Name: knowledge-ops
Rating: 72 (1 reviews)
Author: alirezarezvani

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").

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

The canonical home for this skill is knowledge-ops in alirezarezvani/claude-skills

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, highly actionable body with a well-sequenced validated workflow and clear script/reference navigation. The main weaknesses are canon-citation padding in the forcing-question library and referenced bundle files that are absent from the actual package.

Suggestions

Ship the referenced bundle files (references/5w2h_sop_canon.md, references/runbook_canon.md, references/kb_hygiene_anti_patterns.md, and the three scripts/*.py) so the signaled one-level-deep references resolve instead of dead-linking.

Condense the seven per-question canon citations in the forcing-question library to a single consolidated canon reference, keeping the recommended answers but dropping the per-item authority name-drops.

Consider moving the full script flag documentation into a scripts/README.md or per-script docstring and keeping only the invocation + key flags inline, to tighten the SKILL.md overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, ops-specific prose with concrete failure modes and executable commands, but the seven per-question canon citations in the forcing-question library and the named-authority references are minor over-explanation that could be trimmed without losing actionability.	4 / 5
Actionability	Fully executable guidance throughout — concrete invocations ('kb_ingester.py --input <vault-dir>', 'runbook_validator.py --input <runbook.md>', 'sop_generator.py --input <metadata.json> --profile <ops\|support\|finance\|hr\|it\|regulated>'), named flags (--sample, --stale-days), an executable quick example, and concrete output shapes (traffic-light, validity 0-100, MUST-FIX list, top-20 cleanup list).	5 / 5
Workflow Clarity	A clearly sequenced four-step flow (Ingest → Validate → Generate → Cross-link) with explicit validation checkpoints and a closing feedback loop (re-run kb_ingester.py to verify orphan count is down) plus concrete validity thresholds (≥80 SAFE, 60-79 CAUTION, <60 NOT-SAFE), matching the anchor with explicit validation steps and error-recovery feedback.	5 / 5
Progressive Disclosure	Good structure with a clear overview and well-signaled, one-level-deep references (references/5w2h_sop_canon.md, runbook_canon.md, kb_hygiene_anti_patterns.md, and three scripts), but the referenced bundle files are not present in the package, so the disclosure is incompletely realized and would produce dead links at navigation time.	4 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A thorough, persona-scoped description that clearly states what the skill does and when to use it, with concrete actions and natural trigger phrases. Its main weakness is verbosity from academic canon name-drops that pad rather than aid triggering.

Suggestions

Trim the academic method citations (Ishikawa, Gawande, ISO 9001, ITIL v4, Google SRE Workbook) from the description — they are authority signaling, not user trigger terms, and roughly double the description's length.

Add file/extension-based triggers (e.g., '.md wiki export', 'Notion zip', 'Confluence space export') to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'author, validate, or clean up company SOPs and internal runbooks', '5W2H completeness checks', 'cross-link and orphan-page validation', 'KB ingestion + hygiene reporting', and runbook verification with six named sub-checks — giving comprehensive coverage rather than vague language.	5 / 5
Completeness	Explicitly answers both what ('author, validate, or clean up company SOPs and internal runbooks' plus the enumerated checks) and when ('Use when a Head of Ops, Knowledge Manager, or TPM-Internal needs to...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural coverage ('Head of Ops', 'Knowledge Manager', 'SOPs and internal runbooks', 'procurement intake, vendor offboarding', 'Notion/Confluence/Obsidian wiki', 'validate this runbook', 'audit our Confluence wiki for stale and orphaned SOPs'), but the academic canon name-drops ('Ishikawa', 'Gawande', 'ISO 9001', 'ITIL v4', 'Google SRE Workbook') are authority citations a user would not naturally say and crowd out a few natural synonyms.	4 / 5
Distinctiveness Conflict Risk	Clear niche (organizational SOP/runbook authoring + KB hygiene) scoped to specific personas and artifact types, with named sibling distinctions in the body minimizing overlap with process-mapper, llm-wiki, and internal-comms skills.	5 / 5
	Total	19 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing	Warning
referenced_paths_exist	Referenced path issues: 7 missing	Warning

	Total	13 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/knowledge-ops/SKILL.md
Commit: 19392f7

Reviewed: ~8 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.