ralph-specum-tasks
This skill should be used only when the user explicitly asks to use `$ralph-specum-tasks`, or explicitly asks Ralph Specum in Codex to run the tasks phase.
Install
npx skills add https://github.com/tzachbon/smart-ralph/tree/main/plugins/ralph-specum-codex/skills/ralph-specum-tasks
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install tzachbon-smart-ralph@llmmart
git clone https://github.com/tzachbon/smart-ralph.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole tzachbon/smart-ralph collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
Ralph Specum Tasks
You are a coordinator, not a task planner -- delegate ALL work to a task-planner sub-agent.
Derive RALPH_CODEX_PLUGIN_ROOT from this loaded skill by resolving two parent directories from the SKILL.md directory. Never derive it from the project working directory.
Contract
- Resolve the active spec by explicit path, exact name, or
.current-spec - Require
requirements.mdanddesign.md - Merge state fields only
- Keep the Ralph disk contract unchanged
Action
- Resolve the active spec. If none exists, stop.
- Require
requirements.mdanddesign.md. Readresearch.mdwhen present,.progress.md, and current state. - Run
phase_gate.py modethrough"$RALPH_CODEX_PLUGIN_ROOT/scripts/phase_gate.py"withSTATEand exact--quick, exact--interactive, or no flag. Reject both,-q, variants, and natural-language substitutes. - In interactive mode, require artifact approval for the current
design.mdbefore starting tasks. Exact quick mode continues with the validated artifact. - Run prototype record selection with the resolved
basePathbefore generation:python3 "$RALPH_CODEX_PLUGIN_ROOT/scripts/prototype_records.py" select-downstream --base-path "$BASE_PATH" --state "$BASE_PATH/.ralph-state.json" - Include only affected, valid,
gateApproved: true, non-superseded records returned by the selector. Exclude malformed, superseded, skipped, failed, inconclusive, cancelled, and normal-mode excluded records. - Stop before generation when selection reports an
activePrototypesblocker for tasks. Name the active ID and route resume through$ralph-specum-prototype. Allow proven unrelated prototypes when the selector reports no task dependency. - Stop when selection reports stale
design.md, stale task indexes, or a stale upstream artifact that design depends on. Route to the earliest stale phase and do not plan from stale design. - Clear any prior approval gate by merging
awaitingApproval: falsebefore generation. - Respect
granularityfrom state. Allow--tasks-size fine|coarseto override it. Treat task sizing as administration, not an interview question. In exact quick mode, default unset granularity tofine. - When
research.mdexists, require skill discovery pass 2 against the goal plus final research. When it is absent, require pass 1 against the goal alone. Run the applicable pass when the state lacks its revision. Select explicitly named skills and record harness-shadowed duplicates. - Load
"$RALPH_CODEX_PLUGIN_ROOT/skills/interview-framework-codex/SKILL.md", its required algorithm and domain-modeling references, and all selected domain contracts in both interactive and quick mode. In interactive mode, follow the algorithm for critical delivery slicing, dependency order, rollout risk, and verification thresholds. Inspect commands, file layout, and existing test tools instead of asking. - In interactive mode, require explicit
approve and delegate; in exact quick mode, recordbypassed_quick. In both modes, runphase_gate.py check-delegationwith the current loaded-manifest identity before creating the child. Apply the shared hard-transition invariant before task-planner dispatch. A failedcheck-delegationin either mode ends this invocation before phase transition, child dispatch, or target-artifact write; after a normal-mode failure, the next explicit invocation creates a fresh manifest/interview identity and does not create an alternate quick bypass. After an exact--quickdelegation failure, the next explicit invocation reruns discovery, records a freshphaseSkillLoadand interview identity, and does not reuse a terminalbypassed_quickinterview or its discovery revision. Only a matching in-progresscollectingorawaiting_confirmationinterview is resumable. - Delegate task planning to a
task-plannersub-agent. Pass the absolute helper path, state path, identity tuple, unique teammate dispatch identity, verbatim manifest, requirements, design, research, selected prototype evidence, the clean blocker/stale-gate result, and interview context. The child reloads and records the manifest, passescheck-agent-writewith that unique identity, and writestasks.md. Do NOT write tasks.md yourself. - Read the sub-agent's output and validate it exists.
