agentleFS
akshay-diwadkarakshay-diwadkar/first-four-hours/skills/sensemaking/router/SKILL.md

router

Skill1 starsChanged 4 days agoMITView on GitHub

Author the smallest sufficient route of suite capabilities into ignored `route.md`. Use when the next capability is unclear, work spans several capabilities, or current state may already satisfy part of the request; skip it when one capability obviously applies.

19 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use research and setup.

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.
  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 3 projects that use this

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 1

    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:

    Read Routing Policy; it selects the target repository and shapes step prompts.

    line 17
  2. Very specific:

    When current state already satisfies the target, replace the numbered steps with one None: <established postcondition> line.

    line 38

“Common” is measured: kept by at least 6 in 10 of the 15 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

Router

Purpose

Author one bounded route of public capabilities from the current target and authoritative state, seal it as .first-four-hours/routes/<slug>/route.md, and return control. Never execute a routed capability, plan, edit source, publish, commit, push, or create a PR; write only that route and its local Git exclude rule.

Author

Read Routing Policy; it selects the target repository and shapes step prompts. Draft the route outside that repository:

# Route: <target>

Repository: <absolute path of the target repository>

<only the current state needed to read the steps>

## Steps

1. `<capability>`
   - Why: <why it is needed now>
   - Input: <authoritative input or current-state dependency>
   - Result: <expected observable result>
   - Prompt:
     ```text
     <copyable request that runs this step>
     ```

When current state already satisfies the target, replace the numbered steps with one None: <established postcondition> line.

Seal

python <skill-root>/scripts/cli.py --repo-root <Repository path> \
  --input draft=<draft.md> --input slug=<route-slug> --format json run

Repair each reported defect in the draft and rerun; on a repository mismatch, pass the intended repository rather than editing the line to where you run. Complete when the result names the sealed route.md under that Repository; return that path and end with step 1's sealed Prompt as the one optional next step, or none for a None: route. Only the user's later "yes" starts it, via its capability and gates, and the user runs a user-invoked step's Prompt themselves. Exhausting the route returns control; it does not by itself complete the target.

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.