agentleFS
pinkroosteraipinkroosterai/PinkRoosterMcp/.claude/skills/pm-triage/SKILL.md

pm-triage

Skill2 starsChanged 8 months agoMITView on GitHub

Review and prioritize open issues and feature requests. Analyzes severity, age, and codebase impact to recommend priority adjustments and next steps.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. pmatos/skills★ 2same 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 repository15 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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
  1. Very specific:

    Call mcp__pinkrooster__get_project_status with projectPath set to the directory above

    line 19
  2. Very specific:

    If the item has an affectedComponent (issues), use Grep to check code health in that area.

    line 45
  3. Distinctive:

    NEVER modify entities — this is strictly read-only analysis

    line 107
  4. Distinctive:

    Always produce the full report even if some tiers are empty (show "None")

    line 108
  5. Very specific:

    Always suggest the most appropriate PM skill for each recommendation: /pm-next for ready items, /pm-implement for specific WPs, …

    line 110

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.

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

Triage Issues and Feature Requests

Analyze all open issues and feature requests to produce a prioritized triage report. This is a READ-ONLY analysis — never modify any entities.

Step 1: Resolve Project

  • Current directory: !pwd
  • Call mcp__pinkrooster__get_project_status with projectPath set to the directory above
  • Extract the projectId
  • Note the counts for context

Step 2: Load All Open Items

Make these four calls:

  1. mcp__pinkrooster__get_issue_overview with projectId and stateFilter: "Active"
  2. mcp__pinkrooster__get_issue_overview with projectId and stateFilter: "Inactive"
  3. mcp__pinkrooster__get_feature_requests with projectId and stateFilter: "Active"
  4. mcp__pinkrooster__get_feature_requests with projectId and stateFilter: "Inactive"

Step 3: Analyze Each Item

For every issue and feature request, assess:

  1. Age: Days since createdAt. Flag items older than 14 days as aging, older than 30 as stale.
  2. Priority alignment: Does the priority match the severity/urgency?
    • Critical severity + Low/Medium priority = misaligned (flag)
    • Low severity + Critical/High priority = potentially over-prioritized (flag)
  3. Work package linkage: Does it have linked work packages?
    • Active issues/FRs without linked WPs = planning gap (flag)
    • Approved/Scheduled FRs without linked WPs = ready for scaffolding (flag)
  4. State staleness: Items in NotStarted for >14 days need attention
  5. Blocked items: Items in Blocked state without clear path to unblock

If the item has an affectedComponent (issues), use Grep to check code health in that area.

Step 4: Categorize into Tiers

Tier 1: High Priority (act now)

  • Critical severity issues
  • Items blocking other work
  • Priority/severity misalignment favoring underpriced critical items
  • Active items without linked WPs that are >7 days old

Tier 2: Should Prioritize

  • Major severity issues without WPs
  • Approved/Scheduled FRs ready for scaffolding
  • Items aging (14-30 days) in NotStarted

Tier 3: Stale (consider closing)

  • Items in NotStarted for >30 days
  • Low-severity items with no activity
  • Deferred FRs older than 30 days

Step 5: Format Report

## Triage Report — {projectId}
**Date**: {today}
**Items analyzed**: {count} issues + {count} feature requests

### Tier 1: Act Now
| ID | Name | Type | Age | Priority | Severity | Issue |
|----|------|------|-----|----------|----------|-------|
| {id} | {name} | Issue/FR | {N}d | {priority} | {severity} | {reason} |

### Tier 2: Should Prioritize
| ID | Name | Type | Age | Priority | Issue |
|----|------|------|-----|----------|-------|

### Tier 3: Stale
| ID | Name | Type | Age | Priority | Issue |
|----|------|------|-----|----------|-------|

### Misalignment Flags
(Items where priority doesn't match severity)
- {id}: {severity} severity but {priority} priority — consider adjusting

### Recommendations
1. {Actionable recommendation referencing specific entity IDs}
2. {Suggest specific PM skill based on the situation}
3. ...

**Skill suggestions per situation:**
- Items with linked WPs ready for work → `/pm-next` or `/pm-implement {wpId}`
- Items needing work packages → `/pm-scaffold {entityId}`
- Items that appear done but aren't marked → `/pm-done {entityId}`
- FRs lacking detail (no user stories, vague description) → `/pm-refine-fr {frId}`
- New work to track → `/pm-plan <description>`
- Stale/cancelled items accumulating → `/pm-housekeeping` to remove them
- Stale items to close → cancel via dashboard (http://localhost:3000)

Constraints

  • This skill runs in a forked Explore agent — you have NO conversation history
  • NEVER modify entities — this is strictly read-only analysis
  • Always produce the full report even if some tiers are empty (show "None")
  • Include specific entity IDs in all recommendations so the user can act on them
  • Always suggest the most appropriate PM skill for each recommendation: /pm-next for ready items, /pm-implement for specific WPs, /pm-scaffold for unplanned items, /pm-done for completable items, /pm-plan for new work

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.