agentleFS
Sign inStart free
rpraharajrpraharaj/ai-sdlc/skills/draft-steerco/SKILL.md

draft-steerco

Skill0 starsChanged 16 days agoMITView on GitHub

Draft a steerco pack from status, RAID, and change assessments only. Use when the user asks for a steerco deck, steering brief, or /draft-steerco. Do not add facts that are not in those files. Do not invent RAG.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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. Distinctive:

    Do not invent RAG or progress.

    line 19
  2. Very specific:

    If status is missing, stop and run write-status first.

    line 35
  3. Distinctive:

    Read AGENTS.md if present.

    line 44

≈ “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

Draft steerco

Decisions asked, options, recommendation — no new facts. This is not write-status and not assess-change.

Do not invent RAG or progress.

Is this the right skill?

SignalDo this instead
Weekly one-pagerwrite-status
Impact of a changeassess-change first
RAID updateupdate-raid

Required inputs

  • Latest docs/govern/status-*.md
  • docs/govern/raid.md
  • Any open docs/govern/change-*.md

If status is missing, stop and run write-status first.

Human decisions (do not invent)

  • RAG they will present
  • Which recommendation they adopt

Procedure

  1. Read AGENTS.md if present. Read status, RAID, and open change assessments. Nothing else becomes a fact.
  2. Find the home: docs/govern/steerco-YYYY-MM-DD.md.
  3. Open references/steerco-template.md. Copy every heading. Write n/a when unused.
  4. Each decision asked cites a change file or RAID id. Options include reject.
  5. RAG stays unassigned unless the status already has a human-set RAG — then copy it and cite status.

Output

  • Path: docs/govern/steerco-YYYY-MM-DD.md
  • Template: references/steerco-template.md

Quality bar

  • Status path is named
  • Every fact cites status, RAID, or a change file
  • No new metric or date
  • Unused headings are n/a

Done

  1. Path
  2. Decisions-asked count
  3. Next: human sends it; then update-raid if they decided

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