raise-the-bar
Skill2 starsChanged 17 days agoMITView on GitHub
Deep, unhurried review of a whole area of Heinzelmännchen (a module, a head, the release process, the docs, the developer experience) against the best projects of its kind, at the highest effort, to find what would make it excellent rather than acceptable. Use when asked to raise the bar, before a release, or before a design decision with long-lasting consequences; not on every change.
In this repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/AGENTS.mdAGENTS.md
- tests/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/CLAUDE.mdCLAUDE.md
- starter/CLAUDE.mdCLAUDE.md
- template/CLAUDE.mdCLAUDE.md
- tests/CLAUDE.mdCLAUDE.md
- add-moduleSkill
- add-operationSkill
- codifySkill
- releaseSkill
- reviewSkill
- scaffold-pluginSkill
- self-auditSkill
- ship-smallSkill
- write-adrSkill
- write-testsSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Start the architect agent with effort: max and that brief.
- Very specific: line 15
If the area touches security, CLI/DX or docs, start the matching reviewer in parallel with the same brief and effort: high.
≈ “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
Raise the bar
Expensive on purpose: the most capable model at maximum effort. Run it when the decision outlives the change.
- Name the area and the question in one sentence ("Is the plugin API as small as it can be?"). Collect the files, ADRs and docs that define it.
- Start the
architectagent witheffort: maxand that brief. Ask it to compare the area with two or three well-regarded projects that solve the same problem (cite them), and to return: what is already excellent, the three changes with the most leverage (each with cost and risk), and what to stop doing. - If the area touches security, CLI/DX or docs, start the matching reviewer in parallel with the same brief and
effort: high. - Turn the result into decisions: an ADR for anything structural (skill
write-adr), issues or pull requests for the rest. Report the decisions, not the transcript.
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.

