agentleFS
skyelan1999skyelan1999/aide/.agents/skills/aide-development-router/SKILL.md

aide-development-router

Skill4 starsChanged 31 days agoMITView on GitHub

Route Aide repository development requests to the smallest useful specialist skill and agent team. Use at task intake, resume, or when dividing work across agents.

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill only as the entry point.

    line 8
  2. Very specific:

    Run python3 scripts/agent-route.py route --request "<original request>" to select specialist skills.

    line 13
  3. Distinctive:

    If routes overlap, split by non-overlapping files or work products.

    line 15
  4. Very specific:

    Do not assume a client automatically loads this directory.

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

aide development router

Use this skill only as the entry point. Keep project policy in AGENTS.md and docs/agent/WORKFLOW.md; do not duplicate the full release or verification process here.

Intake

  1. From the repository root, read AGENTS.md, docs/agent/WORKFLOW.md, docs/agent/router.json, then inspect Git status and the applicable docs/tasks/<id>.json.
  2. Run python3 scripts/agent-route.py route --request "<original request>" to select specialist skills. Treat its output as routing advice, not permission to spawn agents, edit outside scope, push, publish, or stop services.
  3. Assign one primary skill to the implementation owner. Add a second specialist only for a distinct, necessary concern. Keep a coordinator responsible for shared task record, integration, and final verification.
  4. If routes overlap, split by non-overlapping files or work products. Avoid multiple agents editing the same file concurrently. If no route matches, stay with the coordinator and inspect before delegating.

Agent handoff

Each assignment must include the user request, task ID, acceptance criteria, allowed paths, baseline Git status, expected deliverable, and evidence required. Specialists must report changed files, commands actually run, results, and unresolved risks. The coordinator owns merge/integration and the repository workflow stages; an agent's report is not verification evidence until checked.

Client handling

Do not assume a client automatically loads this directory. Use python3 scripts/agent-route.py prompt <client> --request "<original request>" to create a portable bootstrap for supported clients, or include the selected skill output from route. Never send prompts to an external service automatically.

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.