run
goalforge-internal — use entry commands; do not auto-trigger Chain driver for the goalforge stages: capture → spec → decompose → harden → execute → verify. Reads the target's on-disk `status:` and enters the one step that status admits; supports --dry-run. Use it to drive a feature end-to-end; for a single stage, use the entry command for that stage.
- License 许可
- MIT
- 最近更新
- 2026-11-12
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- run
- metadata
- { "version": "2.0.0", "skill-kind": "preference" }
- description
- goalforge-internal — use entry commands; do not auto-trigger Chain driver for the goalforge stages: capture → spec → decompose → harden → execute → verify. Reads the target's on-disk `status:` and enters the one step that status admits; supports --dry-run. Use it to drive a feature end-to-end; for a single stage, use the entry command for that stage.
02 资源文件 5
- 参考文档chain.yaml2.8 KB
- 脚本scripts/goalforge-plan-consumer.sh9.5 KB
- 脚本scripts/goalforge-router.sh4.7 KB
- 参考文档workflows/captured-full-chain.md630 B
- 参考文档workflows/README.md558 B
03 SKILL.md 正文
goalforge-run
Sibling chain.yaml declares the step sequence; never reorder or extend it here
(that is /skill-improve). <PLANS_ROOT> resolves per
${CLAUDE_PLUGIN_ROOT}/references/schema.md.
Steps
-
Resolve the target: a feature slug (chain entry) or a WP slug (mid-chain).
-
Read its on-disk
status:and enter the single step that status admits:status:target next step child skill gate (none yet) feature capture goalforge-capture— draftfeature spec goalforge-spechuman specfeature spec (ratify) goalforge-spechuman at spec → readyreadyfeature decompose goalforge-decomposeauto specWP harden goalforge-hardenhuman at hardened → readyhardenedWP harden (re-entry) goalforge-hardenhuman at hardened → readyready/executingWP execute (resume) goalforge-executeauto implementedWP verify goalforge-verifyauto verified/abandoned/archivedWP — — complete -
Run that step by reading
${CLAUDE_PLUGIN_ROOT}/skills/<child>/SKILL.mdand following it in-session. At a human gate stop and ask; underSDD_AUTONOMY=unattended, park. -
On return, re-read
status:and repeat untilverifiedor a step parks. -
--dry-run: print each step, its resolved skill path, its precondition, and whether the target satisfies it. Zero side effects — no files written, no subagents dispatched, no status mutated.bash ${CLAUDE_PLUGIN_ROOT}/skills/run/scripts/goalforge-router.sh --dry-run <feature>
Workflows
run/workflows/ holds the compiled Workflow scripts — the output of
scripts/goalforge-workflow-compile.py, one run/workflows/<wp>.js per work
package. goalforge-execute compiles the WP checklist into that file and
launches it through the Workflow tool; nothing in this directory is
hand-edited.
Gotchas
- Routing keys entirely off the on-disk
status:— a hand-edited or drifted value matches no step and the driver halts rather than guessing. Fix the status, do not force re-entry. - The status is re-read at every resume: a parallel session that advanced the WP moves the entry point under you. Re-check before resuming a suspended chain.
04 同仓库更多 Skills
wayfind
goalforge-internal — use entry commands; do not auto-trigger Chart a foggy, multi-session effort into a decision map BEFORE goalforge-capture — when the work is too big to spec yet, spans multiple sessions, and needs a decision map before anyone can write a real spec. Triggers: "chart this foggy effort", "multi-session decision map", "too big to spec yet", "map the unknowns before we plan". Establishes <PLANS_ROOT>/<effort>/wayfind/ (map.md pointer-index + one-decision-per-ticket files), drives a frontier-computed work loop across sessions, and graduates the converged map into goalforge-capture. SKIP when the effort is one session and already clear — a single well-understood feature goes straight to goalforge-capture with no map. SKIP for a bounded one-off edit, and for anything already past spec (that is the SDD chain, not wayfind).
verify
goalforge-internal — use entry commands; do not auto-trigger Verify a work package at `status: implemented`: gate A deterministic (lint, typecheck, verification.command, diff ⊆ owned_files), gate B one fresh-context review of the WP diff, gate C goal judge plus one second opinion. Advances `implemented → verified` — the sole authority for that edge. TRIGGER: /verify <wp-path>, or when the chain reaches the verify step.
spec
goalforge-internal — use entry commands; do not auto-trigger Run a design pass on a captured feature and propose the spec document, or propose a revision of an approved spec when a learning falsifies it (the respec edge). Reads plans/<feature>/overview.md, optionally invokes personas or architect for a multi-lens review, writes plans/<feature>/spec.md from the feature-spec template as the proposal (draft → spec), and ratifies it on spec → ready. HUMAN-GATED: spec → ready needs explicit user approval. Trigger: the user asks to spec, design, or elaborate on a feature that already has an overview.md (status: draft), or a feature sits at status: spec with a proposal awaiting ratification.
redecompose
goalforge-internal — use entry commands; do not auto-trigger Reconcile a proposed re-decomposition against a partially-executed feature's verified WPs. Calls goalforge-reconcile-diff.sh to produce a 5-bucket diff, then routes: same → untouched (no-op), changed+new → status: spec and onto the harden frontier via goalforge-transition.sh, dropped-verified → supersede in place (ledger row, never delete), ambiguous (slug changed, goal matches a verified WP) → judgment/human — never auto-rename or auto-supersede. Logs goal mutations via goalforge-goal-changelog.sh. Idempotent: re-run on unchanged decomposition is a byte-identical no-op. TRIGGER: /goalforge-redecompose <feature-dir> --learning '<text>' or when goalforge-run loops back on a learning event.
prototype
goalforge-internal — use entry commands; do not auto-trigger Throwaway spike answering exactly ONE design question with runnable code — logic branch (pure logic module + interactive terminal harness, LOGIC.md), UI branch (several radically different variations, UI.md), or perf branch (benchmark study of rival implementations with a scaling curve, PERF.md). Keep the answer, delete the code. Use when an open question is of kind "how should it behave / which approach wins / how should it look / is it fast enough, does it scale, is the optimization worth it" and more interviewing or reading will not settle it — a spike will. Entry points: handoff mode `prototype` (cross-session dispatch seam), goalforge-harden open-question routing, idea-refine, or the user saying "spike this" / "quick prototype to check" / "benchmark this". Refuses to start without a single question AND explicit success criteria.
plan-index
goalforge-internal — use entry commands; do not auto-trigger Generate plans/INDEX.md -- a DERIVED feature register + cross-feature dependency DAG + topological build-order tiers + cycle/orphan detection -- by harvesting each feature overview's `relationships:` frontmatter. The frontmatter is the single source of truth; the index is regenerated, never hand-synced. Use to (re)build or refresh a plans portfolio index after adding/changing features, to see the build order, or to find dependency cycles and orphaned features. TRIGGER: 'generate the plan index', 'rebuild plans/INDEX.md', 'show the feature dependency graph', 'what is the build order', 'find plan cycles/orphans'. Pairs with goalforge-archive's reference-gate (idea: goalforge-plan-index-and-portfolio-housekeeping).