no posting, replying, resolving, or voting — file in, files out.
  • No implementation, no plan in this session: it writes only the ANSWERS and REQUIREMENTS files; the subagents of Next step write their own.

Next step

State the output paths (project-relative). Remind the user the ANSWERS file is theirs to post manually once the fixes land. No REQUIREMENTS file → no launch command, only that reminder (and the self-improve subagent or line below when Lessons were written). While the REQUIREMENTS file holds a blocking Open questions entry, print no execute or plan command and no subagent offer, only who must answer it and the command for once the answer is in: /refine-pr-review <requirements-file>. Otherwise hand off by the size of the accepted change set, leading with your recommendation but giving each option as its own fenced block under the label quoted below, holding a single copy-pasteable launch command (vendor-agnostic — claude below is only the example). The recommendation names only options printed below: without create-implementation-plan, a substantial change set is recommended to harden first (when available), else to execute directly.

Subagents first

When the harness has subagents and at least one subagent below applies, lead with one sentence offering to spawn them now, in this session, with autoaccept, naming what each would do, that it applies its own recommended choices without showing diffs, asking only on a choice that would reshape the change, and that the self-improve one waits for the execute one ("Recommended: I spawn two subagents now, one applying

  • Execute — applies when the change set is the small mechanical kind and the REQUIREMENTS file has no Open questions entry, blocking or not. Brief: the REQUIREMENTS path; the branch and head checked out now, which it must find unchanged, else blocked; read-only git; apply the file, then run the project's validation (lint, tests, build); inside the accepted scope take your own recommended choice, and stop before any choice that would reshape the change (a design decision, scope beyond the file) or a validation failure outside that scope. Report only done with the files changed and the validation result, or blocked with what was already applied, the decision, its candidate answers and your pick with why; no hand-off text.
  • Self-improve — applies whenever Lessons were written and /self-improve is available, per its delegate.md on the ANSWERS file's ## Lessons section, every lesson in one brief, whatever the change set's size. Spawned after the execute subagent has finished — its done, or the user's answer to its blocked stopping it — when one was spawned, else at once; the yes to the offer covers that later spawn. A REQUIREMENTS file whose changes no execute subagent finished applying (none spawned, or one stopped) means they go to a separate session: say, when announcing this spawn, that the execute session is to start after its report, since both may edit the same file.

blocked → put the decision to the user as one question, recommending the subagent's pick, and relaunch with the answer added to the brief — the execute subagent on the tree as it left it, told what it already applied, or, the user declining the relaunch, stopped there with nothing more applied and the execute block re-shown with the report's applied list and the open decision added to its prompt; the self-improve one per its delegate.md. Show each report as returned, then the ANSWERS reminder; fidelity is the subagent's job — never re-run validation or re-read its edits to check.

"Apply the changes directly, for a small mechanical change set:"

claude --name execute-review-<slug> "Apply <requirements-file>, then run the project's validation (lint, tests, build)"

/create-implementation-plan available — "or plan first, for a substantial change set (cross-file rework, design decisions):"

claude --name create-plan-<slug> "/create-implementation-plan <requirements-file>"

/harden-artifact available — "or harden the requirements first, recommended for a substantial change set:"

claude --name harden-requirements-<slug> "/harden-artifact <requirements-file>"

Lessons written and /self-improve available — "Persist the lessons:", or, under an execute command above, "Persist the lessons after the execute session:", since a mechanical lesson may edit a lint config or CI job the execution also touches:

claude --name self-improve-<slug> "/self-improve Persist the lessons listed under Lessons in <answers-file>"

Then offer the alternative: one line offering to clear the current session (vendor-agnostic — /clear is only the example) and run the next phase here, then the same labelled blocks with the bare prompts, under the same gates.

Files (agent-toolkit)
  • SKILL.md 16.3 KB
    ---
    name: refine-pr-review
    description: Triage a fetched PR review with the user, comment by comment, drafting each reply and producing a REQUIREMENTS file for the accepted code changes. Takes the PR-REVIEW file produced by fetch-pr-review, or a PR URL. Invoke manually only.
    license: MIT
    metadata:
      version: "1.12"
    ---
    
    # Refine PR review
    
    The **Refine** phase for review feedback: turn a `.PR-REVIEW.md` (from /fetch-pr-review; ask if
    the path is ambiguous) into user-settled per-comment verdicts, drafted replies, and a REQUIREMENTS
    file covering the accepted code changes. Triage and replies are settled here; the plan and execute
    phases see only code changes.
    
    A PR URL instead: when the harness has subagents and fetch-pr-review is available
    (`../fetch-pr-review/SKILL.md` beside this skill), a subagent fetches it first per its
    [delegate.md](../fetch-pr-review/delegate.md) and the file it returns is the input. Not available
    → say so and ask for the fetched file; available but no subagents → hand off
    `/fetch-pr-review <url>` to a fresh session and stop.
    
