安全
安全扫描与漏洞检测
create-github-action-workflow-specification
adui-studio
"Create a formal specification for an existing GitHub Actions CI/CD workflow, optimized for AI consumption and workflow maintenance."
red-team-adversary
famaoai-creator
Output path for report
mcp-aws-knowledge-connector
famaoai-creator
status: implemented
rails-security
scottwater
"Run a multi-agent security review of Rails application code. Use when the user asks for a Rails security review or audit, or raises a specific concern — authorization/IDOR/tenant isolation, XSS/SQL injection/SSRF, vulnerable gems/Brakeman/bundle audit, or prompt injection in AI features."
quality-scorer
famaoai-creator
Output JSON path
cloud-waste-hunter
famaoai-creator
Actively identifies and eliminates unused or over-provisioned cloud resources. Goes beyond estimation to hunt for actual cost savings in live environments.
supply-chain-sentinel
famaoai-creator
Output path for report
security-scanner
famaoai-creator
Scans the codebase for security risks.
youtube-transcript
ryanhudson
This skill should be used when the user provides a YouTube URL and wants to "download transcript", "get captions", "get subtitles", "transcribe video", or extract text content from a YouTube video. Handles manual subtitles, auto-generated captions, and Whisper transcription as fallback.
sql-code-review
adui-studio
"Universal SQL code review assistant that performs comprehensive security, maintainability, and code quality analysis across all SQL databases (MySQL, PostgreSQL, SQL Server, Oracle). Focuses on SQL injection prevention, access control, code standards, and anti-pattern detection. Complements SQL optimization prompt for complete development coverage."
research
alternative-intelligence-cp
Find and record an up-to-date fact about the world outside the compiler tree — a standard's current edition, a release number, a known defect in prior art, current guidance — and return it as a dated, sourced digest. Use when a plan pins an external version, when a worker meets a question the specifications do not answer, when a library is security-sensitive, and at every audit.
review-brief
mike548141
Write a peer-review brief and run an independent review of work before it is trusted — atelier's enforcement half. Use when work earns a review — the trigger is commitment, not artefact: a design others will build to, a decision that forecloses alternatives, or a diff that ships (structural/first-of-kind work, doctrine, a silent-failure surface, anything irreversible or public) — when the user asks to review a design/diff/branch "properly", or to draft the brief a fresh session will run cold.
slack-communicator-pro
famaoai-creator
status: implemented
code-review
dmonteroh
"Provides high-signal, fast code review with selectable modes (quality, security, performance, tooling). Includes an optional safe-by-default review script to summarize diffs, scan for risky patterns, and produce a deterministic report."
writing-crypto
dbosk
Write cryptography prose and notation using the project's bibsp.sty + preamble.tex conventions (acro + biblatex footnote citations and standardized math macros). Use proactively when: (1) writing/editing cryptography sections in .tex files, (2) introducing or using crypto acronyms such as IND-CPA, IND-CCA, AE, MAC, PRF, ZK, and DH, (3) defining schemes/algorithms/variables in math notation, (4) adding citations for security notions or standard primitives, (5) writing security proofs or reductions, (6) user mentions biblatex, crypto notation, or security proof in cryptographic context.
everclaw
profbernardoj
Open-source first AI inference — GLM-5 as default, Claude as fallback only. Own your inference forever via the Morpheus decentralized network. Stake MOR tokens, access GLM-5, GLM-4.7 Flash, Kimi K2.5, and 30+ models with persistent inference by recycling staked MOR. Open-source first model router routes all tiers to Morpheus by default — Claude only kicks in as an escape hatch when needed. Includes Morpheus API Gateway bootstrap for zero-config startup, OpenAI-compatible proxy with auto-session management, automatic retry with fresh sessions, OpenAI-compatible error classification to prevent cooldown cascades, multi-key auth rotation v2 with proactive DIEM balance monitoring and reactive 402 watchdog, Gateway Guardian v5 with direct curl inference probes (eliminates Signal spam), proactive Venice DIEM credit monitoring, circuit breaker for stuck sub-agents, nuclear self-healing restart, always-on proxy-router with launchd auto-restart, smart session archiver, three-shift cyclic execution engine (v2 with 15-minute execution loops), 24/7 always-on power configuration for macOS, bundled security skills, zero-dependency wallet management via macOS Keychain, x402 payment client for agent-to-agent USDC payments, ERC-8004 agent registry reader for discovering trustless agents on Base, and hardware-aware local Ollama fallback with auto model selection (Qwen3.5 family, 1.5B–72B based on available RAM/GPU).
stakeholder-communicator
famaoai-creator
Output file path
constellation-team
PrakharMNNIT
Coordinate a cross-functional star-team workflow (Product Manager, Principal Engineer, Backend, Frontend, QA/Security, DevOps) with mandatory architecture and code-review checkpoints. Use when a request needs end-to-end product delivery, multi-role collaboration, or explicit role-based outputs (PM/PE/Backend/Frontend/QA/DevOps), or when the user asks for "star team", "cross-functional", "full lifecycle", or "multi-role" planning.
strategic-roadmap-planner
famaoai-creator
Output file path
seven-advisors
krishagel
Seven Advisors decision council - structured multi-perspective deliberation for important decisions. Use when facing complex choices, strategic decisions, or when you need to think through a problem from multiple angles.
ai-ethics-auditor
famaoai-creator
status: implemented
executive-reporting-maestro
famaoai-creator
Output file path (JSON or .md)
SakJules-github-organization-administration
beer-sakthai
"GitHub organization admin: manage org/team roles, audit logs, policies, secrets, and billing."
backend-principle-eng-typescript-pro-max
PrakharMNNIT
"Principal backend engineering intelligence for TypeScript services. Actions: plan, design, build, implement, review, fix, optimize, refactor, debug, secure, scale backend code and architectures. Focus: correctness, reliability, performance, security, observability, scalability, operability, cost."