pr-description
Skill241 starsChanged 30 days agoApache-2.0View on GitHub
Create or update PR. Use this skill every time user asks to create or update a PR to ensure clear, consistent descriptions between PRs.
- Commits and pushes
94 other projects use a version of this.
Adopted by
Most recently taken up by
- TangleML/tangle-uitheir own version, first seen Nov 9, 2026
- taecontrol/skillstheir own version, first seen Nov 8, 2026
- sankalpaacharya/skillstheir own version, first seen Nov 8, 2026
- joel611/skillstheir own version, first seen Nov 8, 2026
- Wade-DevCode/awesome-coding-skills-cntheir own version, first seen Nov 8, 2026
- AlessioScarfone/skillstheir own version, first seen Nov 6, 2026
Used with
Projects with it also use ao-desktop-dev, bug-triage 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.
agentlab-inSkillao-desktop-dev
Launch, restart, or troubleshoot the real AO Electron desktop app from this repository; run a checkout against isolated or real local AO data; combine PR branches for local UI review; and diagnose stale Electron processes, port conflicts, or preload bridge mismatches. Use whenever asked to run, open, show, or visually verify AO frontend changes in the actual desktop app rather than ao preview, dev:web, or mock data.
Also in 4 projects that use this
jMertaSkillbug-triage
Use when the user reports a bug, regression, runtime error, failing build, or broken test and wants reproduction, diagnosis, root-cause analysis, or an authorized fix. Isolates the shared cause and verifies the smallest relevant change.
Also in 4 projects that use this
GitHubSkillcommit-message
Generate conventional commit messages - use when creating commits, writing commit messages, or asking for git commit help
Also in 9 projects that use this
saffron-healthSkilladdress-review
Address PR review comments systematically. Use when responding to code review feedback on a pull request.
Also in 3 projects that use this
NVIDIASkillwriting-docs
Use when adding or changing user-facing behavior or documentation in Megatron-Energon, or when creating new .py, .sh or .md files that need license headers.
Also in 3 projects that use this
Sagargupta16Skilldependency-audit
Audit project dependencies for security vulnerabilities, licensing issues, maintenance health, and optimization opportunities. Use it during regular security audits (monthly or quarterly); before a major release when you want to ensure the dependency tree is clean; when evaluating whether to adopt or replace a dependency; after a security advisory affects one of your dependencies; when your install times or bundle sizes have grown noticeably.
Also in 3 projects that use this
Other versions94 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 94
- jdx/mise★ 36ksame name
- zulip/zulip★ 26ksame name
- Nagi-ovo/gemini-voyager★ 21ksame name
- pipecat-ai/pipecat★ 17ksame name
- AgentWrapper/agent-orchestrator★ 14ksame name
- ComposioHQ/agent-orchestrator★ 14ksame name
- OrchestratorInc/agent-orchestrator★ 14ksame name
- Untrivial-ai/agent-orchestrator★ 14ksame name
- sanity-io/sanity★ 6.4ksame name
- vimeo/psalm★ 5.9ksame name
84 more not listed
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 repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- frontend/AGENTS.mdAGENTS.md
- llms.txtllms.txt
- agent-capabilitySkill
- agent-specSkill
- alembic-migrationSkill
- backend-testsSkill
- background-taskSkill
- channel-botSkill
- dev-agentSkill
- e2e-testsSkill
- frontend-featureSkill
- mcp-connectionsSkill
- permissions-rbacSkill
- pr-commentsSkill
- project-docsSkill
- rag-knowledgeSkill
- resolve-changelog-conflictSkill
- review-mapSkill
- ste-writingSkill
- vault-secretsSkill
- vstorm-code-reviewSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 89 edited versions we read keep these.
2
Distinctive
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 8
Create or update PR description based on git diff.
- Very specific: line 17
If the user names a different base (e.g.
- Distinctive: line 77
Use present tense ("Add", "Update", "Remove")
- Very specific: line 80
Attach diagrams for an architectural change: When a change adds or reshapes a flow across components — a new tool or service path, a new …
“Common” is measured: kept by at least 6 in 10 of the 89 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
Skill: PR Description
Create or update PR description based on git diff.
