Loading...
Loading...
Found 851 Skills
Use this skill when auditing AI agent skills for security vulnerabilities, prompt injection, permission abuse, supply chain risks, or structural quality. Triggers on skill review, security audit, skill safety check, prompt injection detection, skill trust verification, skill quality gate, and any task requiring security analysis of AI agent skill files.
Use when work must be verified in local Canvas Workbench, or when the user asks to run, open, or check a component in Workbench. Verifies that Canvas Workbench is available through the project's package runner, starts the local Workbench dev server, and keeps Workbench verification as part of the implementation workflow.
Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review, devil's advocate challenges, ethics review, and post-research literature monitoring. Triggers on: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, guide my research, help me think through, 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 事實查核, 引導我的研究, 幫我釐清, 幫我想想, 我不確定要研究什麼, 研究方向, 研究主題.
Evidence-first mailbox triage, drafting, send verification, and sent-mail-safe follow-up workflow for ECC. Use when the user wants to organize email, draft or send through the real mail surface, or prove what landed in Sent.
GANG validator skill. You are a validator, performing rule-based verification to check if the worker's handoff meets the val standards and issuing a verdict.
Browser verification, proof screenshots, traces, console and network checks, and reproducible UI evidence for Workbench QA.
Perform cross-source validation on academic literature entry by entry, compare fields including authors, titles, years, volumes/issue numbers, and page numbers, mark issues such as conflicts between volume year and DOI year, abnormal author order, and page number deviations, and output a structured verification report. It supports batch processing of reference lists in entire papers/proposal reports, single-entry verification, and synchronous correction with Zotero.
Guide Agents to accurately call taiwan-legal-db and dr-lawbot (semantic precedent retrieval) MCP tools in a hallucination-resistant manner to retrieve Taiwanese laws, precedents, and constitutional judgments, and implement citation verification and trust gates.
Implement secure webhook systems for event-driven integrations, including signature verification, retry logic, and delivery guarantees. Use when building third-party integrations, event notifications, or real-time data synchronization.
Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification. Masters screenshot analysis, visual regression testing, and component validation. Use PROACTIVELY to verify UI modifications have achieved their intended goals through comprehensive visual analysis.
Creates comprehensive deployment checklists with pre-deployment checks, smoke tests, verification steps, and sign-off workflows. Use for "deployment checklist", "release verification", "deployment runbook", or "production readiness".
TDD workflow planning with Red-Green-Refactor task chain generation, test-first development structure, cycle tracking, and post-execution compliance verification. Triggers on "workflow:tdd-plan", "workflow:tdd-verify".