good-api
Skill1 starsChanged 3 months agoMITView on GitHub
Assess how users grow from first success to advanced composition without learning contradictory semantics or ejecting from the API. 1. Name the target users: beginner, novice, expert, and enterprise/integration-heavy if relevant. 2. Assess the API as a learning ladder: - Flexible: experts can solve many real problems without hidden restrictions or forced eject paths. - Gradual: novices can learn one stable layer at a time; adding power does not contradict earlier semantics. - Convenient: beginners can solve the common case…
In this repository14 other files it gives its agents.
- audit-pi-sessionSkill
- bash-scriptSkill
- cli-uxSkill
- code-quality-gateSkill
- docs-pesapSkill
- external-reviewSkill
- githubSkill
- gitlabSkill
- prekSkill
- pythonSkill
- rust-pesapSkill
- tdd-pesapSkill
- torcSkill
- uvSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- Distinctive: line 30
Check for hidden dependencies, restrictive coupling, oversimplified data models, and semantic surprises between layers.
- Distinctive: line 32
Treat convenience wrappers as packaging over understandable primitives, not substitutes for a flexible model.
- Distinctive: line 37
Read the ladder model when the full vocabulary, failure modes, or source-derived review questions are needed.
- Very specific: line 39
Use evals/trigger-prompts.json only when tuning recognition and evals/evals.json only when grading non-trivial API reviews.
≈ “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
API design
Assess how users grow from first success to advanced composition without learning contradictory semantics or ejecting from the API.
Core method
- Name the target users: beginner, novice, expert, and enterprise/integration-heavy if relevant.
- Assess the API as a learning ladder:
- Flexible: experts can solve many real problems without hidden restrictions or forced eject paths.
- Gradual: novices can learn one stable layer at a time; adding power does not contradict earlier semantics.
- Convenient: beginners can solve the common case quickly with defaults, examples, or safe packaging.
- Design or recommend changes in this order: flexible primitives first, gradual layers second, convenient wrappers/defaults third.
- Check for hidden dependencies, restrictive coupling, oversimplified data models, and semantic surprises between layers.
- Treat convenience wrappers as packaging over understandable primitives, not substitutes for a flexible model.
Reference router
- Read the ladder model when the full vocabulary, failure modes, or source-derived review questions are needed.
- Use
evals/trigger-prompts.jsononly when tuning recognition andevals/evals.jsononly when grading non-trivial API reviews.
Output
- Ladder assessment: flexible / gradual / convenient.
- Top API risks, ranked by user impact.
- Concrete redesign recommendations.
- Tradeoffs and cases where convenience should win.
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.

