All authors
Claude Skills by HuntsDesk
github.com/HuntsDesk15 skills0 installs15 views
- BootstrapUse when setting up a new project with the ve-kit framework, adding a layer to an existing setup, or upgrading an older .claude/ config. Runs the ve-kit BOOTSTRAP protocol interactively — prerequisite checks, project-info questions, writes all rules/hooks/skills/agents files, builds the Vibe Board MCP server, self-verifies at the end. Triggers on "/bootstrap", "set up this project with ve-kit", "run the bootstrap", or "upgrade my ve-kit setup".Votes: 0GitHub stars: 3
- CloseWind this window down so it can be closed without losing anything. Stashes this session's own uncommitted edits by explicit path, returns its in-progress Vibe Board tasks, ends the board session with a handoff, and files anything that needs a HUMAN on the human task board. Run when the user types /close, or when a cross-session message quotes the user's instruction to close windows. Never self-initiate.Votes: 0GitHub stars: 3
- GoFull autonomous RIPER cycle in one command. Runs RESEARCH → PLAN → REVIEW → EXECUTE → REVIEW with auto-advance on REVIEW PASS. Stops only on REVIEW FAIL, user-required decisions, or safety guards.Votes: 0GitHub stars: 3
- PlanUse when entering PLAN mode or when the user says "Enter P". Creates structured implementation plans with Vibe Board tasks and specialist agent assignments for each checklist item.Votes: 0GitHub stars: 3
- Review AgentsReview all specialist agent definitions in .claude/agents/ for accuracy, currency, and Anthropic best-practice compliance. Flags stale references, wrong model assignments, missing examples, merge/split candidates, and gap-analysis coverage. Files every finding to the board (tasks for high/critical, a ledger comment for medium/low).Votes: 0GitHub stars: 3
- Review AllOrchestrator that runs the full review-* family (rules, agents, skills, docs, memory, board, security) and aggregates findings under a single board parent task. Produces a prioritized remediation roadmap. Use for full system audits.Votes: 0GitHub stars: 3
- Review BoardReview the Vibe Board (Firebase Firestore) for stale tasks, orphans, duplicates, done-but-unmarked work, abandoned projects, session handoff quality, and referential integrity. Files every finding to the board (tasks for high/critical, a ledger comment for medium/low).Votes: 0GitHub stars: 3
- Review DocsReview the docs/ hub for broken links, staleness, duplicate coverage, index currency, and size bloat. Files every finding to the board (tasks for high/critical, a ledger comment for medium/low).Votes: 0GitHub stars: 3
- Review MemoryReview the per-project auto-memory directory at ~/.claude/projects/<slug>/memory/ for index currency, stale entries, duplicates, type correctness, and uncaptured patterns. Files every finding to the board (tasks for high/critical, a ledger comment for medium/low).Votes: 0GitHub stars: 3
- Review RulesReview the core instruction layer — CLAUDE.md, .claude/rules/*.md, and RIPER/CAT mode definitions — for size, staleness, cross-reference integrity, alignment with active hooks, and redundancy. Files every finding to the board (tasks for high/critical, a ledger comment for medium/low).Votes: 0GitHub stars: 3
- Review SecuritySecurity audit of the .claude/ configuration layer — secrets leaked in agent/skill bodies, overly broad permissions, deny list gaps, hook script shell injection, MCP server tool grants, dangerous agent instructions. Distinct from the built-in /security-review which audits code changes. Files every finding to the board (tasks for high/critical, a ledger comment for medium/low).Votes: 0GitHub stars: 3
- Review SkillsReview all skill definitions in .claude/skills/ for frontmatter correctness, progressive-disclosure hygiene, trigger clarity, merge/split candidates, and gap analysis. Files every finding to the board (tasks for high/critical, a ledger comment for medium/low).Votes: 0GitHub stars: 3
- ReviewUse when entering REVIEW mode or when the user says "Enter RE". Validates plans or implementations by invoking specialist sub-agents based on what changed. Detects whether this is a post-plan review or post-execute review automatically.Votes: 0GitHub stars: 3
- Self ImproveMine recent Vibe Board review findings + worker batch outcomes for RECURRING patterns, then propose preventive guardrails — LESSONS.md rules (applied), agent-definition hardening (proposed), and flagged CLAUDE.md / rules proposals (human approval only). The feedback loop that turns "what reviewers keep catching" into "encoded so it stops happening." Run manually or after every ~5 worker batches.Votes: 0GitHub stars: 3
- Build AgentsInterview a codebase for the specialist agents it actually deserves, then build them properly. Surveys structure, churn and fix-density; proposes a SMALL set of candidates with evidence; asks which to create; interviews you per candidate; writes valid `.claude/agents/<name>.md`; registers them in the roster and the tier manifest; verifies they load. Use when a project has no agents yet, when a new domain has grown an owner-shaped hole, or when someone asks "what agents should this repo have?"...Votes: 0GitHub stars: 3