agentleFS
Sign inStart free
unclejobs-aiunclejobs-ai/second-claude-code/skills/godhands/SKILL.md

godhands

Skill41 starsChanged 7 days agoMITView on GitHub

Use when a request needs extra hands that find, analyze, plan, decompose, benchmark, and improve through gated gather, draft, check, and cut. Do not use merely because a request is vague; vagueness takes a clarifying question, not a full pass.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    Do not dispatch Pokemon filenames.

    line 56

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Resolve runtime paths before file or script operations.

Iron Law

When God Hands is selected, honor the phase gates. Do not skip Check.

God Hands is the public name of the gated knowledge-work pass: find, analyze, plan, decompose, benchmark, improve. The runtime state and MCP tools stay pdca_*. /scc:pdca is the slash-only compat name.

When to Use

  • End-to-end knowledge work that must find sources, analyze them, plan, draft, check, and improve
  • The user says "research and write", names a full pass, or asks for extra hands on the work
  • A fork is already settled or does not apply (/scc:coach first when it does)

When Not to Use

  • The user already named /scc:write, /scc:review, or another single skill
  • The request is vague — ask one question; do not start a pass
  • Named replay (/scc:workflow) or a parallel split (/scc:batch)

The pass

Gather  →  /scc:research + /scc:analyze
Draft   →  /scc:write --skip-research --skip-review
Check   →  /scc:review
Cut     →  Action Router → /scc:refine, or back to Gather/Draft

Load gate checklists from ../pdca/references/ at each transition. Do not skip gates. Direct skills remain available without wrapping.

/scc:write runs an internal review unless --skip-review. God Hands Draft must pass --skip-research --skip-review so Check owns quality.

Options

Same flags as the compat command /scc:pdca: --phase, --depth, --target, --max, --max-cycles, --no-questions.

State

.data/state/pdca-active.json. MCP: pdca_get_state, pdca_start_run, pdca_transition, pdca_check_gate, pdca_end_run.

See ../pdca/SKILL.md for phase schemas, stuck detection, and the Action Router. Do not dispatch Pokemon filenames. Call the chained skills above.

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