    A trailing `head=<sha>` token (fetch-pr-review's refresh hand-off) is the head a refresh just
    confirmed: Phase 1's moved-head check uses it in place of the file's `Head` line.
    
    Its own `.PR-REVIEW.REQUIREMENTS.md` instead, once a blocking answer is in: run Phase 1's checkout
    and remote-head check first — a checkout differing from the ANSWERS `Head`, or a dirty tree, is
    reported and the user decides, never a branch switch; a moved PR head is reported with the
    re-fetch offer and the user decides whether to finish this round first. Verdicts, replies and
    Lessons stand as its `.PR-REVIEW.ANSWERS.md` records them. Apply the answer: every reply whose
    described change it alters is re-drafted under Phase 1's voice rule, confirmed, and updated in
    place; a verdict changes only as an explicit, user-confirmed exception to Phase 2's "Scope is
    settled in Phase 1"; a lesson whose source rows are no longer all accepted is put to the user; no
    row affected → the ANSWERS file is not rewritten. Then Phase 2 on that file, then Next step.
    
    ## Verdicts
    
    - **address**: the change enters the requirements in full; the reply stays a canned one-liner
      ("fixed", "good catch, thanks").
    - **partial**: part of the change is accepted into the requirements, and the reply explains what
      was done and what was kept and why.
    - **push back**: no code change; the reply carries the reason.
    - **no action**: no code change; a reply is optional (a question answered, an outdated concern the
      current code settles, an approval with no ask, the author's own comment) — when written, it is
      drafted and shown like any other.
    
    Bot findings take `bot: included` (reply "fixed"), `bot: partial` (Notes say which part; the
    reply names what was fixed and why the rest was not) or `bot: ignored` (reply: the reason, one
    short factual sentence, no thanks or hedging).
    
    ## Naming a comment
    
    Never refer to a comment by index or position, anywhere — questions, batch lists, hand-off text.
    Quote its opening words instead, truncated to the shortest unique prefix — the comment "the null
    check here misses …". Always verbatim, never translated or corrected, so the quote can be searched
    on the page. Only the ANSWERS table's own row numbers stay, for in-file cross-references.
    
    ## Phase 1 — triage every comment with the user
    
    Before the first code check, compare the checkout with the PR-REVIEW head: a different commit or
    branch, or a dirty tree, is reported and the user decides; never switch branches yourself. A PR
    head that moved since the fetch (the remote compared with the file's `Head`, or with the
    `head=<sha>` token when given) → offer a re-fetch before triage; a refresh (no new activity) keeps
    the file, the checkout still compared with the current head, and a refresh the URL path's fetch
    just reported needs no re-fetch. The URL path gets the same check — the subagent's fetch is seconds
    old, the checkout is still the user's.
    
    On a `-N` file, read the earlier rounds' ANSWERS first: a comment re-raising one already triaged
    keeps its verdict and reply unless it brings evidence the earlier one lacked, and its Notes say
    `kept from round K, row M`; a kept row's work and lessons stay with round K, never counted as
    accepted below. An earlier round without ANSWERS was never triaged: its comments join this triage,
    each row's Notes saying `joined from round K`, its status read from the latest `## Since round`
    block listing it. A `-N` file with no touched thread (a Since block only) → say there is nothing
    to triage, list the status changes, write no ANSWERS or REQUIREMENTS file, print no launch command,
    stop. This round's ANSWERS file or REQUIREMENTS file already exists (and the REQUIREMENTS file is
    not the input) → one question before triage, covering both: **update in place** (recommended —
    existing rows stand, their verdicts and replies kept unless the user changes them or a comment
    brings new evidence; only new or changed comments are triaged) or **start over** (every comment
    re-triaged, both files replaced at write time). Never a second ANSWERS sheet; nothing overwritten
    without this answer.
    
    Read the code behind each comment first: verify its premise against the checkout, never judging
    from the quoted hunk alone. Then form a recommendation — verdict, reasoning, and a draft reply for
    every verdict but address: partial, push back, and a `no action` reply that answers or explains, a
    courtesy reply on an outdated thread included. Before the first such draft in a round (even one
    with no partial or push-back row), actually invoke `use-conversational-language` (Developer
    conversations, author replies) and follow it; reciting its rules from memory does not count.
    Not installed: plain prose, no dashes and no AI tells. Every reply other than address's canned
    one-liner is shown to the user before it is written. Nothing is decided silently, and every
    question to the user is worded via `explain-in-simple-language` when available, the draft reply it
    carries excepted:
    
    - **Contentious ones one at a time**: every comment recommended partial or push back, or
      uncertain, is its own question carrying recommendation, reasoning, and draft reply.
    - **Obvious ones as one batch**: then list the comments recommended address or no action, each
      `no action` item with its draft reply, for a single confirmation; the user can pull any item out
      for individual discussion.
    
