agentleFS
Sign inStart free
CG-5228CG-5228/ClaudeCodeImpactLab_hackathon/skills/start/SKILL.md

start

Skill1 starsChanged 14 days agoMITView on GitHub

Start a StopCode mission for this project - save the original objective, set a few practical completion criteria, and begin tracking. Use when the user runs /stopcode:start or asks to begin a tracked mission.

130 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-engine, team-audio and 10 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.
  • CoralGameSkill

    setup-engine

    Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.

    Also in 13 projects that use this

  • CoralGameSkill

    team-audio

    Orchestrate audio team: audio-director + sound-designer + technical-artist + gameplay-programmer for full audio pipeline from direction to implementation.

    Also in 13 projects that use this

  • lilangMaxSkill

    create-stories

    Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.

    Also in 11 projects that use this

  • lilangMaxSkill

    story-done

    End-of-story completion review. Reads the story file, verifies each acceptance criterion against the implementation, checks for GDD/ADR deviations, prompts code review, updates story status to Complete, and surfaces the next ready story from the sprint.

    Also in 11 projects that use this

  • +5 more from CoralGame
  • +3 more from lilangMax

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 117 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the mission text is empty, ask one short question: "What is the one goal for this session?" Then continue with the answer.

    line 17
  2. Distinctive:

    Run exactly one command (the project is detected from the current working directory):

    line 19
  3. Distinctive:

    If a previous mission existed, the command preserves it in history and says so.

    line 27
  4. Distinctive:

    Do not begin implementing the mission in this turn unless the user explicitly asked for that as well.

    line 31

“Common” is measured: kept by at least 6 in 10 of the 117 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

/stopcode:start

Mission text from the user: $ARGUMENTS

StopCode keeps the original goal immutable and visible so the day does not quietly expand. This skill records it; it does not start the work.

Steps

  1. If the mission text is empty, ask one short question: "What is the one goal for this session?" Then continue with the answer. Do not run a long onboarding.
  2. Derive 2 to 4 practical completion criteria: observable checks a person could verify (for example "auth tests pass", "login rejects an empty password with 400", "README documents the flag"). Keep them small and faithful to the goal; do not add requirements the user did not imply. If the text contains --budget <minutes>, treat it as an optional advisory time budget.

  3. Run exactly one command (the project is detected from the current working directory):

    node "${CLAUDE_PLUGIN_ROOT}/bin/stopcode.js" start "<objective>" --criteria "<criterion 1>" --criteria "<criterion 2>" [--budget <minutes>]

    Pass --project "<path>" only if the user explicitly named a different project directory.

  4. Report the command's output in at most 6 lines: the saved objective, the criteria with their ids, and that tracking has begun. Mention /stopcode:status and /stopcode:finish.
  5. If a previous mission existed, the command preserves it in history and says so; repeat that to the user.

Rules

  • Do not begin implementing the mission in this turn unless the user explicitly asked for that as well.
  • Later requests that go beyond this objective are recorded, not silently absorbed: stopcode scope accept "<text>" for an accepted addition, stopcode idea add "<text>" to park an idea for later.
  • Evidence for criteria is recorded with stopcode evidence add --kind test_run --outcome pass|fail|unknown --summary "<what ran>" --criterion <id>; a file edit alone is not evidence that a criterion is met.

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