skills/hq-knowledge-governance/SKILL.md
Use when auditing knowledge base health, classifying documents by criticality (K1-K5), checking cross-reference integrity, identifying documentation gaps, enforcing governance compliance, or when the user asks about knowledge organization, document freshness, or KB audits. NEVER use for generic documentation writing (use documentation-templates skill), generic knowledge base design for non-Sharkitect projects (use knowledge-management skill), or research synthesis from web sources (use research-synthesizer agent).
npx skillsauth add sharkitect-solutions/sharkitect-claude-toolkit hq-knowledge-governanceInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
| File | Load When | Do NOT Load |
|------|-----------|-------------|
| references/k-classification.md | Classifying new documents or reclassifying existing ones | Simple document reads with no classification need |
| references/governance-protocol.md | Running compliance checks, reviewing governance adherence | Quick document lookups or edits |
| references/audit-methodology.md | Running KB audits, freshness checks, gap analysis | Single document operations |
Launch knowledge-governance agent (Task tool) for execution-heavy work:
Use this skill directly (without agent) for:
| Level | Name | Description | Review Cadence | Examples | |-------|------|-------------|----------------|----------| | K1 | Critical Enterprise | Loss = operational failure | Monthly | Client contracts, pricing model, compliance docs | | K2 | Core Operational | Loss = significant disruption | Quarterly | SOPs, workflow docs, architecture decisions | | K3 | Standard Reference | Loss = inconvenience | Semi-annually | Meeting notes, project plans, research summaries | | K4 | Supporting Context | Loss = minor gap | Annually | Historical decisions, past analyses, reference material | | K5 | Experimental | Temporary, disposable | On creation (30-day expiry) | Draft ideas, test documents, scratch notes |
Default-to-Higher Rule: When uncertain between two levels, classify at the HIGHER (more critical) level. Downgrading is safe; missing a critical classification is not.
NEW DOCUMENT ARRIVES
|
+-- Classify using K1-K5 (see references/k-classification.md)
|
+-- Check: Does it REPLACE an existing document?
| YES --> Version the old one, update cross-references
| NO --> Check: Does it RELATE to existing documents?
| YES --> Add cross-references in both directions
| NO --> Standalone document, proceed
|
+-- Apply metadata:
| - Classification level (K1-K5)
| - Owner (who maintains it)
| - Review date (based on cadence)
| - Related documents (cross-references)
|
+-- Store in appropriate location based on classification
Run a KB audit when ANY of these conditions are true:
development
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ad copy,' 'ad creative,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' or 'audience targeting.' This skill covers campaign strategy, ad creation, audience targeting, and optimization.
testing
--- name: using-sharkitect-methodology description: Use when starting any conversation in a Sharkitect workspace OR before any task involving NEW pricing, positioning, proposal, strategy, plan-execution, or schema-design work — mandates invocation of Sharkitect-specific methodology skills (pricing-strategy, marketing-strategy-pmm, smb-cfo, hq-revenue-ops, executing-plans, brainstorming) under the same anti-rationalization discipline as using-superpowers. Documentation has failed 4 times across H
testing
Use when user says 'end session', 'wrap up', 'stop for the day', 'done for today', 'close out', 'save session', 'wrapping up', or invokes /end-session. Runs the full 9-step end-of-session protocol: resource audit, MEMORY.md update, lessons capture, plan status, pending items, workspace checklist, .tmp/ audit, git commit+push, Supabase brain sync, session brief, summary. Final step schedules a detached self-kill of the current session ONLY (3s delay) so the window closes cleanly. Other claude.exe processes (active workspaces) are NOT touched -- orphan cleanup is handled separately by Claude-Orphan-Cleanup-Hourly with proper age safeguards. Do NOT use for: mid-session quick saves (use session-checkpoint), skill syncing (use sync-skills.py), brain memory queries (use supabase-sync.py pull), document freshness reviews (use document-lifecycle), resource gap detection (use resource-auditor).
testing
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases.