skills:scan

Security Community

Skill notes

When to Use

Setting up Claude Code skills in a new repository Auditing an existing repo for skill gaps Updating skills after the repo's tech stack or workflows changed Onboarding to a new codebase

Phase 1: Analyze Repository Structure

Scan for technology markers: Check CI configuration: Check deployment patterns: Check test structure:

Phase 2: Identify Skill Categories

Based on findings, propose categories: Marker · Suggested Skills .github/workflows/ · ci:status, ci:monitoring, tdd:ci, rca:ci charts/ or helm/ · helm:debug Dockerfile · docker:build, docker:debug

Phase 3: Generate Core Skills

Every repo should have these (create with skills:write): Skill · Purpose skills:write · How to create skills skills:validate · How to validate skills skills:scan · This skill (self-referential)

Phase 4: Generate settings.json

Create .claude/settings.json with auto-approve patterns: Read operations (kubectl get, logs, describe) → auto-approve Sandbox write operations (kubectl apply on dev clusters) → auto-approve Management/destructive operations → require approval

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
Security
Author-declared agents
No explicit declaration found; this is not inferred or tested compatibility
Static check
88 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@kagenti · no license declared
Token usage
Lean
Setup complexity
Guided setup
External API key
Not required
Operating systems
Docker
Runtime requirements
Docker
Detected file/system behavior
  • Read-only
  • Write / modify
Network behavior
Local-only
Install commands
None (reference only)

Heads up: Tool permissions are not declared; actual access depends on the runtime.

01
Phase 1: Analyze Repository Structure

Scan for technology markers: Check CI configuration: Check deployment patterns: Check test structure:

02
Phase 2: Identify Skill Categories

Based on findings, propose categories: Marker · Suggested Skills `.github/workflows/` · `ci:status`, `ci:monitoring`, `tdd:ci`, `rca:ci` `charts/` or `helm/` · `helm:debug` `Dockerfile` · `docker:build`, `docker:debug`

03
Phase 3: Generate Core Skills

Every repo should have these (create with `skills:write`): Skill · Purpose `skills:write` · How to create skills `skills:validate` · How to validate skills `skills:scan` · This skill (self-referential)

04
Phase 4: Generate settings.json

Create `.claude/settings.json` with auto-approve patterns: Read operations (kubectl get, logs, describe) → auto-approve Sandbox write operations (kubectl apply on dev clusters) → auto-approve Management/destructive operations → require approval

05
Phase 1: Validate Existing Skills

Run `skills:validate` on every skill: Check for issues: Frontmatter name/directory mismatches Old-style references (dashes instead of colons) Missing Related Skills sections

06
Phase 2: Gap Analysis

Compare existing skills against the repo's actual tech stack: Run Phase 1 of the "New Repo" flow to detect technology markers Compare detected categories against existing skill categories List categories that exist in the repo but have no skills List skills that reference tools/patterns no longer in use

07
Phase 3: Content Quality Review

For each existing skill, assess: Check · Criteria Actionability · Commands are copy-pasteable, not just documentation Length · 80-200 lines (300 max). Split if too long Freshness · Commands and paths still match current repo structure

08
Phase 3b: Developer Docs Consistency

If `docs/developer/claude-code-skills.md` exists, verify: Skills listed in dev docs match actual skills — no stale references Workflow diagrams in dev docs match skill diagrams — same nodes, same flow Best practices in dev docs are enforced by skills — worktree gate, checklist items Sub-skill table is accurate — inputs, outputs, invocations match reality

09
Phase 4: Connection Analysis

For each skill, determine: Outgoing links: Skills referenced in Related Skills section Incoming links: Which other skills reference this one (search all files) Broken refs: References to skills that don't exist Orphans: Skills with no incoming references (only parent links)

10
Phase 5: Usefulness Assessment

Rate each skill 1-5: Rating · Criteria 5 · Decision trees, copy-paste commands, troubleshooting, used daily 4 · Good reference with commands, covers edge cases 3 · Useful but needs more actionability or is too long

11
Phase 6: Generate Report

Save to `/tmp/kagenti/skills-scan/`: Output a structured report:

12
Phase 7: Update Skills README

After completing the scan, update `.claude/skills/README.md`: Regenerate the Complete Skill Tree (ASCII listing of all categories and leaves) Update Mermaid workflow diagrams for root flows: TDD workflow (tdd → tdd:ci/tdd:hypershift/tdd:kind escalation) RCA workflow (rca → rca:ci/rca:hypershift/rca:kind escalation)

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.