agentsclimarketplace
Sign in

Ankle sprain

Skill CyrilLeMat/temper-skills/examples/ankle_sprain/output/ankle-sprain

Frozen, deterministic decision (no LLM): maps pain_malleolar_zone, bone_tenderness_lateral_malleolus, bone_tenderness_medial_malleolus, can_bear_weight, visible_deformity, sprain_grade, hours_since_injury, age_years, patient_profile to one of urgent_care, seek_imaging, see_clinician, police_acute, police_subacute. Use when this decision must be made consistently and auditably — extract the features, call assess_ankle(), and relay its verdict without overriding it.From its SKILL.md

Install
npx -y skills add CyrilLeMat/temper-skills --skill ankle-sprain

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.5 KB, 554 tokens by cl100k_base, as published. Nobody here has run it

assess_ankle — skill (tempered by temper-skills)

You are an assistant.

The decision is frozen. Do not re-derive it from prose or your own judgment — the routing logic now lives in a deterministic decision tree (assess_ankle.assess_ankle, zero LLM calls, reviewed and version-controlled). Your job is the part the tree cannot do: turn the request into structured features, call the tree, and phrase its verdict.

How to answer

  1. Extract these structured features from the request:

    • pain_malleolar_zone
    • bone_tenderness_lateral_malleolus
    • bone_tenderness_medial_malleolus
    • can_bear_weight
    • visible_deformity
    • sprain_grade
    • hours_since_injury
    • age_years
    • patient_profile

  2. Call the decision tree and treat its result as authoritative (bundled at scripts/assess_ankle.py):

    from scripts.assess_ankle import assess_ankle
verdict = assess_ankle({"pain_malleolar_zone": pain_malleolar_zone, "bone_tenderness_lateral_malleolus": bone_tenderness_lateral_malleolus, "bone_tenderness_medial_malleolus": bone_tenderness_medial_malleolus, "can_bear_weight": can_bear_weight, "visible_deformity": visible_deformity, "sprain_grade": sprain_grade, "hours_since_injury": hours_since_injury, "age_years": age_years, "patient_profile": patient_profile})

  3. Relay verdict to the user. Do not override it. If a feature can't be extracted, pass it as None — the tree is built to fall through safely.

Gray zones to surface

The tree flags these as underdetermined — mention the caveat when the answer touches them:

  • (n2) Ottawa Rules are validated for ages ~18–55; outside that, escalate (handled below)
  • (n6) ice for symptom relief is fine briefly; the harm is prolonged/aggressive icing and immobilization

Generated by temper-skills from the original skill · 2026-07-01T12:45:19Z · model: claude-opus-4-8 via temper-skills. The decision logic is now testable (temper-skills validate) and evolvable (temper-skills incremental) — regenerate this skill when the tree changes.

What ships with it: 5 files

15.4 KB alongside SKILL.md, 4 of them executable

assets/

scripts/

Gives 0 of the 12 instructions most healthcare skills give in 554 tokens

Counted across 147 of the 152 authors here whose files we hold, read 2026-08-07

  • Export trial data to CSV formatin 11 of 147, across 2 files
  • Retrieve trial details using an NCT IDin 11 of 147, across 2 files
  • Split clinical datasets strictly by patientin 11 of 147, across 3 files
  • Use the ClinicalTrials.gov API v2in 10 of 147, across 1 file
  • Search trials by condition, drug, location, status or phasein 10 of 147, across 1 file
  • Use maximum page size for bulk data retrievalin 10 of 147, across 1 file
  • Extract and summarize key study informationin 10 of 147, across 1 file
  • Combine multiple filters for targeted searchesin 10 of 147, across 1 file
  • Print and review dataset statistics before modelingin 8 of 147, across 1 file
  • Start model development with simple baselinesin 8 of 147, across 1 file
  • Match preprocessing processors directly to data typesin 8 of 147, across 1 file
  • Monitor validation metrics for task type and class imbalancein 8 of 147, across 1 file

Said here and by no other author read

  • extract structured features from the request
  • call the deterministic decision tree
  • treat the decision tree result as authoritative
  • relay the verdict to the user
  • pass missing features as None
  • mention caveats when the answer touches gray zones

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.