Loading...
Loading...
Found 766 Skills
Three-layer verification pipeline for AI output. Extracts verifiable claims, finds supporting or contradicting sources via web search, runs adversarial review for hallucination patterns, and produces a structured verification report with source links for human review.
Use this skill for mathematical code verification. Use when reviewing math-heavy code, verifying algorithm correctness, checking numerical stability, aligning with mathematical standards. Do not use when general algorithm review - use architecture-review. DO NOT use when: performance optimization - use parseltongue:python-performance.
Production deployment principles and decision-making. Safe deployment workflows, rollback strategies, and verification. Teaches thinking, not scripts.
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.
Pre-commit quality checklist covering lint, typecheck, tests, code-spec sync, API changes, database migrations, cross-layer verification, and manual testing. Blocks commit if infra or cross-layer specs lack executable depth. Use when code is written and tested but not yet committed, before submitting changes, or as a final review before git commit.
Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships.
Chinese functional specification creation tool used to convert natural language feature descriptions into structured functional specification documents. Supports automatic branch name generation, Git branch creation, specification file initialization, and quality verification. Trigger words include: "speckit specification", "functional specification", "create specification", "feature description conversion", "speckit-specify". Use this skill when users need to convert feature ideas into structured specifications.
Enforces spec-before-code workflow for AI-driven development. Automatically selects Spec-Kit or OpenSpec mode, triages complexity (quick/standard/thorough), recovers session context, and applies quality gates (G0-G4) with automated review loops at every stage. Use this skill whenever the user says "/super-spec", "spec first", "规范先行", or starts any feature, bugfix, or refactor — especially in projects with .spec-mode, .specify/, or openspec/ directories. Even if the user doesn't explicitly ask for spec-driven workflow, activate this skill for any non-trivial code change to prevent skipping the design phase. Orchestrates: Spec-Kit/OpenSpec (OPSX) + planning-with-files + ui-ux-pro-max (v2.0, 67 styles, 161 palettes, 13 stacks) + Superpowers (TDD, code review, verification, debugging, spec/plan review loops, subagent model selection).
SafetyMails platform help — bulk email verification (up to 2M emails, 19-step algorithm), real-time API validation (JavaScript embed for forms), Email Finder (B2B corporate lookup), list cleaning, spamtrap/disposable/catch-all detection, integrations. Use when asking 'how do I do X in SafetyMails', verifying emails with SafetyMails, cleaning email lists in SafetyMails, setting up SafetyMails API/JavaScript embed, using SafetyMails Email Finder, or managing SafetyMails integrations. Do NOT use for general deliverability strategy across tools (use /sales-deliverability), general enrichment strategy (use /sales-enrich), building prospect lists (use /sales-prospect-list), or connecting tools generically (use /sales-integration).
Guides the agent through upgrading a Capacitor app project to a newer major version. Covers multi-version jumps, dependency alignment, native platform checks, and verification. Do not use for plugin library upgrades or non-Capacitor mobile frameworks.
Solve competition math problems (IMO, Putnam, USAMO, AIME) with adversarial verification that catches the errors self-verification misses. Activates when asked to 'solve this IMO problem', 'prove this olympiad inequality', 'verify this competition proof', 'find a counterexample', 'is this proof correct', or for any problem with 'IMO', 'Putnam', 'USAMO', 'olympiad', or 'competition math' in it. Uses pure reasoning (no tools) — then a fresh-context adversarial verifier attacks the proof using specific failure patterns, not generic 'check logic'. Outputs calibrated confidence — will say 'no confident solution' rather than bluff. If LaTeX is available, produces a clean PDF after verification passes.
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.