write-pull-request
Skill4 starsChanged 2 days agoApache-2.0View on GitHub
Write or update a Pnyx pull request description, including Intent, Problem, Fix, Validation and Review. Read before opening a PR or changing its title or body, and after every push to keep the description true to the final diff.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- revisit-studies/studytheir own version, first seen Nov 9, 2026
- DataDog/dd-trace-rbtheir own version, first seen Nov 2, 2026
- yaohuangguan/remote-arctheir own version, first seen Nov 1, 2026
- Remote-Arc/remote-arctheir own version, first seen Nov 1, 2026
- yaohuangguan/agent-playbooktheir own version, first seen Nov 1, 2026
- venables/skillstheir own version, first seen Sep 12, 2026
Used with
Projects with it also use audit-test-suite, change-data-safely and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
yaohuangguanSkillaudit-test-suite
Find where an existing test suite is weak and decide what to test next, ranked by risk. Use this when asked to add missing tests, find gaps, raise coverage, assess test quality or see which areas are thin, even if the request only mentions a coverage percentage.
Also in 3 projects that use this
yaohuangguanSkillchange-data-safely
Change a database schema or stored data without breaking running code or losing data. Use this for any migration, new or changed column, backfill, bulk update, delete, index, or change to a stored format, including in small projects. Data mistakes are often impossible to undo.
Also in 3 projects that use this
SauravSrivastavSkilldebug-failure
Diagnose a failing test, command, or runtime behavior using evidence and produce a minimal verified fix.
Also in 3 projects that use this
MicrosoftSkillfix-flaky-test
Reproduces and fixes flaky or quarantined tests. Tries local reproduction first (fast), then falls back to CI reproduce workflow (reproduce-flaky-tests.yml). Use this when asked to investigate, reproduce, debug, or fix a flaky test, a quarantined test, or an intermittently failing test.
Also in 3 projects that use this
Codagent-AISkillimplement-change
Implements an approved change in one continuous session, with tiered test runs. Use when asked to implement a change from its approved definition, or to invoke codagent:implement-change.
Also in 3 projects that use this
srclightSkillrefactor-safely
This skill should be used when the user asks to "refactor", "rename", "move", "change a function signature", "extract a method", "delete unused code", "clean up", or any modification that could break callers or dependents. Provides a pre-change safety checklist using srclight's graph tools to assess blast radius before touching code.
Also in 3 projects that use this
- +6 more from yaohuangguan
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- DataDog/dd-trace-rb★ 417same name
- revisit-studies/study★ 46same name
- yaohuangguan/remote-arc★ 5same name
- Remote-Arc/remote-arc★ 1same name
- venables/skills★ 1same name
- yaohuangguan/agent-playbook★ 1same name
- dabstractor/agent-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- audit-testsSkill
- deslopSkill
- follow-conventionsSkill
- review-codeSkill
- write-ci-workflowSkill
- write-front-endSkill
- write-skillSkill
- inscribeSkill
- pnyx-arrange-columnsSkill
- pnyx-cliSkill
- pnyx-firstmate-as-hydraSkill
- pnyx-manage-workersSkill
- pnyx-orchestrateSkill
- pnyx-report-progressSkill
- pnyx-set-upSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use the PR template and the checks in CONTRIBUTING.md.
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Write a pull request
Use the PR template and the checks in CONTRIBUTING.md. Write for a reviewer who has not seen the conversation.
- Intent: follow the template's Intent guidance before describing the problem.
- Problem: explain what is wrong or missing and who it affects. Include discovery context only when it helps explain the failure.
- Fix: describe the resulting behavior and material limits. Cover the whole diff against the PR's base; a stacked PR describes only its own change. Link any agreed design or issue needed to judge it.
- Validation: name the checks actually run and their results. State failures, skipped checks and pending checks honestly. For each new or changed test, record the behavior or past bug it guards and the flip result required by audit-tests. Include before/after media for visible changes; say when there is no visible UI change.
- Review: record findings and fixes, or no findings, from each required checklist in order, covering bugs, tests and simpler. Tick only completed, required boxes. The boxes alone do not replace the review results.
- Remove the template placeholders. Keep all five headings, each with substantive text; hidden comments and examples do not count.
pnpm verifychecks structure, not whether the claims are true. - After every push, compare the description with the final diff and current validation. Rewrite stale claims, changed scope and validation gaps. Preserve the hidden verification marker and the review boxes; rerun
pnpm verifyon the pushed head after editing the body. - Read the final title, body and changed code comments using deslop. Use plain English, keep enough context to assess the change and remove session history.
File structure changes
For a PR that adds, moves, splits, renames or deletes files, put one combined tree in a fenced code block inside Fix. Show folders, subfolders and their files together, replacing path lists and separate before/after trees. PRs that only edit existing files do not need a tree.
- Give each file one line with a short note on what it holds. Siblings that share a note may share a line, joined with
·. - Mark new files with
+, moved or renamed files with⇐and(from old/path)in the note, and removed files with-. For splits or merges, show the resulting files and their source in the notes; include the removed source if it no longer exists. - Add
~Nfor a file's approximate line count after the change when useful. Collapse unchanged files to one line such as(other files unchanged).
Example:
src/
├── app/
│ ├── host.ts ~600 wiring only after the split
│ ├── +live-sessions.ts agent processes (from app/host.ts)
│ ├── +server-clients.ts client connections (from app/server.ts)
│ ├── server.ts ~400 mount, event pump, shutdown
│ ├── -legacy-clients.ts removed obsolete client handling
│ └── (other files unchanged)
└── hydra/
├── +send-cli.ts · +history-cli.ts send and history commands
└── operations.ts ⇐ stop, outage, retry (from app/operations.ts)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.

