agentleFS
Sign inStart free
websublimewebsublime/mister-anderson/skills/implementation/SKILL.md

implementation

Skill3 starsChanged 7 months agoMITView on GitHub

Stage 3 orchestrator — guides Implementation for a phase: shows task progress, routes through investigate → do → review → quality per task.

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use bug-fix, playwright-cli and 2 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.
  • u9401066Skill

    bug-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

  • MicrosoftSkill

    playwright-cli

    Automate browser interactions, test web pages and work with Playwright tests.

    Also in 4 projects that use this

  • MicrosoftSkill

    release

    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

  • SentrySkill

    skill-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

The file

Show its rules and text

We split this skill into the rules it gives an agent

21 rules. 0 are common, 10 are distinctive, and 11 are very specific to this project.

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 10

    Distinctive

    This author's own choices. Worth a look.

  • 11

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user provides $ARGUMENTS, analyze them for:

    line 14
  2. Very specific:

    Beads must exist for the phase: Check bd list --status=open --json for matching epics.

    line 21
  3. Very specific:

    Spec should be APPROVED: Check docs/specs/{NN}-spec-*.md if phase number provided.

    line 22
  4. Very specific:

    No beads found for this phase.

    line 26
  5. Distinctive:

    If no bead ID was provided in arguments:

    line 60
  6. Very specific:

    Run bd ready to show unblocked tasks

    line 61
  7. Distinctive:

    Ask: "Which task do you want to work on?"

    line 63
  8. Very specific:

    Check if investigation already exists for this bead (search comments for INVESTIGATION:).

    line 71
  9. Very specific:

    If exists → ask if user wants to re-investigate or skip to /do

    line 72
  10. Very specific:

    If not → dispatch: Skill(skill="investigate", args="{BEAD_ID}")

    line 73
  11. Distinctive:

    Wait for completion before proceeding.

    line 75
  12. Very specific:

    Wait for supervisor to complete.

    line 83
  13. Very specific:

    Check if bead has needs-review label.

    line 89
  14. Very specific:

    If yes → dispatch: Skill(skill="review", args="{BEAD_ID}")

    line 90
  15. Distinctive:

    If no → inform user the task is not ready for review

    line 91
  16. Distinctive:

    If no → inform user the task hasn't passed code review yet

    line 101
  17. Distinctive:

    Ask user if they want to close the bead

    line 108
  18. Distinctive:

    If more ready tasks exist, ask: "Pick the next task?"

    line 110
  19. Distinctive:

    If all tasks complete, show phase completion summary

    line 111
  20. Distinctive:

    If more tasks remain → pick next task

    line 121
  21. Very specific:

    If phase complete → recommend starting next phase with /specification {NN+1} or check overall status with /workflow </on-next>

    line 122

“Common” is measured: kept by at least 6 in 10 of the 15 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Implementation (Stage 3 Orchestrator)

Guide the user through Stage 3 — Implementation for a specific phase. Shows task progress and routes through the per-task pipeline.

<on-init> If the user provides $ARGUMENTS, analyze them for: - A phase number (e.g., `01`, `02`) — optional, used to filter tasks - A bead ID (e.g., `bd-a3f`, `bd-001.2`) — jump directly to that task - `status` — show current implementation state only </on-init><on-check> 1. **Beads must exist for the phase.** Check `bd list --status=open --json` for matching epics. 2. **Spec should be APPROVED.** Check `docs/specs/{NN}-spec-*.md` if phase number provided. </on-check><on-check-fail if="beads"> No beads found for this phase. Recommend running `/specification {NN}` or `/tasks` first. </on-check-fail><on-state> Show implementation progress:
bd ready
bd list --status=in_progress
bd blocked

Display:

Stage 3 — Implementation (Phase {NN})
  Progress: {completed}/{total} tasks complete
  Ready:       {list of ready task IDs with titles}
  In progress: {list of in-progress task IDs with titles}
  In review:   {list of in-review task IDs with titles}
  Blocked:     {count}

For each task, show its pipeline position:

  • [ ] — not started
  • [investigate] — investigation done, awaiting implementation
  • [do] — implementation in progress
  • [review] — awaiting or in code review
  • [quality] — awaiting or in QA
  • [done] — closed</on-state>
<on-step name="pick"> **Pick a task** — Select the next task to work on.

If no bead ID was provided in arguments:

  1. Run bd ready to show unblocked tasks
  2. Present list with: ID, title, priority, labels, pipeline position
  3. Ask: "Which task do you want to work on?"

Determine the task's current pipeline position and route to the appropriate step. </on-step>

<on-step name="investigate"> **Investigate** — Run codebase analysis before implementation.

Check if investigation already exists for this bead (search comments for INVESTIGATION:).

  • If exists → ask if user wants to re-investigate or skip to /do
  • If not → dispatch: Skill(skill="investigate", args="{BEAD_ID}")

Wait for completion before proceeding. </on-step>

<on-step name="do"> **Implement** — Dispatch the implementation supervisor.

Dispatch: Skill(skill="do", args="{BEAD_ID}")

Wait for supervisor to complete. After completion, the bead should be in-review with needs-review label. </on-step>

<on-step name="review"> **Review** — Run code review gate.

Check if bead has needs-review label.

  • If yes → dispatch: Skill(skill="review", args="{BEAD_ID}")
  • If no → inform user the task is not ready for review

The /review skill handles auto-dispatching rework if needed. </on-step>

<on-step name="quality"> **QA** — Run quality assurance gate.

Check if bead has approved label.

  • If yes → dispatch: Skill(skill="quality", args="{BEAD_ID}")
  • If no → inform user the task hasn't passed code review yet

The /quality skill handles auto-dispatching rework if needed. </on-step>

<on-complete> After QA passes: 1. Ask user if they want to close the bead 2. Re-scan implementation state 3. If more ready tasks exist, ask: "Pick the next task?" 4. If all tasks complete, show phase completion summary
Stage 3 — Implementation (Phase {NN}): COMPLETE
  All {total} tasks closed
  Ready for merge to main
</on-complete><on-next> - If more tasks remain → pick next task - If phase complete → recommend starting next phase with `/specification {NN+1}` or check overall status with `/workflow` </on-next>

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free