agentleFS
Sign inStart free
neuraforge-cl-esneuraforge-cl-es/adaptive-engineering/skills/task-triage/SKILL.md

task-triage

Skill1 starsChanged 11 days agoMITView on GitHub

Classify a software task as FAST, STANDARD, or DEEP based on risk, scope, ambiguity, reversibility, and blast radius. Use before non-trivial implementation or when choosing process depth.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 3

    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:

    All or nearly all are true:

    line 25
  2. Very specific:

    no security/data/public-contract/production boundary

    line 30
  3. Distinctive:

    Keep the triage concise:

    line 53
  4. Distinctive:

    Do not turn triage into a design document.

    line 60

“Common” is measured: kept by at least 6 in 10 of the 4 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

Task Triage

Classify the task before choosing the workflow.

Inputs

Inspect enough repository context to answer:

  • What behavior is changing?
  • How many modules/services/contracts are involved?
  • What breaks if the change is wrong?
  • Is the change easy to roll back?
  • Are security, data integrity, public compatibility, concurrency, production infrastructure, or deployment involved?
  • Is the current architecture sufficiently understood?

Decision

Choose exactly one initial mode:

FAST

All or nearly all are true:

  • local scope
  • low failure cost
  • low ambiguity
  • reversible
  • no security/data/public-contract/production boundary
  • expected implementation is small

STANDARD

Any are true:

  • multiple coherent files in one subsystem
  • new behavior needs acceptance criteria
  • bug cause needs investigation
  • meaningful tests must be added or changed
  • refactor has moderate blast radius

DEEP

Any strong-risk signal is present:

  • auth/security boundary
  • destructive/persistent data migration
  • public API/protocol compatibility
  • CI/CD, networking, release, or production infrastructure
  • multiple services or distributed consistency
  • difficult rollback
  • architectural ambiguity with large blast radius

Output

Keep the triage concise:

  • Mode: FAST|STANDARD|DEEP
  • Why: one sentence
  • Key risks: only material risks
  • Expected budget: files/dependencies/services/abstractions as relevant

Do not turn triage into a design document.

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.

Check your setup, free