github.com/modu-ai/moai-adk
| Skill | Added | Review |
|---|---|---|
moai-gtd .agents/skills/moai-gtd/SKILL.md Canonical GTD entry point for capture, clarification, organization, review, and engagement | 64 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1176c97 | |
moai-harness .agents/skills/moai-harness/SKILL.md Manage harness learning subsystem (status/apply/rollback/disable) OR create a harness via natural-language analysis (Context-First Discovery + name derivation + approval gate) | 57 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1176c97 | |
moai-harness-learner .claude/skills/moai-harness-learner/SKILL.md Harness learning subsystem coordinator. Produces Tier 4 auto-update proposal payloads consumed by the orchestrator (which surfaces them via AskUserQuestion) and orchestrates Apply/Rollback flows. Triggers when harness learning proposals are pending or learning lifecycle management is needed. | 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1176c97 | |
moai-jev-skill-suggestion .claude/skills/moai-jev-skill-suggestion/SKILL.md Guidance for a display-only skill-suggestion capability: how a caller should suggest a skill to the operator, how the emitted answer is read, and what must never happen (selection, auto-loading, judgment). The capability gate ships off; this skill carries mechanism and contract ONLY — never the call path; where and how to reach the capability is the catalogue's concern. | 51 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1176c97 | |
moai-lane-watchdog .claude/skills/moai-lane-watchdog/SKILL.md One lane stall watchdog iteration: measure lane progress on three channels, classify the stall cause, apply the remedy or resolve the judgment through the decision ladder — instead of waiting on a reply — then record the outcome and report. Reads the unified --auto doctrine at .claude/rules/moai/workflow/auto-semantics.md for the ladder, the gate inventory, and the record formats. | 67 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1176c97 | |
moai-loop .agents/skills/moai-loop/SKILL.md Iteratively fix issues until all resolved or max iterations reached | 54 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1176c97 | |
moai-meta-harness .claude/skills/moai-meta-harness/SKILL.md DEPRECATED — legacy 7-Phase meta-harness. Redirects to the v4 harness Builder (/moai:harness <natural-language request>) which replaces the static 7-Phase workflow with an orchestrator-direct 4-phase Builder (ANALYZE / PLAN / GENERATE / ACTIVATE) + a manifest-driven dynamic-workflow Runner. Retained as the redirect source for backward-compat invocation paths; the 7-Phase body below is preserved as historical reference, NOT for new harness creation. | 52 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1176c97 | |
moai-mx .agents/skills/moai-mx/SKILL.md Scan codebase and add @MX code-level annotations for AI context | 59 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1176c97 | |
moai-plan .agents/skills/moai-plan/SKILL.md Create SPEC document with EARS format requirements and acceptance criteria | 58 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1176c97 | |
moai-platform-auth .moai/archive/skills/v2.16/moai-platform-auth/SKILL.md Authentication and authorization specialist covering Auth0, Clerk, and Firebase Auth. Use when implementing authentication, MFA, SSO, passkeys, WebAuthn, social login, or security features. | 55 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1176c97 | |
moai-platform-chrome-extension .moai/archive/skills/v2.16/moai-platform-chrome-extension/SKILL.md Chrome Extension Manifest V3 development specialist covering service workers, content scripts, message passing, chrome.* APIs, side panel, declarativeNetRequest, and Chrome Web Store publishing. Use when building browser extensions. | 52 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 1176c97 | |
moai-platform-database-cloud .moai/archive/skills/v3.0/moai-platform-database-cloud/SKILL.md Cloud database platform specialist covering Neon (serverless PostgreSQL), Supabase (PostgreSQL 16 with real-time), and Firebase Firestore (NoSQL with offline sync). Use when choosing or setting up cloud databases. | 52 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1176c97 | |
moai-platform-deployment .moai/archive/skills/v2.16/moai-platform-deployment/SKILL.md Deployment and hosting platform specialist covering Vercel, Railway, and Convex. Use when deploying applications, configuring edge functions, setting up continuous deployment, or managing serverless infrastructure. | 55 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1176c97 | |
moai-project .agents/skills/moai-project/SKILL.md Generate project documentation (product.md, structure.md, tech.md, codemaps/) | 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1176c97 | |
moai-ref-api-patterns .claude/skills/moai-ref-api-patterns/SKILL.md REST/GraphQL API design patterns, error handling conventions, and input validation reference for backend development. Agent-extending skill that amplifies backend domain work (spawned via Agent(general-purpose) with backend instructions) with production-grade API patterns. Use when designing APIs, implementing endpoints, or reviewing backend code. NOT for: frontend development, DevOps, database schema design, security audits. | 65 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1176c97 | |
moai-ref-aside-browser .claude/skills/moai-ref-aside-browser/SKILL.md Safe-use reference for the optional Aside browser agent (the `aside` command-line tool and its MCP server), which works inside the operator's own logged-in browser. Covers when the orchestrator may use it, how its permission modes work, and the rules that keep it read-only by default. Operated by the orchestrator alone. NOT for: public pages that a plain fetch can read, subagent work, or CI runs. | 69 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 1176c97 | |
moai-ref-cross-model-audit .claude/skills/moai-ref-cross-model-audit/SKILL.md Cross-model audit convergence reference for the plan-auditor and sync-auditor agents. Documents how to invoke the `audit_multi` MCP tool to fan a code review out across the Claude subscription, codex, and GLM (z.ai) backends, converge their independent verdicts, and fold the resulting per-backend verdicts + disagreement flag into the audit output. The single skill both audit entry points load — no duplication. | 62 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1176c97 | |
moai-ref-git-workflow .claude/skills/moai-ref-git-workflow/SKILL.md Git workflow patterns, branch strategies, conventional commits, and PR templates reference for git operations. Agent-extending skill that amplifies manager-git expertise with production-grade git workflow patterns. NOT for: code implementation, testing, architecture design, documentation content. | 60 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1176c97 | |
moai-ref-jev-question-design .claude/skills/moai-ref-jev-question-design/SKILL.md Question-design reference for the gated TypeSafe System One judgment capability. How to author typed questions that return useful, honest answers: compute the question in code, always admit a no-match answer, keep the supplied state small, phrase noul questions so both polarities are expressible. Carries the question-design rules ONLY — never the call path; where and how to reach the capability is the MCP catalogue's concern. | 58 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1176c97 | |
moai-ref-llm-security .claude/skills/moai-ref-llm-security/SKILL.md AI/LLM defensive security reference: prompt-injection defense, OWASP LLM Top 10 defensive mapping, MCP and agentic tool-call hardening, training-data poisoning detection, model-output validation and guardrails, MITRE ATLAS defensive correlation, and NIST AI RMF governance. Agent-extending skill that amplifies backend, security, and AI-application engineering with production-grade defensive patterns for LLM-backed systems. NOT for: offensive techniques (jailbreak authoring, attack-payload crafting, red-team exploitation), model training or fine-tuning methodology, prompt optimization for capability, web-app OWASP Top 10 (see moai-ref-owasp-checklist), or general API design (see moai-ref-api-patterns). | 57 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1176c97 |