agentleFS
qwibitaiqwibitai/nanoclaw/.claude/skills/update-skills/SKILL.md

update-skills

Skill31k starsChanged 9 days agoMITView on GitHub

Refresh installed NanoClaw channel and provider payloads (channels from their registry branch, providers from their skill payload) with fork-safe remote resolution and a blocking structured result. Use after updating NanoClaw or whenever installed channel/provider code may be stale.

  • Reads credentials

We split this skill into the rules it gives an agent

6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run from the NanoClaw project root.

    line 11
  2. Distinctive:

    If it is dirty, stop. Never mix a refresh with unrelated changes.

    line 22
  3. Distinctive:

    Never record a failed skill and continue toward an upgrade completion stamp.

    line 51
  4. Distinctive:

    After a successful refresh:

    line 60
  5. Very specific:

    If files under container/agent-runner/src/ changed, also run:

    line 67
  6. Very specific:

    If anything under container/ changed, update the install's agent image using the source mode already selected in .env:

    line 73

“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

Update installed skills

Refresh the code carried by installed channel and provider skills. This does not re-run credential setup, change .env, alter wiring, or restart services.

Run from the NanoClaw project root. Use ordinary conversation for any choice; do not depend on a provider-specific question or skill-invocation tool.

1. Preflight and selection

Require a clean working tree:

git status --porcelain

If it is dirty, stop. Never mix a refresh with unrelated changes.

The default is every installed channel/provider. If the user asked for a subset, pass its comma-separated names. Otherwise use all:

pnpm exec tsx scripts/update-skills.ts --skills all
# Example subset: --skills slack,opencode

The helper detects installed skills from the real channel/provider barrels. Provider skills refresh from their own payload/ in this checkout and need no remote; a provider first installed from the old providers branch is rewritten from the payload the same way. For channel skills it resolves the registry branch by checking configured remotes, so a fork whose origin is the user's repo and whose official source is upstream works without special handling. NANOCLAW_REGISTRY_REMOTE=<name> is an explicit override and is validated before use.

2. Treat the JSON result as a gate

The command prints nanoclaw-skill-refresh/v1-shaped JSON fields with one result per selected skill and exits nonzero unless every selected skill was fully refreshed.

  • Continue only when success is true and every status is refreshed.
  • A missing skill, missing structured apply contract, unresolved input, agent fallback, fetch error, or dependency error is blocking.
  • Never record a failed skill and continue toward an upgrade completion stamp.
  • Preserve the full report in the update summary.

The refresh engine overwrites skill-owned registry files and advances exact dependency/CLI-manifest pins. It skips prompts, operator walkthroughs, .env writes, wiring, restarts, and ordinary build/test directives.

3. Validate the composed checkout

After a successful refresh:

pnpm run build
pnpm test

If files under container/agent-runner/src/ changed, also run:

pnpm exec tsc -p container/agent-runner/tsconfig.json --noEmit

If anything under container/ changed, update the install's agent image using the source mode already selected in .env:

if grep -q '^NANOCLAW_HARDENED_IMAGE=true$' .env 2>/dev/null; then
  ./container/build.sh pull
else
  ./container/build.sh
fi

Any validation or image failure is blocking. Do not restart or report success.

4. Report

Show the selected skills, the registry remote used for each branch, changed files, validation results, and any blocking error. If this was a standalone refresh and the service was running, restart it through the service mode that actually owns this install and verify data/ncl.sock plus bin/ncl groups list. When called inside /update-nanoclaw, leave restart and health checking to that transaction.

Download now (ZIP)

Trending

Quiet since July.about the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 15 mentionsMar 2026: 42 mentionsApr 2026: 7 mentionsMay 2026: 12 mentionsJun 2026: 2 mentionsJul 2026: 1 mentionAug 2026: 0 mentionsSep 2026: 0 mentionsOct 2026: 0 mentionsNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the qwibitai/nanoclaw repository that our weekly crawl found. There is no adoption data for this file yet.

Who's talking about qwibitai/nanoclaw

The biggest 5 of 79 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 79

Talked about on GitHub, YouTube, Bluesky and Hacker News (79 times).

On GitHub · 50

45 more on GitHub

On YouTube · 22

17 more on YouTube

On Bluesky · 6

1 more on Bluesky

On Hacker News · 1

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.