write-api-examples
Skill0 starsChanged 15 days agoMITView on GitHub
Write request and response examples from an existing integration contract. Use when the user asks for API examples, sample payloads, or /write-api-examples. Do not create a second contract. Do not implement.
In this repository66 other files it gives its agents.
- AGENTS.mdAGENTS.md
- a11y-passSkill
- assess-changeSkill
- build-regression-packSkill
- charter-exploratorySkill
- classify-dataSkill
- commitSkill
- cut-releaseSkill
- data-changeSkill
- debugSkill
- design-experimentSkill
- diff-environmentsSkill
- draft-steercoSkill
- engineering-barSkill
- explain-codeSkill
- explore-codebaseSkill
- fix-ciSkill
- handoffSkill
- implement-changeSkill
- incident-triageSkill
- lean-reviewSkill
- map-dependenciesSkill
- map-design-handoffSkill
- map-processSkill
- open-prSkill
- performanceSkill
- plan-data-migrationSkill
- plan-incrementSkill
- plan-rollbackSkill
- plan-uatSkill
- prioritize-backlogSkill
- production-passSkill
- ready-to-mergeSkill
- record-decisionSkill
- refactor-safelySkill
- revert-changeSkill
- review-architectureSkill
- review-changeSkill
- review-pipelineSkill
- security-passSkill
- shape-workSkill
- ship-notesSkill
- spec-analyticsSkill
- spec-observabilitySkill
- start-projectSkill
- synthesize-discoverySkill
- triage-blockersSkill
- triage-defectSkill
- update-raidSkill
- verify-uiSkill
- write-architectureSkill
- write-designSkill
- write-dev-tasksSkill
- write-docsSkill
- write-integration-contractSkill
- write-nfrSkill
- write-opportunitySkill
- write-prdSkill
- write-requirementsSkill
- write-runbookSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- Distinctive: line 19
Do not add fields the contract does not have.
- Very specific: line 33
If missing, stop and name write-integration-contract.
- Distinctive: line 41
Read AGENTS.md if present.
- Very specific: line 45
Use obviously fake values (user@example.com only if the contract has email.
≈ “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
Write API examples
Illustrate the contract that already exists. This is not write-integration-contract and not write-tests.
Do not add fields the contract does not have. Do not use real secrets or personal data.
Is this the right skill?
| Signal | Do this instead |
| No contract yet | write-integration-contract |
| Stored schema migration | plan-data-migration / data-change |
| Automated tests of the contract | write-tests |
Required inputs
- Path to the integration contract (or an existing OpenAPI/schema in the repo that is already the contract)
If missing, stop and name write-integration-contract.
Human decisions (do not invent)
- Whether an example is normative (default: illustrative only)
Procedure
- Read
AGENTS.mdif present. Read the contract. List fields. - Find the home: sibling
docs/contracts/<slug>-examples.md. - Open references/examples-template.md. Copy every heading. Write
n/awhen unused. - One happy example and one error example per operation the contract names. Types must match the contract.
- Use obviously fake values (
user@example.comonly if the contract has email; preferuser@example.invalid).
Output
- Path:
docs/contracts/<slug>-examples.md - Template:
references/examples-template.md
Quality bar
- Contract path is named
- No field that is not on the contract
- Happy + error for each listed operation
- No secrets or live PII
- Unused headings are
n/a
Done
- Path
- Operation count
- Next skill:
write-testsorimplement-change
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.