agentleFS
Jason-hub-starJason-hub-star/model-orchestrator/skills/aim-before-build/SKILL.md

aim-before-build

Skill0 starsChanged 2 months agoMITView on GitHub

Compare a desired outcome with the real codebase before implementation and classify it as already done, partial, not started, or conflicting. Use for “check before building”, “is this already implemented?”, “조준”, or requests that combine a goal with status discovery.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check decisions, archived attempts, and recent commits for conflicts or previously rejected approaches.

    line 14
  2. Very specific:

    Use converge-plan for an expensive uncertain decision, goal-contract for multi-turn work with a clear target, or direct implementation for …

    line 29

≈ “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.

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

Aim Before Build

This stage is read-only. Its cheapest valid outcome is discovering that no implementation is needed.

Workflow

  1. Separate the requested target from the action verb. Resolve project-specific terms from code or current documentation.
  2. Trace the relevant path end to end. Count completed behavior paths, not changed files.
  3. Check decisions, archived attempts, and recent commits for conflicts or previously rejected approaches.
  4. Return exactly one verdict:
    • CONFLICTING: the goal contradicts current architecture or a confirmed decision; do not start.
    • ALREADY_DONE: the behavior exists and is verified; stop.
    • PARTIAL: name the shortest missing end-to-end path.
    • NOT_STARTED: identify the first owned path and whether planning risk is high.

An index or search result can prove presence, but an empty result alone cannot prove absence.

Output

Verdict, direct evidence, completed paths n/m, conflict history, and one next action.

Next

Use converge-plan for an expensive uncertain decision, goal-contract for multi-turn work with a clear target, or direct implementation for a small reversible change.

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.