write-integration-contract
Skill0 starsChanged 16 days agoMITView on GitHub
Write an API, event, or file contract with compatibility rules. Use when the user asks for an integration contract, API contract, event schema, interface agreement, or /write-integration-contract. Do not implement. Do not break compatibility in the same change that adds a field.
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-api-examplesSkill
- write-architectureSkill
- write-designSkill
- write-dev-tasksSkill
- write-docsSkill
- 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
5 rules. About 0 are common, 3 are distinctive, and 2 are 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Do not implement. Do not drop or rename a field in the same document that adds one unless the human explicitly accepts a breaking change.
- Very specific: line 31
If there is no design or architecture and the shape is not already in the repo, stop and offer write-design first — unless the user is …
- Very specific: line 47
Read AGENTS.md if present.
- Distinctive: line 48
Read the design/architecture or the existing interface.
- Distinctive: line 54
No secrets. No production URLs with credentials.
≈ “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 integration contract
Lock the shape two sides share. This is not a design of internals (write-design), not examples-only (write-api-examples), and not a migration plan (data-change).
Do not implement. Do not drop or rename a field in the same document that adds one unless the human explicitly accepts a breaking change.
Is this the right skill?
| Signal | Do this instead |
| How the initiative is built | write-design (then this, if a public shape exists) |
| Stored schema / expand-then-contract steps | data-change |
| Request/response examples only | write-api-examples |
| Process handoffs, not payloads | map-process |
| Why we picked this protocol | record-decision |
If there is no design or architecture and the shape is not already in the repo, stop and offer write-design first — unless the user is documenting an existing interface. Then read the code or spec that exists.
Required inputs
- A design, architecture, or existing interface (path or code)
- Producer and consumer named from
context/systems-of-record.mdor the design AGENTS.md
Human decisions (do not invent)
- Breaking vs expandable change
- Authz model if the repo has no existing pattern
- Error catalog that is not already in the repo
Procedure
- Read
AGENTS.mdif present. Readcontext/systems-of-record.mdif present. - Read the design/architecture or the existing interface. Prefer types and routes that already exist.
- Find the home: first existing
docs/contracts/, or offer to create it. Name:docs/contracts/<slug>.md. - Open references/contract-template.md. Copy every heading. Write
n/awhen unused. - State producer, consumer, transport, and identity as this program already uses them.
- Fields: name, type, required, meaning. Mark new vs existing. Add is allowed. Remove/rename requires a human breaking-change yes and a compatibility section.
- Errors, idempotency, and versioning: copy the repo’s existing pattern or write
unknown — need human. - No secrets. No production URLs with credentials.
Output
- Path:
docs/contracts/<slug>.md - Template:
references/contract-template.md
Quality bar
- Producer and consumer are named
- Every field has type and required/optional
- Compatibility section is not empty (expand / break+waiver / existing unchanged)
- Remove/rename is absent unless a human accepted a break
- Unused headings are
n/a
Done
- Path
- Transport + field count
- Next skill:
write-dev-tasks,write-test-strategy, orwrite-api-examples
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.