skillz-self-update
Skill1 starsChanged 23 days agoMITView on GitHub
Refresh the cross-harness research, then audit, improve, and autoimprove this repository's published skillz skill. Use when a maintainer asks to "self-update skillz", "update the published skillz skill", "refresh the harness layout", or invokes /skillz-self-update. Do NOT use for audits of other skills or as a /skillz mode.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- python-authoringSkill
- releaseSkill
- skillzSkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 0 are distinctive, and 12 are 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.
12
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 17
Do not treat this as a published /skillz mode.
- Very specific: line 27
Read skills/skillz/references/harness-layout.md, including ## Sources and ## Rejected.
- Very specific: line 28
Check every source in ## Sources for changes since Checked:.
- Very specific: line 33
Run /skillz audit skills/skillz/SKILL.md, then /skillz improve skills/skillz/SKILL.md.
- Very specific: line 34
Keep the published modes and the /skillz wedge and autoimprove boundaries unchanged.
- Very specific: line 35
Run /skillz autoimprove skills/skillz after the improve fixes land.
- Very specific: line 36
Follow skills/skillz/references/experiments.md for the questions, the run, the gate, and the export.
- Very specific: line 37
Run the checkout's skills/skillz/scripts/skillz-experiment.pyz, not an installed copy.
- Very specific: line 41
Put the expected findings in expected.
- Very specific: line 42
Never skip the case or budget approval.
- Very specific: line 43
When the user declines a question, skip this step and report the skip.
- Very specific: line 47
Run just build and fix any failure.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.
Files
skillz self-update
Maintain skills/skillz/references/harness-layout.md and skills/skillz/SKILL.md in this repository.
Do not treat this as a published /skillz mode.
- Resolve the canonical source. Run
realpath "$(git rev-parse --show-toplevel)/skills/skillz/SKILL.md". Refuse to continue when the directory is not a git checkout. Print the real path. Refuse when the real path is outside the toplevel. Confirm the checkout is this repository:git remote get-url originmatchespaulnsorensen/skillz-that-grillz. Refuse a real path under~/.agents/skills,~/.claude/skills,~/.omp/agent/skills,~/.codex/skills,~/.cursor/skills, or~/.copilot/skills. Refuse a real path in a dotfiles-managed ornpx skills-managed tree. Continue on such a copy only when the user selects it explicitly after seeing the real path. - Read
skills/skillz/references/harness-layout.md, including## Sourcesand## Rejected. - Check every source in
## Sourcesfor changes sinceChecked:. Use a fresh-context research agent when the host offers one. Cover frontmatter fields, discovery paths, invocation policy, argument handling, and body budgets. Cover Claude Code, the Agent Skills spec, Codex, OMP, Pi, Zed, and theskillsCLI. - Compare the research digest with the reference. Update its matrix, rules, template, and
Checked:date. Record each rejected claim and its reason under## Rejected. - Run
/skillz audit skills/skillz/SKILL.md, then/skillz improve skills/skillz/SKILL.md. Keep the published modes and the/skillz wedgeandautoimproveboundaries unchanged. - Run
/skillz autoimprove skills/skillzafter the improve fixes land. Followskills/skillz/references/experiments.mdfor the questions, the run, the gate, and the export. Run the checkout'sskills/skillz/scripts/skillz-experiment.pyz, not an installed copy.maintracks no archive, so runjust buildfirst to build it. Pass--edit prose+cliso the search can also change theinspect-skillsources inpackages/skillz/src/skillz_inspect. Drafttaskcases that each audit one skill fixture namedfixture.md. Put the expected findings inexpected. The shipped contract judges them with itstaskrubric. Never skip the case or budget approval. When the user declines a question, skip this step and report the skip. Apply the patch only on apromoteverdict and the user's approval. Then run the step 5 audit again. On apromote-cheaperverdict, do not apply the patch. Report the verdict, the delta, the SE, the token change, and themax_quality_lossmargin. - This repository has no deploy step. Do not install or sync the result to any installed copy.
- Run
just buildand fix any failure.
Done means: Checked: is today, every source was queried, and the published skill passes its own rubric.
Autoimprove also reports a gate verdict or a recorded skip.
Report the research delta, applied fixes, rejected claims, the autoimprove verdict, and the verification result.
What this skill never does
- It never runs
npxorskills addagainst the working copy. - It never applies an autoimprove patch without a
promoteverdict and the user's approval. Apromote-cheaperverdict is advisory only. - It does not upgrade GEPA,
skillz-experiment.pyz, the analytics engine snapshot, Python dependencies,skills/skillz/scripts/wedge.pyz, or releases. - It does not sync the result to other harnesses. That is out of scope for this skill.
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
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.

