precise-alloyprecise-alloy/ritus/skills/triage/SKILL.md

triage

Skill1 starsChanged 4 months agoMITView on GitHub

Use before any implementation work - classifies changes by blast radius and recommends a model capability and effort. TRIGGER - invoke when user provides a requirement, feature request, or ticket key/URL (e.g., PROJ-123)

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

0
Common
Most of the 179 edited versions we read keep these.
4
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:
Run before any context load or task generation.
line 14
Distinctive:
When starting triage, create this TODO - every item below, verbatim (never a single item named after the skill) - and mark items done as …
line 16
Very specific:
If the user provides a ticket key or URL (e.g., PROJ-123, Jira URL) instead of a plain requirement:
line 28
Distinctive:
Default classification to STANDARD - ticket content is not available at triage time.
line 30
Distinctive:
If the user provides a plain requirement, classify using the signals below.
line 34
Very specific:
Recommended model and effort: - if the project opted into routing, read the Implementation (per triage) section of the model routing table …
line 82

“Common” is measured: kept by at least 6 in 10 of the 179 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

Triage

Core principle: Classify before you load context. The blast radius of a change determines how much process it needs - not how simple it looks.

When to use

Run before any context load or task generation. Every incoming change must be classified first.

When starting triage, create this TODO - every item below, verbatim (never a single item named after the skill) - and mark items done as you complete them:

TODO:

- [ ] Classify the requirement
- [ ] State classification + recommended model
- [ ] Load next skill (ticket-review or implement directly for TRIVIAL)

Input handling

If the user provides a ticket key or URL (e.g., PROJ-123, Jira URL) instead of a plain requirement:

Default classification to STANDARD - ticket content is not available at triage time.
Skip classification signals - proceed directly to Output and the Handoff (which invokes ticket-review).
ticket-review may upgrade to EPIC after fetching and analyzing the ticket content.

If the user provides a plain requirement, classify using the signals below.

Classification signals

Signal	Weight
Blast radius - how many systems / modules / teams affected	Primary
Contract impact - does a public interface / shared type change?	Primary
Validation clarity - is pass/fail unambiguous without running the system?	Primary
File count	Supporting hint
LOC	Supporting hint

Classification levels

Level	Criteria	Output
TRIVIAL	Single file, no public contract change, clear validation, low blast radius	Direct fix - no task file
SIMPLE	≤2 files, no cross-module contract, clear path, low blast radius	Task note: TASK + DONE WHEN + VERIFY
STANDARD	Cross-file, design decision, public contract changed, or validation unclear	Full task file
EPIC	Multi-session, multiple modules, new architecture pattern	Full task file + memory file

Safety override

Force upgrade to STANDARD regardless of classification when touching:

auth / session / token handling
payment / billing logic
database migrations
tenant / workspace isolation
infra / runtime config
shared contracts (types or interfaces exported across modules)

Context budget per level

Level	Load	Approx tokens
TRIVIAL	ritus golden rules + grep target file	~1k
SIMPLE	ritus + relevant skill file	~2–3k
STANDARD	ritus + docs/PROJECT_CONTEXT.md + relevant skills + docs/ARCHITECTURE.md (if new resource)	~5–8k
EPIC	Full context + memory file	~10–15k

Standards tokens are in addition to the budget above - load applicable standard skills per ritus standards table.

Output

After classification, state:

Classification level - TRIVIAL / SIMPLE / STANDARD / EPIC
Recommended model and effort - if the project opted into routing, read the Implementation (per triage) section of the model routing table in docs/PROJECT_CONTEXT.md ## Model routing for this classification (it drives execute-task; reviewers use the Review & verification (per worker) section; requirement-analysis is pinned to most capable). If model_routing is session (the default), there is no per-task model choice - every dispatched subagent runs on the session model.

Handoff

Report: the classification (TRIVIAL / SIMPLE / STANDARD / EPIC) + recommended model/effort.
TODO update:
- TRIVIAL → no TODO; implement directly in this session (ritus golden rules), self-verify with build + test, then report to the user.
- SIMPLE / STANDARD / EPIC → invoke ticket-review.

Download now (ZIP)

Other versions191 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 191
mattpocock/skills★ 309ksame name
withastro/astro★ 64ksame name
vectorize-io/hindsight★ 57ksame name
ogulcancelik/herdr★ 47ksame name
herdrdev/herdr★ 47ksame name
colinhacks/zod★ 44ksame name
QuivrHQ/quivr★ 40ksame name
vercel-labs/skills★ 37ksame name
pnpm/pnpm★ 37ksame name
vercel-labs/add-skill★ 35ksame name
181 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.
Used alongsideProjects with it also use writing-beats, setup-matt-pocock-skills and 10 more.
Other files people use alongside this one.
- LesaniSkill
  writing-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 61 projects that use this
- GoogleSkill
  setup-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 159 projects that use this
- SethGammonSkill
  ascii-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
- liufeng1976Skill
  setup-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 37 projects that use this
- simo97Skill
  migrate-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 64 projects that use this
- FabienDehopreSkill
  decision-mapping
  Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.
  Also in 7 projects that use this
In this repository21 other files it gives its agents.
- address-feedbackSkill
- brainstormSkill
- code-conventionsSkill
- comprehensionSkill
- debugSkill
- definition-of-doneSkill
- execute-taskSkill
- migrate-docsSkill
- pr-reviewSkill
- repo-scanSkill
- requirement-analysisSkill
- securitySkill
- setupSkill
- start-ritusSkill
- syncSkill
- task-generationSkill
- tddSkill
- testing-policySkill
- ticket-reviewSkill
- verify-taskSkill
- wrap-upSkill

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.

Check your setup, free

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

Triage

When to use

Input handling

Classification signals

Classification levels

Safety override

Context budget per level

Output

Handoff

Word for word · 0

Edited · 0

Wrote their own version · 191

writing-beats

setup-matt-pocock-skills

ascii-diagram

setup-ts-deep-modules

migrate-to-shoehorn

decision-mapping

Does it work?

No reviews yet

Your trail

Now do this for your own.