pr
Skill1.6k starsChanged 3 days agoMITView on GitHub
Use when writing a PR body.
In this repository29 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ask-mattSkill
- codebase-designSkill
- code-reviewSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- eol-checkSkill
- gdpr-auditSkill
- grillingSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- implementSkill
- implement-specSkill
- improve-codebase-architectureSkill
- prototypeSkill
- researchSkill
- retroSkill
- security-findingsSkill
- setup-matt-pocock-skillsSkill
- tddSkill
- to-questionnaireSkill
- to-specSkill
- to-ticketsSkill
- triageSkill
- wait-whatSkill
- wayfinderSkill
- writing-for-agentsSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Write the PR body in the shape of the repo's .github/pull_request_template.md.
- Very specific: line 46
Every PR belongs to an EPIC in Flashlight - EPICs kanban (see engineering-standards.md).
- Very specific: line 110
Use diff when the point is what changes and the surrounding shape already exists.
- Distinctive: line 171
Place each visual next to the short text it supports.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 the PR body in the shape of the repo's .github/pull_request_template.md. Keep its sections and fill each one; delete the HTML comments and the checklist items that don't apply:
**Notion EPIC:** <EPIC page URL> ← bamlab/flashlight-cloud only; never in bamlab/flashlight
Closes #<issue>
## Description
<what and why; diagram, diff-sketch or tree>
## Type of change
<ticked boxes>
## What to look at
<where the reviewer's attention goes, file:line>
## Validation
<feature: screenshots / video / output · bug: before vs after>
**How to test it:** <steps>
## Merge danger
**Door:** <one-way or two-way>
**Blast Radius:** <one word>
## Checklist
<the template's checklist, ticked>Sections
Skip all preambles and keep prose brief. Use the user's domain language from GLOSSARY.md.
Notion EPIC
Every PR belongs to an EPIC in Flashlight - EPICs kanban (see engineering-standards.md). In bamlab/flashlight-cloud, put its URL on the first line. In bamlab/flashlight (public) never write a Notion link: add the PR to the EPIC page in Notion instead.
Description
What changes and why, with the smallest visual that makes it clear (below).
What to look at
Tell the reviewer where to spend attention: the tricky logic, the decision you are unsure of, the parts that can be skimmed. Link file:line.
Visuals for the description
Pick the smallest view that makes the key point clear.
- Show logic or an algorithm as pseudocode:
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
diffwhen 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.tsFor a call-tree or call-stack change:
submitForm
createSession
persistPrompt
+ expandSkillMention
launchAgent
- navigateToSession
+ navigateToSession
+ subscribeToEventsFor 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.
Validation
Concrete evidence that the change works. A feature shows it working; a bug fix shows 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.
Merge Danger
Describe whether it's a one-way or two-way door. You can walk back through two-way doors, but not one-way doors. A PR that is cheap to roll back is lower risk. Changes that involve destructive actions or hard-to-reverse decisions are one-way doors.
The blast radius is the potential impact or scope of the changes introduced by this PR. Consider all possibilities. Examples are layout shift, breakages for consumers, mobile responsiveness, etc.
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.