- Count tasks and merge state with:
phase: "tasks"awaitingApproval: true(orfalsewhen--quickis active)taskIndex: first incomplete or totalTaskstotalTasks: counted tasks
- Update
.progress.mdwith the phase breakdown, next milestone, blockers, next step, chosen granularity, skill discovery, and verification strategy. - If spec commits are enabled, commit only the spec artifacts.
Stop Behavior
- Without
--quick: STOP HERE. Display the walkthrough summary and approval prompt. Do NOT continue to implementation. Wait for the user to explicitly approve and request the next phase. - With exact
--quick: Record the quick bypass, review, then continue directly into implementation.
Output Shape
Use atomic tasks with exact file targets, explicit success criteria, verification commands, and commit messages. Preserve POC-first ordering. Support [P] markers for safe parallel work, [VERIFY] checkpoints, and VE tasks when end-to-end verification is part of the plan.
Response Handoff
- After writing
tasks.md, nametasks.mdand summarize the task plan briefly. - When normalized
quickModeis false, end with exactly one explicit choice prompt:approve current artifactrequest changescontinue to implementation
- Treat
continue to implementationas approval oftasks.md. - With exact
--quick, do not show this prompt; continue directly to implementation after the gates succeed. - During artifact review,
apply the changesimmediately delegates already-recorded feedback through a new unique dispatch, redisplays the artifact, and stays at this approval gate. Ask one focused change question only when no feedback is pending. Control-onlycontinue,proceed, andgo aheadapprove nothing.
Files (smart-ralph)
-
agents
-
openai.yaml 1.1 KB
interface: display_name: "Ralph Specum Tasks" short_description: "Plan gated tasks with approved prototype evidence" default_prompt: "Use $ralph-specum-tasks to load the selected skill manifest in every mode and select valid prototype evidence. In interactive mode, classify replies, grill critical delivery decisions, and persist the explicit `approve and delegate` choice with confirm source approve-and-delegate; only exact --quick bypasses questions. Run phase_gate.py check-delegation before dispatch. Route active prototype blockers through $ralph-specum-prototype. Require the task agent to record manifest loads and pass check-agent-write with the full identity tuple, including discovery revision, before writing tasks.md. Refuse dispatch or artifact writes on any gate or required-load failure. Keep the next implementation decision with the parent coordinator. Ask me to `approve current artifact`, `request changes`, or `continue to implementation` only when quickMode is false; exact --quick continues after successful gates without prompting." policy: allow_implicit_invocation: false
-
-
SKILL.md 6.3 KB
--- name: ralph-specum-tasks description: This skill should be used only when the user explicitly asks to use `$ralph-specum-tasks`, or explicitly asks Ralph Specum in Codex to run the tasks phase. metadata: surface: helper action: tasks --- # Ralph Specum Tasks You are a **coordinator, not a task planner** -- delegate ALL work to a `task-planner` sub-agent. Derive `RALPH_CODEX_PLUGIN_ROOT` from this loaded skill by resolving two parent directories from the `SKILL.md` directory. Never derive it from the project working directory. ## Contract - Resolve the active spec by explicit path, exact name, or `.current-spec` - Require `requirements.md` and `design.md` - Merge state fields only - Keep the Ralph disk contract unchanged ## Action 1. Resolve the active spec. If none exists, stop. 2. Require `requirements.md` and `design.md`. Read `research.md` when present, `.progress.md`, and current state. 3. Run `phase_gate.py mode` through `"$RALPH_CODEX_PLUGIN_ROOT/scripts/phase_gate.py"` with `STATE` and exact `--quick`, exact `--interactive`, or no flag. Reject both, `-q`, variants, and natural-language substitutes. 4. In interactive mode, require artifact approval for the current `design.md` before starting tasks. Exact quick mode continues with the validated artifact. 5. Run prototype record selection with the resolved `basePath` before generation: ```bash python3 "$RALPH_CODEX_PLUGIN_ROOT/scripts/prototype_records.py" select-downstream --base-path "$BASE_PATH" --state "$BASE_PATH/.ralph-state.json" ``` 6. Include only affected, valid, `gateApproved: true`, non-superseded records returned by the selector. Exclude malformed, superseded, skipped, failed, inconclusive, cancelled, and normal-mode excluded records. 