agentleFS
TakaGotoTakaGoto/rag-learning-academy/.claude/skills/triage/SKILL.md

triage

Skill24 starsChanged 19 days agoMITView on GitHub

Not sure where to start or what's wrong? Get routed to the right agent or skill.

190 other projects use a version of this.

Adopted by

Most recently taken up by

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.
  • 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 74 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 182 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

  • 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 74 projects that use this

  • LesaniSkill

    writing-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 70 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 47 projects that use this

  • +1 more from Lesani

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 179 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask one question to categorize their need:

    line 12
  2. Distinctive:

    Ask: "What would you like to do?"

    line 24
  3. Distinctive:

    Ask: "What stage are you at?"

    line 38
  4. Distinctive:

    Ask: "What's the symptom?"

    line 49
  5. Distinctive:

    Ask: "What would you like to review?"

    line 61
  6. Distinctive:

    Ask if they'd like to proceed or if they had something else in mind.

    line 75
  7. Very specific:

    If they confirm, tell them to run the suggested /command.

    line 76
  8. Distinctive:

    If none of the options fit, ask the learner to describe their situation in their own words and use your judgment to route them — you can …

    line 78

“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: Find the Right Help

When to use this: You're stuck, confused, or not sure which /command to run next. Triage asks a few quick questions and points you in the right direction.

Step 1: Understand the Learner's Situation

Ask one question to categorize their need:

"What best describes where you are right now?"

  1. "I'm brand new to RAG" → Suggest /start to begin their learning journey
  2. "I'm learning and want to study a topic" → Go to Step 2 (Learning Path)
  3. "I'm building something and need help" → Go to Step 3 (Building Path)
  4. "Something is broken / not working well" → Go to Step 4 (Debugging Path)
  5. "I want to review or improve what I have" → Go to Step 5 (Review Path)

Step 2: Learning Path

Ask: "What would you like to do?"

GoalRecommended
Learn a concept step by step/lesson
Get a quick definition/glossary [term]
Understand something deeply/explain [concept]
Test what I know/quiz [topic]
See my progress/roadmap
Read a research paper/paper-review
Compare two approaches/compare

Step 3: Building Path

Ask: "What stage are you at?"

StageRecommended
I haven't started building yet/build — guided component construction
I need to design my system first/architecture — design your RAG architecture
I want a real-world challenge/challenge — open-ended project
I need help choosing between approaches/compare — side-by-side comparison

Step 4: Debugging Path

Ask: "What's the symptom?"

SymptomRecommended
Retrieved documents aren't relevant/debug-rag → retrieval diagnosis
The LLM makes things up / hallucinates/debug-rag → generation diagnosis
Results are slow or expensive/benchmark → performance profiling
I'm not sure what's wrong, quality just feels off/evaluate → measure with metrics first
I'm getting errors in my code/code-review → get expert feedback

Step 5: Review Path

Ask: "What would you like to review?"

GoalRecommended
Get feedback on my code/code-review
Measure my pipeline's quality/evaluate
Check performance / speed / cost/benchmark
See what to learn next/roadmap

Step 6: Route and Hand Off

Once you've identified the right skill:

  1. Briefly explain WHY you're suggesting that skill ("Based on what you described, /debug-rag is the best fit because it has a structured diagnostic process for retrieval issues.")
  2. Ask if they'd like to proceed or if they had something else in mind.
  3. If they confirm, tell them to run the suggested /command.

If none of the options fit, ask the learner to describe their situation in their own words and use your judgment to route them — you can also suggest they talk directly to a specific agent (e.g., "You might want to ask the chunking-strategist about that").

Suggest 2-3 relevant next steps:

  • /start — if they haven't begun their learning journey yet
  • /roadmap — to see their overall progress and recommended path
  • The specific skill identified through triage

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.