working-style-skills
Skill3 starsChanged 28 days agoMITView on GitHub
Route requests for terse, minimal or unambiguous output to the pinned style skills: caveman, ponytail, i-have-adhd, asd-ste100.
In this repository25 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- adrSkill
- api-contract-syncSkill
- architecture-advisorSkill
- ci-triageSkill
- compassSkill
- debugSkill
- delivery-digestSkill
- design-taste-skillsSkill
- grillSkill
- harness-improveSkill
- harness-loopSkill
- impact-analysisSkill
- native-mobile-skillsSkill
- plugin-authorSkill
- pr-flowSkill
- project-memorySkill
- remaining-workSkill
- reviewSkill
- slide-deckSkill
- spec-flowSkill
- task-flowSkill
- ui-conformanceSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 23
Add the source id to upstream in .agents/compass.json.
≈ “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.
Files
working-style-skills
Four style skills are pinned upstream. Compass keeps no copy of them. The compass contract applies all four in every session. Install them in a project that does not have them.
| Skill | Source id | What it shapes |
ponytail | ponytail | How much you build. The laziest solution that works. |
caveman | caveman | How many words you spend. Compressed prose, exact technical terms. |
i-have-adhd | i-have-adhd | The order of an answer. Action first, numbered steps, no preamble. |
asd-ste100 | asd-ste100 | Ambiguity in durable text: commits, docs, errors, prompts for agents. |
Install
Add the source id to upstream in .agents/compass.json. Then run ac sync.
Precedence
ponytaildecides the work.i-have-adhdshapes the answer.cavemancompresses the prose.asd-ste100overridescavemanfor durable text. A commit, a doc, an error message or a prompt for an agent is read later without you.
Never remove
- The completion gate: changed files, each command with its result, and the open risks.
- Reasoning, risks and verification results.
- A test, a validation run or a security control.
ponytailargues for less code, never for less proof.
Sub-agents
A sub-agent does not inherit the style. Restate it in each delegation. Say that the returned report is durable text, so asd-ste100 applies.
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.