7. Stop before generation when selection reports an `activePrototypes` blocker for tasks. Name the active ID and route resume through `$ralph-specum-prototype`. Allow proven unrelated prototypes when the selector reports no task dependency. 8. Stop when selection reports stale `design.md`, stale task indexes, or a stale upstream artifact that design depends on. Route to the earliest stale phase and do not plan from stale design. 9. Clear any prior approval gate by merging `awaitingApproval: false` before generation. 10. Respect `granularity` from state. Allow `--tasks-size fine|coarse` to override it. Treat task sizing as administration, not an interview question. In exact quick mode, default unset granularity to `fine`. 11. When `research.md` exists, require skill discovery pass 2 against the goal plus final research. When it is absent, require pass 1 against the goal alone. Run the applicable pass when the state lacks its revision. Select explicitly named skills and record harness-shadowed duplicates. 12. Load `"$RALPH_CODEX_PLUGIN_ROOT/skills/interview-framework-codex/SKILL.md"`, its required algorithm and domain-modeling references, and all selected domain contracts in both interactive and quick mode. In interactive mode, follow the algorithm for critical delivery slicing, dependency order, rollout risk, and verification thresholds. Inspect commands, file layout, and existing test tools instead of asking. 13. In interactive mode, require explicit `approve and delegate`; in exact quick mode, record `bypassed_quick`. In both modes, run `phase_gate.py check-delegation` with the current loaded-manifest identity before creating the child. Apply the shared hard-transition invariant before task-planner dispatch. A failed `check-delegation` in either mode ends this invocation before phase transition, child dispatch, or target-artifact write; after a normal-mode failure, the next explicit invocation creates a fresh manifest/interview identity and does not create an alternate quick bypass. After an exact `--quick` delegation failure, the next explicit invocation reruns discovery, records a fresh `phaseSkillLoad` and interview identity, and does not reuse a terminal `bypassed_quick` interview or its discovery revision. Only a matching in-progress `collecting` or `awaiting_confirmation` interview is resumable. 14. **Delegate** task planning to a `task-planner` sub-agent. Pass the absolute helper path, state path, identity tuple, unique teammate dispatch identity, verbatim manifest, requirements, design, research, selected prototype evidence, the clean blocker/stale-gate result, and interview context. The child reloads and records the manifest, passes `check-agent-write` with that unique identity, and writes `tasks.md`. Do NOT write tasks.md yourself. 15. Read the sub-agent's output and validate it exists. 16. Count tasks and merge state with: - `phase: "tasks"` - `awaitingApproval: true` (or `false` when `--quick` is active) - `taskIndex: first incomplete or totalTasks` - `totalTasks: counted tasks` 17. Update `.progress.md` with the phase breakdown, next milestone, blockers, next step, chosen granularity, skill discovery, and verification strategy. 18. If spec commits are enabled, commit only the spec artifacts. ### Stop Behavior - **Without `--quick`**: STOP HERE. Display the walkthrough summary and approval prompt. Do NOT continue to implementation. Wait for the user to explicitly approve and request the next phase. - **With exact `--quick`**: Record the quick bypass, review, then continue directly into implementation. ## Output Shape Use atomic tasks with exact file targets, explicit success criteria, verification commands, and commit messages. Preserve POC-first ordering. Support `[P]` markers for safe parallel work, `[VERIFY]` checkpoints, and VE tasks when end-to-end verification is part of the plan. ## Response Handoff - After writing `tasks.md`, name `tasks.md` and summarize the task plan briefly. - When normalized `quickMode` is false, end with exactly one explicit choice prompt: - `approve current artifact` - `request changes` - `continue to implementation` - Treat `continue to implementation` as approval of `tasks.md`. - With exact `--quick`, do not show this prompt; continue directly to implementation after the gates succeed. - During artifact review, `apply the changes` immediately delegates already-recorded feedback through a new unique dispatch, redisplays the artifact, and stays at this approval gate. Ask one focused change question only when no feedback is pending. Control-only `continue`, `proceed`, and `go ahead` approve nothing.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.