change-narrative
Skill0 starsChanged 13 days agoMITView on GitHub
Write a useful pull request or change summary that leads with the problem, impact, and proof. Use when preparing a handoff, code review request, release note, or engineering change record.
In this repository25 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-skill-auditSkill
- api-contract-checkSkill
- build-rescueSkill
- context-handoffSkill
- data-quality-gateSkill
- dataset-workshopSkill
- dependency-careSkill
- docs-syncSkill
- experiment-ledgerSkill
- failure-forensicsSkill
- model-diff-reviewSkill
- model-eval-designSkill
- multi-agent-crosscheckSkill
- parallel-task-designSkill
- performance-proofSkill
- release-readinessSkill
- repo-scoutSkill
- research-evidence-mapSkill
- review-lensSkill
- safe-migrationSkill
- security-surfaceSkill
- spec-firstSkill
- sql-integrity-checkSkill
- test-driven-changeSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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 14
Call out schema/config/API compatibility, rollout steps, migrations, or monitoring needs when relevant.
- Distinctive: line 16
Keep the message scannable and proportional to the diff.
- Distinctive: line 28
Never claim “fully tested,” “production-ready,” or “no risk” without evidence.
- Distinctive: line 29
Never hide a known regression to make a change easier to merge.
- Distinctive: line 30
Avoid promotional language.
≈ “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
Change Narrative
Procedure
- Identify the user or operational problem in one sentence. Explain why the change matters before listing files.
- Summarize behavior before and after the change. State what deliberately remains unchanged.
- Include the most important design choice and any trade-off a reviewer should understand.
- List tests and checks that were actually run with results. Mention skipped checks and why.
- Call out schema/config/API compatibility, rollout steps, migrations, or monitoring needs when relevant.
- Link issue, benchmark, screenshot, or log evidence when available. Do not create fake links or metrics.
- Keep the message scannable and proportional to the diff.
Suggested structure
Problem — the motivating failure or user need.
Change — key behavior changes, not a file-by-file inventory.
Proof — tests/commands/results and known limitations.
Risk & rollout — compatibility, migration, flag, rollback, or monitoring needs.
Boundaries
- Never claim “fully tested,” “production-ready,” or “no risk” without evidence.
- Never hide a known regression to make a change easier to merge.
- Avoid promotional language; the purpose is to help the reviewer make a good decision.
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.