发现 Skills

Guidance for analyzing log files and generating summary reports with counts aggregated across multiple date ranges and severity levels. This skill applies when tasks involve parsing log files by date, counting occurrences by severity (ERROR, WARNING, INFO), and outputting structured CSV summaries across time periods like "today", "last 7 days", or "last 30 days".

This skill provides guidance for semantic similarity retrieval tasks using embedding models (e.g., MTEB benchmarks, document ranking). It should be used when computing embeddings for documents/queries, ranking documents by similarity, or identifying top-k similar items. Covers data preprocessing, model selection, similarity computation, and result verification.

Research standards/patterns via MCP Ref. Generates Standards Research for Story Technical Notes subsection. Reusable worker.

Coordinates security scanning (secrets + deps). Delegates to ln-761 and ln-625 (mode=vulnerabilities_only). Generates SECURITY.md, pre-commit hooks, and CI workflow.

Conduct deep research on any topic using parallel subagents and web tools (web_search, web_fetch, playwright). Use for queries that require comprehensive research from multiple perspectives.

Build a content marketing program by producing a Content Marketing Plan Pack (content–market-fit brief, demand-validated SEO topic map, human-voice + primary channel strategy, editorial calendar, content briefs, AI-assisted writing SOP, measurement plan). Use for content marketing, content strategy, blog, SEO, thought leadership, founder-led content. Category: Marketing.

Jailbreak API-served LLMs using G0DM0D3 techniques — Parseltongue input obfuscation (33 techniques), GODMODE CLASSIC system prompt templates, ULTRAPLINIAN multi-model racing, encoding escalation, and Hermes-native prefill/system prompt integration. Use when a user wants to bypass safety filters, jailbreak a model, or red-team model robustness.

Applies Bayesian reasoning to systematically update probability estimates with new evidence, helping make better forecasts and avoid overconfidence. Use when making predictions or judgments under uncertainty, forecasting outcomes, evaluating probabilities, testing hypotheses, calibrating confidence, assessing risks with uncertain data, or when user mentions priors, likelihoods, Bayes theorem, probability updates, forecasting, calibration, or belief revision.

Synthesizes information from multiple sources into coherent insights and applies analogical reasoning to transfer knowledge across domains. Use when conducting literature reviews, integrating stakeholder feedback, reconciling conflicting viewpoints, identifying cross-source patterns, creating explanatory analogies ("X is like Y"), finding creative solutions through cross-domain transfer, or testing whether analogies hold (surface vs deep). Use when user mentions "synthesize", "combine sources", "analogy", "similar to", "transfer from", "integrate findings".

Systematic approach to discovering novel vulnerabilities through code analysis, fuzzing, and attack surface research

Use when designing REST or GraphQL APIs, defining endpoints, implementing pagination/filtering, handling API versioning, or establishing API documentation with OpenAPI/Swagger.

Plugin release process for MAG Claude Plugins marketplace. Covers version bumping, marketplace.json updates, git tagging, and common mistakes. Use when releasing new plugin versions or troubleshooting update issues.

YAML frontmatter schemas for Claude Code agents and commands. Use when creating or validating agent/command files.

Analyze and optimize E-E-A-T signals (Experience, Expertise, Authority, Trust) for content credibility. Use when auditing content for Google quality signals, improving author credibility markers, or diagnosing why content lacks trust signals. Provides signal-by-signal implementation framework.

Remove AI flavor from web fiction. Detects and removes AI writing traces in text to restore natural, human-feel prose. Trigger methods: /story-deslop, /remove-ai, "remove AI flavor", "de-AI", "deslop", "this is too AI"

Comprehensive FastAPI skill for building modern Python web APIs with focus on customer support systems, ticket management, real-time chat, and backend operations

This skill should be used when users want to scrape multiple websites (Firecrawl, Parallel, or hybrid), extract brand guideline signals (including CSS variables and computed styles via browser probing), generate per-site prompt packs, and blend sources into a composite brand direction with exactly three outputs: brand_guidelines.md, prompt_library.json, design_tokens.json.

Generate cinematic, film-style video prompts for Seedance 2.0 (Higgsfield). Use when users want cinematic, filmic, movie-quality, Hollywood-style, dramatic, or professional film-grade AI video. Trigger words: cinematic, filmic, movie scene, dramatic lighting, depth of field, lens flare, distortion, letterbox, film noir, epic, stabilized camera, dolly shot, crane shot, or any movie-grade video generation request. Use this skill even if the user does not explicitly say cinematic but describes film aesthetics.

arc42 architecture documentation template and guidance

Deploy universal wisdom voices from all traditions simultaneously - Hindu, Buddhist, Taoist, Abrahamic, Indigenous, Scientific - revealing their unified recognition of consciousness navigation.

Navigate through the original three-world shamanic technology. Deploy when soul retrieval, power animal guidance, or journey between realms emerges. Deeply respectful of Tungus, Buryat, Yakut, Evenki traditions. Use for consciousness navigation, NOT cultural appropriation.

Test smart contracts comprehensively using Hardhat and Foundry with unit tests, integration tests, and mainnet forking. Use when testing Solidity contracts, setting up blockchain test suites, or validating DeFi protocols.

Use this skill when the user wants to "report a bug", "file an issue", "report an issue", "submit a bug report", or report any problem with the mcp-apps plugin to the GitHub repository.

Retrieve NBA game information from ESPN public APIs, including daily scoreboards, game summaries, boxscores, play-by-play, team lists, team schedules, and standings context. Use when requests ask for NBA scores, live game status, specific game-id details, or team-centric recent/upcoming game context.