triage
Skill0 starsChanged 25 days agoMITView on GitHub
Read-only first look at any new work item (Slack message or thread, ticket, PR, error report, customer complaint, pasted text): works out what it is asking for, checks the code, logs or linked items just enough to know, and proposes the next steps, each naming the skill that fits (investigate, implement, spec, pr-review, pr-follow-up, qa, document, deploy) plus drafts of any reply or ticket. Sends and creates nothing. Use on "triage this", "what does this need", "what should I do with this message", "/triage".
189 other projects use a version of this.
Adopted by
Most recently taken up by
- udecode/platetheir own version, first seen Nov 8, 2026
- vercel-labs/add-skilltheir own version, first seen Nov 8, 2026
- chrysogonus/power-agentstheir own version, first seen Nov 8, 2026
- ishandutta2007/Awesome-Claude-Skillstheir own version, first seen Nov 8, 2026
- Adelie-Squad/solosquadtheir own version, first seen Nov 8, 2026
- cloudflare/vinexttheir own version, first seen Nov 8, 2026
Used with
Projects with it also use writing-beats, setup-matt-pocock-skills 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.
LesaniSkillwriting-beats
Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.
Also in 66 projects that use this
GoogleSkillsetup-matt-pocock-skills
Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
Also in 167 projects that use this
liufeng1976Skillsetup-ts-deep-modules
Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.
Also in 42 projects that use this
SethGammonSkillascii-diagram
Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.
Also in 4 projects that use this
simo97Skillmigrate-to-shoehorn
Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.
Also in 68 projects that use this
LesaniSkillwriting-shape
Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.
Also in 63 projects that use this
- +1 more from Lesani
Other versions189 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 189
- mattpocock/skills★ 309ksame name
- withastro/astro★ 64ksame name
- vectorize-io/hindsight★ 60ksame name
- ogulcancelik/herdr★ 47ksame name
- herdrdev/herdr★ 47ksame name
- colinhacks/zod★ 44ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- vercel-labs/add-skill★ 39ksame name
- vercel-labs/skills★ 39ksame name
179 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 repository18 other files it gives its agents.
- address-commentsSkill
- demoSkill
- deploySkill
- documentSkill
- gather-contextSkill
- implementSkill
- investigateSkill
- observeSkill
- pr-follow-upSkill
- project-profileSkill
- pr-reviewSkill
- qa-planSkill
- qaSkill
- resolve-conflictsSkill
- specSkill
- sprintSkill
- standupSkill
- todoSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 176 edited versions we read keep these.
3
Distinctive
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 14
Follow ../../shared/policy.md.
- Distinctive: line 18
No changes: no code edits, commits, branches, PRs, ticket changes, messages, or writes to any shared service.
- Very specific: line 20
Stay shallow: Read enough to classify and to make the drafts correct.
- Very specific: line 25
Run dev-skills:gather-context on the input (the whole thread, linked tickets, PRs, docs).
- Distinctive: line 26
Write 2-3 lines: who asks, what they want, what is the deadline or impact, what is unclear.
- Distinctive: line 55
Do not send, post or create any of them.
“Common” is measured: kept by at least 6 in 10 of the 176 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
Triage
Follow ../../shared/policy.md. Run dev-skills:project-profile first.
Goal: decide what this item needs and hand back next steps to approve. Output is a short read plus options, not a fix.
Rules
- No changes: no code edits, commits, branches, PRs, ticket changes, messages, or writes to any shared service. Reads only (tickets, threads, PRs, code, logs, metrics through read tools).
- Stay shallow. Read enough to classify and to make the drafts correct; do not run a full
investigation. When the cause of a problem is unclear, the next step is
investigate, not a guess. - Claims in the item are hypotheses until something you read backs them; mark unverified ones.
1. Understand the item
Run dev-skills:gather-context on the input (the whole thread, linked tickets, PRs, docs).
Write 2-3 lines: who asks, what they want, what is the deadline or impact, what is unclear.
2. Classify
Pick the main kind; more than one can apply:
- Question: answerable from code, docs or data now.
- Problem report: something broken or unexpected.
- Change request: new behavior or a fix that is already clear.
- Review request: a PR or doc to read.
- Follow-up on my own work: a PR or ticket of mine that needs action.
- FYI / nothing to do: say so and stop.
3. Look just enough
- Question: find the answer in code or docs, with
file:line. - Problem report: one pass on the code path and, if the project has them, logs or errors in the window. Say if it looks real, already known (search the tracker first) or working as designed.
- Change request: find the code involved and judge size (small, medium, large).
- Review request: read the diff summary and the linked ticket.
4. Propose next steps
A short ranked list. Each step has: what it does in plain words, the skill that would run it, and whether it needs the user's ok. Typical steps:
investigatewhen a problem's cause is not proven.implementwhen the change is clear (with the ticket; draft one first if none exists).specwhen it is large or ambiguous.pr-review/pr-follow-upfor PRs.qa,document,deploywhen that is what is left.- Reply draft to the sender, in the thread's tone and language, answering what you found.
- Ticket draft (title, description, fields per the tracker) when none exists and the work is real.
- Other action (change a PR already open, run a read-only command for the user): spell it out. Do not send, post or create any of them. Ask for confirmation with the list.
Output
Print:
# <item> — <one-line read>
**Asks:** <who wants what, by when>
**Kind:** question | problem | change | review | follow-up | nothing to do
**Found:** <2-4 lines with `file:line` or the source of each fact; unverified claims marked>
**Next steps:**
1. <step> — skill: <name> | draft | action — needs ok: yes/no
2. ...
**Drafts:** <reply and/or ticket, ready to edit>End with "Reply ok to do these, or tell me which to change." Nothing is sent until then.
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.

