Ost target selection
Skill itseffi/agentic-os/.agents/skills/ost-target-selection
Select one target opportunity from an OST using evidence-based weighted scoring and tie-breakers.From its SKILL.md
npx -y skills add itseffi/agentic-os --skill ost-target-selectionAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
SKILL.md
1.3 KB, 270 tokens by cl100k_base, as published. Nobody here has run it
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.
What ships with it: 1 file
181 B alongside SKILL.md
agents/
- openai.yaml181 B