agentleFS
mmurakarummurakaru/skills/pr-create/SKILL.md

pr-create

Skill0 starsChanged 6 days agoMITView on GitHub

Use when opening a pr.

  • Commits and pushes

26 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use explore, commit and 1 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.
  • genomewalkerSkill

    explore

    RLM-style recursive memory exploration - dynamically navigate the memory graph

    Also in 4 projects that use this

  • SentrySkill

    commit

    Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.

    Also in 5 projects that use this

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 23 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the repo's .github/pull_request_template.md if present.

    line 14
  2. Very specific:

    Use diff when the point is what changes and the surrounding shape already exists.

    line 103
  3. Distinctive:

    Place each visual next to the short text it supports.

    line 164
  4. Very specific:

    After gh pr create succeeds, open the PR in the user's browser and print the URL:

    line 187
  5. Distinctive:

    Check for ci checks failing, if so pull the error and propose a solution.

    line 199
  6. Very specific:

    When a reviewer, human or a bot, leaves feedback > invoke the /pr-feedback skill to address those comments.

    line 216
  7. Very specific:

    No code identifiers in the body (class names, utilities, prop/function/file names) - describe in plain language.

    line 223

“Common” is measured: kept by at least 6 in 10 of the 23 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Body template

Use the repo's .github/pull_request_template.md if present. Write to /tmp/<slug>-pr-body.md:

[TEAM-XXXX](https://company.atlassian.net/browse/TEAM-XXXX)

## Summary

<diagram, diff-sketch, or tree>

- one bullet per logical change, one line each
- imperative verb + object - "add X", "extract Y", "register Z"
- no semicolons, no sub-clauses, no follow-up sentences inside a bullet
- match the bullets to the commits where possible
- describe behaviour and intent, not implementation - say what changed for the user/system, not how
- never leak code into the description

## Evidence

- **Before:** <screenshot/output/failing test run>
- **After:** <screenshot/output/passing test run>

for assets prefer a simple 2 column markdown table with placeholder text to drop assets.

## Sections

Skip all preambles and keep prose brief.

### Issue link detection

Determine the Jira ticket for this PR using a strict precedence - **never infer or substitute**:

When no ticket is detected:

- Title omits the `TEAM-XXXX -` prefix use a conventional-commit prefix instead, matching the repo's `git log --format=%s`).
- Issue Link section in the body is `N/A`.

### Summary

Pick the smallest view that makes the key point clear.

- Show logic or an algorithm as pseudocode:

```text
on(save)
  if content is unchanged
    return cached result
  write new content
  return fresh result
```
  • Show runtime control flow as a call tree:
submitForm
  createSession
    persistPrompt
    launchAgent
  navigateToSession
  • Show UI structure as a component tree, including state and module boundaries that matter:
<SessionPage>(apps / example / src / routes / session.tsx);
useSessionEvents() < SessionToolbar > <RunSkillButton>(packages / ui);
  • Show file responsibility or a broad refactor as a shallow file tree:
src/
├── commands/       # parses user actions
├── sessions/       # owns session state
└── transport/      # sends API requests
  • Show component interaction, control flow, or data flow with Mermaid:
sequenceDiagram
    participant User
    participant UI
    participant Daemon
    User->>UI: choose command
    UI->>Daemon: send expanded prompt
    Daemon-->>UI: stream result
  • Use diff when the point is what changes and the surrounding shape already exists. Match the diff shape to the topic.

For a component change:

 <SessionPage>
   useSessionEvents()
   <SessionToolbar>
+    <RunSkillButton />
   <SessionTimeline>
+    <SkillResultCard />

For a file-layout change:

 src/
 ├── commands/
+│   └── show-me.ts       # expands the slash command
 ├── sessions/
-└── transport.ts
+└── transport/
+    ├── client.ts
+    └── stream.ts

For a call-tree or call-stack change:

 submitForm
   createSession
     persistPrompt
+    expandSkillMention
     launchAgent
-  navigateToSession
+  navigateToSession
+    subscribeToEvents

For a state or control-flow change:

 on(save)
-  write content
+  if content is unchanged
+    return cached result
+  write new content
+  invalidate cache
  • Show the whole block when most of it is new, when omitted context would hide ownership or order, or when the user needs a copyable target shape:
function expandSkill(command: string): string {
  const skillName = command.slice(1);
  return `use the ${skillName} skill`;
}

Guidance

Place each visual next to the short text it supports. Keep only the calls, files, props, states, and boundaries needed to answer the user's current question or the options to resolve the current discussion point.

You may use one of these, you may use several, it is unlikely you will use all of them. Use your judgement and don't overwhelm the user.

Evidence

Concrete evidence that the change works. Show a before and after.

Screenshots are S-tier - when the environment is set up for it and the change is visual.

Execution-based evidence is A-tier. Test results, console output. Show the exact test that now fails and passes, using pseudocode.

Create

gh pr create \
  --title "TEAM-XXXX - <desc>" \
  --body-file /tmp/<slug>-pr-body.md \
  ${status:+--draft}   # only when invoked with status=draft

Output - auto-open PR in a new browser tab

After gh pr create succeeds, open the PR in the user's browser and print the URL:

pr_num="$(gh pr view --json number -q .number)"
gh browse "$pr_num"
gh pr view "$pr_num" --json url -q .url

Non-negotiable - the whole point of opening a PR is for the user to see it. Print the URL too in case the browser can't open (headless env, missing default browser).

Monitor - post creation

Check for ci checks failing, if so pull the error and propose a solution.

gh pr checks --watch

There is no native gh watch for comments, so use the built-in Monitor tool (persistent) with a poll loop that emits one line per new review comment:

pr=<pr>; repo=<owner>/<name>; prev="$(mktemp)"; : > "$prev"
while true; do
  cur="$(gh api "repos/$repo/pulls/$pr/comments?per_page=100" --jq '.[]|"\(.id) \(.user.login): \(.body|gsub("\n";" ")[0:160])"' 2>/dev/null || true)"
  comm -13 <(sort "$prev") <(printf '%s\n' "$cur" | sort)
  printf '%s\n' "$cur" | sort > "$prev"; sleep 30
done

When a reviewer, human or a bot, leaves feedback > invoke the /pr-feedback skill to address those comments.

Hard rules

  • --body-file only; never --body / -b.
  • Single hyphens (-), never em dashes (—).
  • No Co-Authored-By or harness specific AI-attribution trailers of the like.
  • No code identifiers in the body (class names, utilities, prop/function/file names) - describe in plain language.
  • Confirm with the user before running gh pr create.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.