    Per comment type:
    
    - Open/active human threads → full triage.
    - **Outdated** → code check first; when the concern is moot in the current code, recommend "no
      action, optional courtesy reply".
    - **Unclear** (a status the fetch could not settle) → ask the user its status first, then triage
      it as that status.
    - **Resolved** → no questions; table row marked "resolved earlier"; closed as won't-fix → Notes
      say so.
    - Review verdict summaries and general comments → each actionable ask inside them is triaged like
      a thread. An `(author)` comment → no action unless it carries an ask worth tracking.
    - Bot comments → present the actionable findings as one batch include-or-ignore question, each
      ignore or partial recommendation carrying its draft reply; a bot comment with no finding (a
      passing quality gate, a change summary) gets no reply. A bot thread flagged `human reply` is
      triaged as a human thread, the reply addressed to that person.
    
    Phase 1 is complete only when every comment in the PR-REVIEW file has a user-confirmed verdict.
    Write the ANSWERS file now, before Phase 2.
    
    ## Phase 2 — requirements via /refine-ticket
    
    Treat the accepted work (address, the accepted part of each partial and bot: partial, and included
    bot findings) as a settled-scope ticket and follow **/refine-ticket** (load and follow its
    SKILL.md): code verification, blocking vs non-blocking, the REQUIREMENTS structure, location and
    naming — all as written, with these overrides:
    
    - Scope is settled in Phase 1 — never re-ask whether to address a comment; grilling covers only
      residual requirement-level gaps.
    - The PR-REVIEW file is the local input, so the output lands next to it per its naming rule
      (`1234-task.PR-REVIEW.md` → `1234-task.PR-REVIEW.REQUIREMENTS.md`); later review rounds carry
      their suffix through (`…PR-REVIEW-2.REQUIREMENTS.md`).
    - The existing-file question was asked before triage: never ask again at write time; update in
      place or replace as answered.
    - A requirement's source tag is the comment's opening words and its `path:line` (threadless: its
      Location label), e.g. `("Validate both new option arguments", install.sh:88)` — never a row
      number.
    - Nothing about replies or verdicts enters the REQUIREMENTS file.
    - Ignore its hand-off commands, the blocking-question one included — this skill owns the hand-off.
    
    When nothing is accepted (no address, partial, bot: included or bot: partial), skip this phase: no
    REQUIREMENTS file, nothing to plan or execute.
    
    ## The ANSWERS file
    
    `<input name>.ANSWERS.md` next to the input (`1234-task.PR-REVIEW.md` →
    `1234-task.PR-REVIEW.ANSWERS.md`) — the user's copy-paste sheet and the durable record of what was
    pushed back. Header: `# Answers: <PR title>`, then `> **Source** [<PR id>](<url>)`,
    `> **Head** <sha>` (the head the verdicts were settled against), `> **Triaged** YYYY-MM-DD`; round
    and requirements file follow from the file name. Then one table row per comment, resolved and bot
    rows included for completeness:
    
    | # | Original comment | Location | Verdict | Reply | Notes |
    
    - **Original comment** — its opening words verbatim, truncated to the shortest unique prefix.
    - **Location** — the thread's permalink from the PR-REVIEW file, with `path:line` as the readable
      label; a reply goes inside its thread, never as a top-level comment. A review summary or general
      comment has no thread: labelled `review summary` or `general comment`, linked to its permalink
      when the fetch has one, its reply a top-level comment quoting the ask.
    - **Verdict** — `address` / `partial` / `push back` / `no action`, or `resolved earlier` /
      `bot: included` / `bot: partial` / `bot: ignored`.
    - **Reply** — canned one-liner for address and bot: included. Post-fix stance: written as if the
      accepted changes are already made ("did X, kept Y as is because …") — the sheet is pasted after
      the fixes land. A reply too long for a cell goes below the table under a `## Reply <row #>`
      heading that opens with the original comment quoted in full as a blockquote, so each reply is
      checkable against its question without scrolling back to the table.
    - **Notes** — the reasoning in a few words, for future review rounds.
    
    ## Lessons
    
    During Phase 1, note accepted comments (address, the accepted part of partial, bot: included, bot:
    partial) whose lesson generalizes — would a fresh agent on another task here plausibly repeat the
    mistake? A one-off slip fails; a convention or recurring pattern passes. After Phase 2, present
    them as one batch for the user to strike or add to, each phrased as the general rule, not the
    incident ("Mock external HTTP in unit tests", not "the null check on line 42"). Append the
    survivors as a `## Lessons` section at the end of the ANSWERS file, one line each with its source
    row numbers; none → no section.
    
    ## Boundaries
    
    - **Never touch the PR**: no posting, replying, resolving, or voting — file in, files out.
    - No implementation, no plan in this session: it writes only the ANSWERS and REQUIREMENTS files;
      the subagents of Next step write their own.
    
    ## Next step
    
    State the output paths (project-relative). Remind the user the ANSWERS file is theirs to post
    manually once the fixes land. No REQUIREMENTS file → no launch command, only that reminder (and
    the self-improve subagent or line below when Lessons were written). While the REQUIREMENTS file
    holds a **blocking** Open questions entry, print no execute or plan command and no subagent offer,
    only who must answer it and the command for once the answer is in:
    `/refine-pr-review <requirements-file>`. Otherwise hand off by the size of the accepted change set,
    leading with your recommendation but giving each option as its own fenced block under the label
    quoted below, holding a single copy-pasteable launch command (vendor-agnostic — `claude` below is
    only the example). The recommendation names only options printed below: without
    create-implementation-plan, a substantial change set is recommended to harden first (when
    available), else to execute directly.
    
    ### Subagents first
    
    When the harness has subagents and at least one subagent below applies, lead with one sentence
    offering to spawn them now, in this session, with `autoaccept`, naming what each would do, that
    it applies its own recommended choices without showing diffs, asking only on a choice that would
    reshape the change, and that the self-improve one waits for the execute one ("Recommended: I spawn
    two subagents now, one applying <requirements-file> and running validation, then, once it is done,
    one persisting the two lessons into the project's docs; both apply their own picks unasked and stop
    only on a choice that reshapes the change. Yes, or pick one."); nothing is spawned before the yes,
    and the fenced blocks then follow under "or in a fresh session:". On the yes, spawn each as one
    subagent briefed with nothing else from the session:
    
    - **Execute** — applies when the change set is the small mechanical kind and the REQUIREMENTS file
      has no Open questions entry, blocking or not. Brief: the REQUIREMENTS path; the branch and head
      checked out now, which it must find unchanged, else `blocked`; read-only git; apply the file,
      then run the project's validation (lint, tests, build); inside the accepted scope take your own
      recommended choice, and stop before any choice that would reshape the change (a design decision,
      scope beyond the file) or a validation failure outside that scope. Report only `done` with the
      files changed and the validation result, or `blocked` with what was already applied, the
      decision, its candidate answers and your pick with why; no hand-off text.
    - **Self-improve** — applies whenever Lessons were written and `/self-improve` is available, per
      its [delegate.md](../self-improve/delegate.md) on the ANSWERS file's `## Lessons` section, every
      lesson in one brief, whatever the change set's size. Spawned after the execute subagent has
      finished — its `done`, or the user's answer to its `blocked` stopping it — when one was spawned,
      else at once; the yes to the offer covers that later spawn. A REQUIREMENTS file whose changes no
      execute subagent finished applying (none spawned, or one stopped) means they go to a separate
      session:
      say, when announcing this spawn, that the execute session is to start after its report, since
      both may edit the same file.
    
    `blocked` → put the decision to the user as one question, recommending the subagent's pick, and
    relaunch with the answer added to the brief — the execute subagent on the tree as it left it, told
    what it already applied, or, the user declining the relaunch, stopped there with nothing more
    applied and the execute block re-shown with the report's applied list and the open decision added
    to its prompt; the self-improve one per its delegate.md. Show each report as returned, then the
    ANSWERS reminder; fidelity is the subagent's job — never re-run validation or re-read its edits to
    check.
    
    "Apply the changes directly, for a small mechanical change set:"
    
    ```
    claude --name execute-review-<slug> "Apply <requirements-file>, then run the project's validation (lint, tests, build)"
    ```
    
    `/create-implementation-plan` available — "or plan first, for a substantial change set (cross-file
    rework, design decisions):"
    
    ```
    claude --name create-plan-<slug> "/create-implementation-plan <requirements-file>"
    ```
    
    `/harden-artifact` available — "or harden the requirements first, recommended for a substantial
    change set:"
    
    ```
    claude --name harden-requirements-<slug> "/harden-artifact <requirements-file>"
    ```
    
    Lessons written and `/self-improve` available — "Persist the lessons:", or, under an execute
    command above, "Persist the lessons after the execute session:", since a mechanical lesson may edit
    a lint config or CI job the execution also touches:
    
    ```
    claude --name self-improve-<slug> "/self-improve Persist the lessons listed under Lessons in <answers-file>"
    ```
    
    Then offer the alternative: one line offering to clear the current session (vendor-agnostic —
    `/clear` is only the example) and run the next phase here, then the same labelled blocks with the
    bare prompts, under the same gates.
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.