agentleFS
future-minefuture-mine/claude-skill/skills/intake-triage/SKILL.md

intake-triage

Skill1 starsChanged 35 days agoNo licenceView on GitHub

Turn a BATCH of raw incoming requests into routed, decided work before any of it reaches the roadmap. Use this whenever several new items arrive at once — triggers on "triage the inbox", "here's what the client/stakeholder asked for", "we got a batch of new requests", "go through the notes from the call", "here's the feedback from the review", "sort these out", "what do we do with all this", a pasted list of ideas or complaints, a dump of user feedback or bug reports, or a task-board export (Jira/Linear/Asana/Trello/Planner/GitHub Issues) full of untriaged items. For each item it dedupes against what is already planned, checks version control to see whether it is ALREADY BUILT, tests it against ARCHITECTURE invariants and accepted ADRs to catch contradictions, classifies it, and routes it to a roadmap status — including `blocked:decision`, carrying the exact question that must be answered. It ends by producing a decision agenda for the next review. It DECIDES and RECORDS ONLY; it never writes code. Use this — NOT feature-integrator — when more than one request arrives at a time or a request is unrefined; feature-integrator takes a single, already-understood feature straight to implementation. Use this, not phase-executor, when the question is "what should we build" rather than "build the next planned slice", and not product-architect, which designs a foundation rather than sorting requests against an existing one. product-guide only recommends what to say next; this actually moves the work.

  • Commits and pushes

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

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.