agentleFS
itseffiitseffi/agentic-os/.agents/skills/ost-target-selection/SKILL.md

ost-target-selection

Skill114 starsChanged 10 months agoMITView on GitHub

Select one target opportunity from an OST using evidence-based weighted scoring and tie-breakers.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use default weights unless custom weights are provided.

    line 18
  2. Distinctive:

    Use this skill when the task directly matches the workflow described above.

    line 43
  3. Distinctive:

    Do not use this skill when the request is unrelated, low-stakes, or better handled by a simpler direct response.

    line 47

≈ “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

OST Target Selection

Choose exactly one opportunity to pursue next.

Instructions

Step 1: Harvest candidates from OST

  • Include leaves and relevant parents with strong evidence.
  • Merge duplicates and reframe solution language into need language.

Step 2: Score candidates

  • Score 1-5 for OS, MF, CF, CuF.
  • Use default weights unless custom weights are provided.
  • Compute weighted priority score (WPS).

Step 3: Build shortlist

  • Select top 3-5 by WPS.
  • Apply tie-breakers: distinctness, evidence quality, time-to-learning, risk diversification.

Step 4: Recommend one target

  • Pick one small, distinct, moment-scoped opportunity.
  • Exclude engineering effort prioritization.

Step 5: Audit alignment

  • Confirm no-effort-policy and moment distinctness.
  • List evidence gaps and follow-up needs.

Output

  • Candidate inventory
  • Scoring matrix with WPS
  • Top 3-5 shortlist
  • Single recommendation with rationale
  • Audit notes

When to Use

Use this skill when the task directly matches the workflow described above.

When Not to Use

Do not use this skill when the request is unrelated, low-stakes, or better handled by a simpler direct response.

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.