.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/majiayu000/vibeguard
home/skills/majiayu000/vibeguard
majiayu000 avatar

majiayu000/vibeguard

27 skills

View on GitHub
$npx skills add majiayu000/vibeguard
SkillInstalls
agentsmd-auditAudit AGENTS.md / CLAUDE.md against the five high-leverage patterns (progressive disclosure, procedural workflows, decision tables, production code examples,…—auto-optimizeAutomate analysis, evaluation, design and optimization of target projects.—benchmark-regression-triageUse this skill whenever VibeGuard hook latency, benchmark-action output, GitHub Actions bench-output artifacts, or a suspected performance regression needs…—eval-harnessAssessment-driven development — Quantify code generation quality with pass@k / pass^k metrics, automatically scored by Grader.—fixflowExecute coding tasks with a strict delivery workflow: build a full plan, implement one step at a time, run tests continuously, and commit by default after each…—implxUse when the user says \"implx\", \"use implx\", \"用 implx\", or asks for the one-line SpecRail queue shortcut.—iterative-retrievalIterative retrieval — 4-stage loop (DISPATCH→EVALUATE→REFINE→LOOP) to pinpoint relevant information in the code base. Up to 3 rounds.—optflowDiscover and deliver repository optimization work end to end: identify performance/reliability/maintainability/security/dx/cost optimization points, prioritize…—plan-flowAnalyze repository-level duplicate/redundant design first, then build and execute a strict step-test-update plan in docs/plan.—plan-modeUse when the user asks to enter Plan mode, says /prompts:plan or /plan, or wants a structured execution plan written to plan/.—specrail-check-impl-against-specUse when comparing a SpecRail implementation, diff, or PR against its linked issue, product spec, technical spec, and task plan.—specrail-diagnose-ciUse when diagnosing or fixing CI failures in a SpecRail-governed repository.—specrail-implementUse when implementing a SpecRail-governed issue after the implementation gate.—specrail-implement-queueUse when implementing or draining a GitHub issue/PR queue in a SpecRail-governed repository where approved specs already exist, such as multiple numbered…—specrail-installUse when installing, updating, verifying, or adopting SpecRail for agents.—specrail-plan-tasksUse when turning an approved SpecRail product and technical spec into the numbered `tasks.md` plan.—specrail-pr-gateUse before reporting a SpecRail PR as merge-ready. Collects read-only PR evidence, runs the offline PR gate, checks linked work, current head SHA, CI, review…—specrail-release-noteUse when drafting a SpecRail release note after a linked PR has merged.—specrail-review-prUse when performing an advisory SpecRail PR review. Checks linked issue/spec evidence, route gates, verification evidence, review-thread state, human-gate…—specrail-triage-issueUse when triaging a GitHub issue or issue-like request in a SpecRail-governed repository.—specrail-workflowUse as the router/startup skill when working in a repository that adopts SpecRail for issue-first, spec-first, AI-assisted development.—specrail-write-product-specUse when writing or updating a SpecRail product spec for a linked issue.—specrail-write-tech-specUse when writing or updating a SpecRail technical spec for a linked issue.—trajectory-reviewPost-hoc diagnosis of a failed agent trajectory. Classifies the first unrecoverable step into one of nine failure categories (plan adherence, hallucinated…—vibeguardUse when the user asks Codex to apply VibeGuard anti-hallucination rules, inspect VibeGuard observability, or route a task through VibeGuard…—vibeguard-observeUse when the user asks for a VibeGuard dashboard, hook health, stats, doctor output, metrics export, or local observability status from the Codex App plugin.—vibeguard-setupUse when the user asks to install, verify, inspect, or remove VibeGuard Codex hooks through the Codex App plugin.—