Inputs
- PR number — required when updating an existing PR; provided by the user (referred to as
<pr-number>below) - Base branch — detect dynamically; do not assume
main:
If the user names a different base (e.g.BASE=$(gh repo view --json defaultBranchRef -q .defaultBranchRef.name)develop), use that instead.
Steps
- Gather context:
- Refresh the base first:
git fetch origin "$BASE".gh repo viewhands back a branch name; it does not update the local remote-tracking ref, and a staleorigin/$BASEdescribes commits that merged upstream days ago as if they were this PR's. - For new PR:
git diff "origin/$BASE"...HEADandgit log "origin/$BASE"..HEAD --oneline - For existing PR:
gh pr diff <pr-number>, and its current body:gh pr view <pr-number> --json title,body. An update is a merge, not a rewrite: a body often carries hand-written limitations, verification evidence and issue links that the diff cannot reconstruct, and--body-filereplaces all of it silently. Carry that content forward, and only rewrite what the diff has actually made wrong.
- Refresh the base first:
- Generate description in this format:
## Changes
### Summary
[Brief summary of changes - 1-3 sentences]
### Business Context
[Business/technical context - why was this change needed. Infer from branch name, commits, and code changes. Remove this section if unclear.]
### Changes
[Technical approach - main architectural decisions, main changes. Use bullet points.]
### Architecture
[Diagrams, for an architectural change only — see Rules. Reference each attached image as `` with one sentence saying what the reader should take from it. Remove this section for a change with no architectural shape.]
### Verification
[Example queries, commands, or steps to verify the changes work correctly. When the change is observable through the project's own tracing/observability backend (new or changed spans, telemetry attributes, logged events — check whether the repo has one before assuming), include links or excerpts from example traces you actually produced — see Rules.]
### Linked Issues
[Link to any relevant issues or tickets found in branch name or commits. Remove this section if none found.]- Execute (write the body to a file and pass
--body-file; a long body with backticks does not survive--body "…"intact):- New PR:
gh pr create --base "$BASE" --title "<title>" --body-file body.md - Existing PR:
gh pr edit <pr-number> --body-file body.md - Diagrams go in the body as mermaid, so there is nothing to upload and no asset URL to
go stale.
ghhas no image-upload flag ---attachis not a flaggh pr createorgh pr edithas ever exposed - and a local PNG referenced by path renders as a broken image for every reviewer.
- New PR:
- Return the PR URL.
Rules
- No "Test plan" or "Generated with..." sections
- Keep descriptions concise
- Use present tense ("Add", "Update", "Remove")
- Omit
Business ContextandLinked Issuessections when there's nothing to fill in — don't leave placeholders - Include trace/log evidence for observable changes, when the repo has the means to produce it. When the change produces or alters observability (new/changed spans, telemetry attributes, structured logs) and the project has a tracing or logging backend, link to or excerpt example traces/log lines you actually produced in the
Verificationsection — one per meaningful path (happy path + key error paths), using that backend's own link format (e.g. a dashboard deep-link, a log query, a captured span tree). Only cite evidence you genuinely produced — never fabricate ids, URLs, or output. If the project has no such backend, or the change isn't observable through one, skip this and verify with the project's normal test/run commands instead. - Attach diagrams for an architectural change. When a change adds or reshapes a flow
across components — a new tool or service path, a new gate, a state machine, a
cross-channel behaviour — put images in the
Architecturesection rather than making the reviewer rebuild the shape from the diff. Two usually suffice: one component/flow diagram (who calls what, and what each outcome writes) and one sequence diagram (the call order, with the refusal branches). Put the mermaid straight in the body, in a fenced ```mermaid block: GitHub renders it in a pull request description, so the diagram needs no renderer, no uploaded asset and no version of anything. It also stays readable in the diff and as text, which a PNG does not. A committed architecture doc's diagram belongs wherever this repo keeps those instead, e.g.docs/architecture.md, adocs/architecture/directory, or an ADR. Diagram the mechanism the PR actually changes, including its failure paths; a box-and-arrow restatement of the module tree earns nothing. Skip the section for a fix, a test-only change, or a one-file tweak.
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.

