AF knowledge-ops
Use when a Head of Ops, Knowledge Manager, or TPM-Internal needs to author, validate, or clean up company SOPs and internal runbooks (procurement intake, vendor offboarding, incident-comms cascade, employee onboarding) — including 5W2H completeness checks (Who-What-When-Where-Why-How-HowMuch), cross-link and orphan-page validation across a sprawling Notion/Confluence/Obsidian wiki, KB ingestion + hygiene reporting, and runbook step verification (named owner, expected duration, observable success signal, rollback path, escalation contact). Pairs Ishikawa's 5W2H method, Gawande's *The Checklist Manifesto*, ISO 9001, ITIL v4, and Google SRE Workbook runbook discipline with deterministic stdlib-only Python tools that score completeness, detect anti-patterns, and emit prioritized cleanup lists (e.g., "validate this runbook before it goes into rotation", "audit our Confluence wiki for stale and orphaned SOPs").
Use when a Head of Ops, Knowledge Manager, or TPM-Internal needs to author, validate, or clean up company SOPs and internal runbooks (procurement intake…
As a process F 52/100 · Will not run — References files that are not bundled: path
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: path - note
frontmatter-keyunknown frontmatter key "compatible_tools"
Process rating: all ten parameters 52/100
- 0Tools and files. 1 referenced file(s) missing: path
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 100Steps. 44 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3785 tokens
- low 10 top-level sections: this looks like several domains in one skill
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 918: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Structure: 11 headings
- +3Step-by-step instructions: 44 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 3 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.