knowledge-base-health-check
Audits a local Claude-managed knowledge base in Simon's '/Users/simon/Claude CoWork/Knowledge Base/' system. Surfaces contradictions between articles, broken backlinks, unsourced claims, stale articles, writing-rules violations, and three suggested new articles. Files a full report into the KB's 'Outputs/' folder, appends a one-line CHANGELOG entry, and (in interactive sessions) walks through which findings to action. Use this skill whenever the user says "run a health check", "audit the [name] KB", "audit my knowledge base", "check the wiki", "let's go through the health check report", or "action the latest health check". Also use when the monthly scheduled task 'knowledge-base-monthly-health-check' fires. Use this skill for any audit-style request against a folder under 'Knowledge Base/' even if the user doesn't say the word "health check" - the protocol is the same.
What this skill does
# Knowledge Base Health Check Skill This skill is the source of truth for the monthly knowledge base health check. The librarian reads it and follows it whenever a health check is invoked, on demand or via the scheduled task. The protocol is deliberately the same for both trigger paths so the output format is stable across runs. ## When to invoke Run this skill when any of the following happens: • The user says "run a health check", "audit the [name] KB", "check the wiki", or similar. or writes "/healthcheck" • The user says "action the latest health check" or "let's go through the health check report" - in that case, jump straight to Phase 2 using the most recent health-check report in the relevant KB's Outputs/ folder. • The monthly scheduled task fires it (taskld: knowledge-base-monthly-health-check ). If the user doesn't specify which KB, askl Don't run on every KB unless explicitly asked. ## The two phases The skill runs in two phases. Phase 1 always runs. Phase 2 runs only in interactive sessions - the scheduled task stops at the end of Phase 1. ### Phase 1 — Audit and file (always) 1. Read the rules. Open About me/writing-rules. md and the per-KB CLAUDE.md for the KB being audited. The writing rules govern the writing-rules check; the per-KB rules govern Wiki structure and source provenance. 2. Read state files. <KB>/CHANGELOG.md (last health check date and what's happened since), <KB>/Wiki/QUESTIONS.md (already-flagged gaps so they aren't double-flagged), <KB>/RAW/\_INGESTED. md (registry of what's in RAW). 3. Read everything in scope. Every article in <KB>/Wiki/, every file in <KB>/RAW/ (at least the frontmatter and titles — full read only when verifying a specific claim), every output in <KB>/Outputs/ filed since the last health check. 4. Run the seven audits. Detailed below. 5. Write the full report to <KB>/Outputs/YYYY-MM-DD_health-check.md 6. Append a one-line summary to <KB>/CHANGELOG.md at the top, format as in Logging below. 7. Surface the chat summary. Print a tight summary into chat — counts only, plus the top three findings worth the user's attention, and a link to the full report. Do not dump the whole report. ### Phase 2 - Ask and action (interactive only) 8. Ask which findings to action. Use AskUserQuestion with multi-select options drawn from the categories that actually have findings. Skip categories that came up clean.
Related in Security
mac-ops
IncludedComprehensive macOS workstation operations — diagnose kernel panics, identify failing drives, audit launchd startup items, decode wake reasons, triage TCC permission denials, manage APFS snapshots, recover from no-boot. Use for: Mac is slow, slow bootup, won't boot, kernel panic, kernel_task hot, mds_stores CPU, photoanalysisd, cloudd, login loop, gray screen, sleep wake failure, drive failing, IO errors, APFS snapshots eating space, Time Machine local snapshots, Spotlight indexing, launchd, LaunchAgent, LaunchDaemon, login items, TCC permissions, Full Disk Access, Screen Recording denied, Gatekeeper, quarantine, com.apple.quarantine, app is damaged, helper tool, /Library/PrivilegedHelperTools, pmset, wake reasons, dark wake, sysdiagnose, panic.ips, DiagnosticReports, configuration profile, MDM profile, remote diagnostics over SSH.
a11y-audit
IncludedRun accessibility audits on web projects combining automated scanning (axe-core, Lighthouse) with WCAG 2.1 AA compliance mapping, manual check guidance, and structured reporting. Output is configurable: markdown report only, markdown plus machine-readable JSON, or markdown plus issue tracker integration. Use this skill whenever the user mentions "accessibility audit", "a11y audit", "WCAG audit", "accessibility check", "compliance scan", or asks to check a web project for accessibility issues. Also trigger when the user wants to verify WCAG conformance or map findings to a specific standard (CAN-ASC-6.2, EN 301 549, ADA/AODA).
erpclaw
IncludedAI-native ERP system with self-extending OS. Full accounting, invoicing, inventory, purchasing, tax, billing, HR, payroll, advanced accounting (ASC 606/842, intercompany, consolidation), and financial reporting. 413 actions across 14 domains, 43 expansion modules. Constitutional guardrails, adversarial audit, schema migration. Double-entry GL, immutable audit trail, US GAAP.
assess
IncludedAssesses and rates quality 0-10 across multiple dimensions (correctness, maintainability, security, performance, testability, simplicity) with pros/cons analysis. Compares against project conventions and prior decisions from memory. Produces structured evaluation reports with actionable improvement suggestions. Use when evaluating code, designs, architectures, or comparing alternative approaches.
spring-boot-security-jwt
IncludedProvides JWT authentication and authorization patterns for Spring Boot 3.5.x covering token generation with JJWT, Bearer/cookie authentication, database/OAuth2 integration, and RBAC/permission-based access control using Spring Security 6.x. Use when implementing authentication or authorization in Spring Boot applications.
code-hardcode-audit
IncludedDetect hardcoded values, magic numbers, and leaked secrets. TRIGGERS - hardcode audit, magic numbers, PLR2004, secret scanning.