Claude Skill

next

Report unfinished brief/propose/ship work in this repo and the exact command to resume each, ranked by what to do now. Use when the user asks "what's next", "what's left", "where do I resume", "/next", "la suite", or to re-orient after a context reset. Reads artifact frontmatter

LLM Mart · 0 points · 18 views 0 listing impressions 0 install-command copies
Virus-scanned Reviewed automatically before listing.

Full trust report

Download mirkobozzetto-arsenal-plugins_next_skills_next-ca70c8a.zip · 5 KB
Part of mirkobozzetto/arsenal — 7 skills

Install

skills CLI npx skills add https://github.com/mirkobozzetto/arsenal/tree/main/plugins/next/skills/next
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install mirkobozzetto-arsenal@llmmart
Git git clone https://github.com/mirkobozzetto/arsenal.git

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

Skill manifest

Next

Run scripts/scan.cjs from the intended repository, not the launch directory by assumption. --json is for tooling; --all includes completed work. The scanner recognizes shipped markers as terminal.

Report the most useful open action. Do not re-read every artifact body after a sufficient scan. Read a specific artifact only for a requested detail. Distinguish implemented work waiting for user acceptance from work to redo. An old todo or reminder is not evidence that a completed fix needs another diagnosis. Never execute the recommended action without a user request.

Arsenal handoff

Return the open-work result to Arsenal when it called this skill. A request to resume work authorizes Arsenal to inspect the selected artifact and choose the next step; a status-only request stops here. Never reopen shipped work.

Execution policy

Work solo. Ask before any subagent or reviewer, even in auto mode. Explain the independent scope and expected benefit first. No hidden advisor, nested delegation, model retuning, repeated successful checks, or progress spam. Use existing context before asking questions. Stop when the requested result is delivered. User stops and scope changes override pending steps.

Files (arsenal)
  • references
    • state-contract.md 2.2 KB
      # State contract
      
      The frontmatter fields the brief/propose/ship skills maintain so `next` can derive the open-work board. The artifact is the single source of truth; there is no separate ledger.
      
      ## brief.md frontmatter
      
      | Field | Set by | Values |
      |-------|--------|--------|
      | `status` | brief (draft -> ready), ship (-> shipped) | `draft`, `ready`, `in_progress`, `shipped`, `superseded` |
      | `next_action` | brief at finalize | one line: what shipping this does |
      | `resume_cmd` | brief at finalize | `/ship docs/brief/<slug>` |
      | `shipped_at` | ship on finish | ISO timestamp |
      | `proposal` | propose at finalize, when it designs this brief | path to the sibling `PROPOSAL.md` |
      
      `tasks.md` checkbox counts (`- [ ]` vs `- [x]`) give progress.
      
      A brief whose HOW moved into a proposal is set `superseded` by propose at
      finalize: it leaves the board, and ship has ONE target for the feature
      instead of two.
      
      ## PROPOSAL.md frontmatter
      
      | Field | Set by | Values |
      |-------|--------|--------|
      | `status` | propose (Draft -> Review -> Accepted), ship (-> shipped) | `Draft`, `Review`, `Accepted`, `Rejected`, `shipped` |
      | `next_action` | propose at finalize | one line |
      | `resume_cmd` | propose at finalize | `/ship <path>/PROPOSAL.md` |
      | `source_brief` | propose at init, when a sibling brief exists | `docs/brief/<slug>/` |
      
      PROPOSAL.md is otherwise immutable. The only mutation ship makes is the `status` flip to `shipped` on finish; if that immutability must be absolute, ship instead writes a sibling `PROPOSAL.shipped` marker and the scanner treats its presence as shipped.
      
      ## The loop
      
      ship closes the loop at finish: a `shipped` run flips the upstream `status`, which removes the item from the board on the next scan. A `halted`/paused run stamps `status: in_progress` + `resume_cmd: /ship -r <artifact>`. This is what prevents a stale "ready"/"Accepted" item from lingering after the work is done.
      
      ## Buckets (how the scanner classifies)
      
      - OPEN (actionable): brief `ready`/`in_progress`, propose `Accepted`.
      - WIP (authoring): brief `draft`, propose `Draft`/`Review`.
      - DONE (hidden by default): `shipped`, `superseded`, `Rejected`.
      - roadmap (`type: roadmap`): OPEN when `ready`, else WIP; `superseded` is DONE.
      
  • scripts
    • scan.cjs 8.7 KB · in bundle
  • SKILL.md 1.4 KB
    ---
    name: next
    description: Report unfinished work and the exact next action from existing artifact states. Never resume or implement automatically.
    argument-hint: "[--all] [feature]"
    ---
    
    # Next
    
    Run scripts/scan.cjs from the intended repository, not the launch directory
    by assumption. --json is for tooling; --all includes completed work. The
    scanner recognizes shipped markers as terminal.
    
    Report the most useful open action. Do not re-read every artifact body after
    a sufficient scan. Read a specific artifact only for a requested detail.
    Distinguish implemented work waiting for user acceptance from work to redo.
    An old todo or reminder is not evidence that a completed fix needs another
    diagnosis. Never execute the recommended action without a user request.
    
    ## Arsenal handoff
    
    Return the open-work result to Arsenal when it called this skill. A request
    to resume work authorizes Arsenal to inspect the selected artifact and choose
    the next step; a status-only request stops here. Never reopen shipped work.
    
    ## Execution policy
    
    Work solo. Ask before any subagent or reviewer, even in auto mode. Explain
    the independent scope and expected benefit first. No hidden advisor, nested
    delegation, model retuning, repeated successful checks, or progress spam.
    Use existing context before asking questions. Stop when the requested result
    is delivered. User stops and scope changes override pending steps.
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.

Related