implementation
Skill2 starsChanged 34 days agoMITView on GitHub
Craft phase 5 - execute the plan part by part, one part-implementer agent each, sequential, with per-part gates and one phase-boundary gate.
18 other projects use a version of this.
Adopted by
Most recently taken up by
- GravionLabs/skillstheir own version, first seen Nov 15, 2026
- thunderstormwang/AgentSkillstheir own version, first seen Nov 6, 2026
- Zejnilovic/agdtheir own version, first seen Nov 1, 2026
- jackstine/forgectltheir own version, first seen Nov 1, 2026
- grace-method/grace-plugintheir own version, first seen Oct 25, 2026
- JosefGisis/skillstheir own version, first seen Oct 20, 2026
Used with
Projects with it also use bug-fix, investigate and 3 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
u9401066Skillbug-fix
Structured bug fixing workflow with root cause analysis and regression prevention. Triggers: BF, 修 bug, fix bug, debug, 除錯, 錯誤, error, 問題, issue, 修復, fix, 故障, fault, 異常, exception, 失敗, failure, 不能用, broken, 壞掉.
Also in 3 projects that use this
VercelSkillinvestigate
Investigate an issue report, or analyze the constraints of a proposed change, with strict, evidence-driven diagnosis.
Also in 3 projects that use this
MicrosoftSkillplaywright-cli
Automate browser interactions, test web pages and work with Playwright tests.
Also in 4 projects that use this
MicrosoftSkillrelease
Use ONLY when the user explicitly asks to cut/publish a Huabu desktop release or tag a version. Performs an outward action — bumps the version in apps/desktop/package.json, commits + annotated-tags vX.Y.Z, and pushes the branch + tag. That tag push auto-builds the macOS/Windows installers and publishes a GitHub Release. Provides `status`, `bump`, `tag-push`, and a one-command `run` (bump → tag-push).
Also in 4 projects that use this
SentrySkillskill-creator
Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.
Also in 4 projects that use this
Other versions18 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 18
- bholmesdev/hubble.md★ 1.5ksame name
- ceedaragents/cyrus★ 888same name
- cyrusagents/cyrus★ 888same name
- EmeaAppGbb/spec2cloud★ 100same name
- jackstine/forgectl★ 8same name
- Zejnilovic/agd★ 5same name
- crgarcia12/Liliput★ 4same name
- websublime/mister-anderson★ 3same name
- jvalin17/agent-toolkit★ 2same name
- JosefGisis/skills★ 1same name
8 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository20 other files it gives its agents.
- architectureSkill
- decisionsSkill
- designSkill
- documentationSkill
- impact-triageSkill
- initSkill
- integrateSkill
- lessonsSkill
- metricsSkill
- planningSkill
- promote-configSkill
- proposeSkill
- pruneSkill
- refactoringSkill
- requirementsSkill
- reviewSkill
- runSkill
- tuneSkill
- validationSkill
- workspaceSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 17 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 63
Phase-boundary gate: after the LAST part, run gates.phase once in-session.
“Common” is measured: kept by at least 6 in 10 of the 17 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
craft:implementation
Preamble (always runs — non-overridable)
- Manifest read (lint if standalone). Probe gates:
gates.part(else: repo test runner over touched files; else fall back togates.phaseper part — slower, never gateless) andgates.phase(else: repo validate/check/test script; if nothing exists, REFUSE to run this phase — a workflow without any gate is not this workflow). - The plan must exist and pass
plan-lint.sh(re-run it; cheap) — unless no plan exists at<plan-dir>/<slug>.mdand the run record holds aNO-OP(planning):line (grep -F 'NO-OP(planning):'on the ledger path thatrun-ledger.sh locateor the reorient block yields). Then the phase is a no-op: spawn nothing, append noPARTline, skip Procedure 1–2, and rungates.phaseonce in-session (the Procedure 3 gate — the phase is never gateless, even here; a manifestoverride:cannot skip it). On green, onerun-ledger.sh append <run-id> implementationcall carriesNO-OP(implementation): no plan parts — planning recorded NO-OP(planning),GATE(implementation): greenandPHASE-DONE(implementation): no-op — no plan parts. On red, append theNO-OPline andGATE(implementation): redwithoutPHASE-DONE, fix and commit as Procedure 3 states, re-run the gate, and append its result:PHASE-DONElands only with a green gate, so a rebuild never reads a red phase as closed. A plan file that exists next to aNO-OP(planning):line is a contradiction: escalate{ implementation, reason, ≤3 options }, never guess which wins. No plan and noNO-OP(planning):line (standalone included): refuse, as before. - Memory read/write surface (advisory).
READS:
gate-cmdentry for this repo as an advisory hint — if a gate command was previously recorded, skip re-discovery but still run it (the gate is sacred; the hint only saves the probe, never the execution). A miss falls through to the full gate probe. WRITES (appended to the run record as produced; saved to the store once atDone): the gate/test command discovered this run — stored as the BARE command only, with any leading env/secret assignment prefix stripped (neverTOKEN=… npm testor a command carrying a credential), since the store is committed; per-partsize+ pass/blockedoutcomefor each implemented part.
Procedure (default body — a manifest override: replaces everything below)
- Execute parts top-to-bottom, one craft:part-implementer per part,
sequential — never two agents writing one tree concurrently. Each spawn carries:
the working directory; the plan path (the agent reads the part there) + the part's
### Contextblock verbatim AND any load-bearing deltas — hand the pre-chew over so the agent never re-greps the codebase, but do NOT re-transcribe the whole committed part; the design doc path; the resolved part gate; the commit message from the plan; global + implementation-phasecontext:files verbatim. - After each agent returns, verify before launching the next: the commit exists
and matches the part promise (
git log,git show --stat). Once verified, in that same verification's Bash call or the very next one, appendPART(<n>): <sha> size=<size> outcome=<pass|blocked>via"${CRAFT_ROOT:-${CLAUDE_PLUGIN_ROOT}}/scripts/run-ledger.sh" append <run-id> implementation—<size>is one kebab-case shape label for the part (e.g.pure-module,docs-prose),?when unknown; a label with a space breaks the token. A landed commit found without aPARTline on resume is verified first, then gets its line. Spot-check conventions on the diff. EveryIMPACT(line and deferred observation in the handback gets its verdict under the run skill invariant Impacts: fold or defer at discovery before the next part spawns. Failed/blocked part → fix in-session or escalate with the agent's options; dead agent → fresh respawn from the plan part (artifact handoff); never relaunch blindly. - Phase-boundary gate: after the LAST part, run
gates.phaseonce in-session. It MUST be green before the review phase — fix and commit anything it surfaces (fix(<scope>): close gate gap after part N).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

