SKILLEMALL.ai
GitHub ↗ RU Sign in

AF skill-router

Route user tasks to the most relevant skills using a layered taxonomy, risk model, and minimum-necessary-loading strategy. Use when deciding which skill to load, when multiple skills could apply, when new downloaded skills need classification, when evaluating whether a skill may threaten the system, or when maintaining a persistent task-to-skill routing policy.

ClawHub Agent Skills author: Stairer v1.5.0 MIT-0 5 files body ≈ 3 840 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 48/100 · Will not run — References files that are not bundled: scripts/update_skill_index.py, references/skill-index.md, references/usage-stats.json

AnalyzerInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
92/100
safety, quality, tests
Safety 60%
100
Quality 40%
79
Run on models
none yet
Process rating
F
48/100
Will not run
References files that are not bundled: scripts/update_skill_index.py, references/skill-index.md, references/usage-stats.json
Tools and files w 18
0
Inputs and preconditions w 11
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: scripts/update_skill_index.py
  • warning missing-ref reference to a missing file: references/skill-index.md
  • warning missing-ref reference to a missing file: references/usage-stats.json
  • warning missing-ref reference to a missing file: references/routing-decisions.jsonl
  • warning missing-ref reference to a missing file: references/new-skill-review.md
  • warning missing-ref reference to a missing file: references/backlog-priority.md
  • warning missing-ref reference to a missing file: references/skill-overlap-report.md
  • warning missing-ref reference to a missing file: references/skill-overlap-map.json
  • warning missing-ref reference to a missing file: references/skill-fusion-view.md
  • warning missing-ref reference to a missing file: references/risk-source-review.md
  • warning missing-ref reference to a missing file: scripts/cleanup_download_inbox.py
  • warning missing-ref reference to a missing file: scripts/review_risk_sources.py
  • warning missing-ref reference to a missing file: scripts/check_download_overlap.py
  • warning missing-ref reference to a missing file: scripts/intake_skill.py
  • warning missing-ref reference to a missing file: scripts/track_skill_usage.py
  • warning missing-ref reference to a missing file: scripts/log_routing_decision.py
  • warning missing-ref reference to a missing file: scripts/review_new_skills.py
  • warning missing-ref reference to a missing file: scripts/prioritize_backlog.py
  • warning missing-ref reference to a missing file: scripts/detect_skill_overlap.py
  • warning missing-ref reference to a missing file: scripts/apply_overlap_fusion.py

Process rating: all ten parameters 48/100

Will not run. References files that are not bundled: scripts/update_skill_index.py, references/skill-index.md, references/usage-stats.json
  • 0Tools and files. 20 referenced file(s) missing: scripts/update_skill_index.py, references/skill-index.md, references/usage-stats.json
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 16 mutating operations with no state check
  • 40Consistency. Frontmatter name (skill-router) differs from the folder (skill-taxonomy-router)
  • 60Result and completion. Output format stated, no completion criterion
  • 100Steps. 213 steps
  • 100Failures and branches. 10 branches, has a failure section
  • 100Execution cost. Instruction body is 3840 tokens
  • 100Progress reporting. Reports progress
  • low 20 top-level sections: this looks like several domains in one skill
  • high The skill tells the model to perform an irreversible action with no human approval

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +1No license
  • +2Single-language instructions
  • +3Description length 363: enough signal without eating the budget
  • +4Structure: 22 headings
  • +3Step-by-step instructions: 213 items
  • +3Output format is stated explicitly
  • +4Has examples (0 code blocks)
  • +4Reference files are cited in the instructions (2 of 3)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.

External checks

ClawHub: clean
No artifact-backed security concern was found in the available scan inputs or workspace evidence.
LLM: benign (medium) · VirusTotal: · 29 May 2026