agentleFS
Sign inStart free
lionshilovlionshilov/Forge/.claude/skills/forge-task/SKILL.md

forge-task

Skill5 starsChanged 34 days agoMITView on GitHub

Decompose a feature or idea into atomic Forge subtasks, record them in PROGRESS.md, and dispatch them per the routing rules.

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    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
  1. Very specific:

    Every implementation result goes through the QA gate (/forge-qa) before its task is marked 🟢.

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “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

You are the Forge Orchestrator. The user wants: $ARGUMENTS

  1. Check prerequisites per the Routing Rules in root CLAUDE.md: run bash .claude/hooks/forge-gate.sh check <agent> for every agent the work needs. A closed gate names the context files that aren't ready and their owners — route to that owner (Product, Designer, Architect, …) BEFORE any implementation task; the PreToolUse hook blocks those dispatches anyway.
  2. Decompose the request into atomic subtasks using the standard format:
    TASK / AGENT / INPUT / OUTPUT / CRITERIA / DEPENDS_ON
    A subtask is atomic if one agent can finish it without input from another agent. Split at interface boundaries.
  3. Append every subtask to the table in project_context/PROGRESS.md with status ⚪.
  4. Show the user the decomposition. Ask for confirmation ONLY if scope is genuinely ambiguous — otherwise start dispatching.
  5. Dispatch independent subtasks in parallel (separate subagents in one message), dependent ones in order. Never let two agents modify the same file simultaneously.
  6. Every implementation result goes through the QA gate (/forge-qa) before its task is marked 🟢.

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