AI Agent Skills

Audit and refine a skill repository, a single skill, a workflow framework, or an eval set. Covers design quality, context engineering, purpose fit, evidence discipline,…

Construction d'agents de navigation web autonomes incluant scraping intelligent, interaction DOM et gestion de sessions. Se déclenche avec "browser agent", "agent naviga…

Use to plan modernization, framework upgrades, service extraction, schema migrations, rewrites, and rollback paths.

Use to extract a source-cited QEMU register and behavior contract from drivers, datasheets, firmware, device trees, runtime traces, and SVD, IP-XACT, SystemRDL, or vendo…

Performs model-guided essence extraction into a final judgment, memorable aha moment, core pillars, and minimal reasons for decision clarity. Use when the user wants to…

Brand voice extraction expertise — auto-activates on copywriting tasks to capture and replicate client tone

Extract or steal an ML/LLM model's parameters, training data, or system prompt via query access — model stealing, membership inference, training-data extraction. Load wh…

Create a bilingual Notion job application tracker and organize job links, full JDs, screenshots, and application updates into it. Use for bulk job tracking, exhaustive e…

Capture Linux.do / L站 topic list titles, links, ids, categories/tags, reply/view/update snippets from the Codex in-app browser login session. Use when the user asks to 抓…

Score a tailored CV against a previously saved job analysis artifact. Use when the user wants a grounded 0-100 match score without re-running job extraction.

Tailor a master CV using a previously saved job analysis artifact. Use when the user wants to update a CV from a stored JD analysis instead of re-running job extraction.

Plan and run the full API-first GTM chain - the orchestrator (step 00) that turns an ICP description plus optional budget, volume, and urgency into the right discovery -…

Audit a codebase for places Hydrafetch would replace fragile scraping infrastructure or add a capability the project lacks. Discovers current endpoints and tools at runt…

Assemble many pages into a table using queued crawl and batch jobs rather than a loop. Use for corpora, bulk enrichment, or any job over more than a handful of URLs.

Design human-visible, machine-readable website layers for AI assistants, RAG, and agentic search. Use this skill when the user asks for llms.txt, LLM discovery plans, vi…

SEO & GEO (Generative Engine Optimization) for websites. Analyze keywords, generate schema markup, optimize for AI search engines (ChatGPT, Perplexity, Gemini, Copilot,…