Explore skills
Showing 29701–29730 of 71536 skills
Use when designing defensive monitoring for agent systems whose risks accumulate across users, sessions, subagents, files, or tool calls. Adds online cross-context clustering with rare escalation, time-to-detect evaluation, provenance checks for control-like workspace content, and sanitized commits for persistent prompt-injection defense.
mouadja02/skills
Stars: 13Claude CodeCodexBuilds AI-powered trading and financial analysis agents with multi-agent LLM architectures: research pipelines, sentiment signals, portfolio optimization, backtesting, risk guardrails, and market monitoring. Use when designing or implementing an LLM-based trading or market-analysis system.
mouadja02/skills
Stars: 13Claude CodeCodexUse when diagnosing agent benchmarks or runtime failures from trajectories instead of aggregate pass rates. Builds shared action-observation decision landscapes, identifies productive cores and trap regions, profiles Access/Trap/Repair behavior, and designs conservative trap-triggered recovery experiments.
mouadja02/skills
Stars: 13Claude CodeCodexUse when designing evaluation suites for agentic systems, choosing agent benchmarks, measuring multi-agent performance, or critiquing single-score evaluation of agents. Based on arXiv:2605.26112v1. Trigger phrases: "evaluate my agent", "benchmark agent", "measure agent reliability", "pass^k evaluation", "agent metrics beyond success rate", "trajectory quality", "memory hygiene metric", "longitudinal agent eval", "why my agent scores well on benchmarks but fails in production".
mouadja02/skills
Stars: 13Claude CodeCodexSet up and optimize a complete local AI infrastructure — Ollama, Open WebUI, local RAG pipelines, and private model serving. Use when running models locally for privacy, compliance, offline use, or cost, or setting up GPU-accelerated local inference and RAG.
mouadja02/skills
Stars: 13Claude CodeCodexUse when evaluating MCP-enabled agents, tool-using LLM systems, multi-server workflows, tool-selection quality, trajectory quality, task completion, or MCP security regressions.
mouadja02/skills
Stars: 13Claude CodeCodexUse when comparing basic, enhanced, GraphRAG, or agentic RAG designs, evaluating domain-specific RAG quality, tuning retrieval components, or deciding whether agentic RAG is worth its cost.
mouadja02/skills
Stars: 13Claude CodeCodexUse when improving, evolving, benchmarking, or maintaining agent skills over time. Treats skills as long-lived structured artifacts: execute tasks, diagnose trajectory evidence, accumulate textual momentum, patch at the correct abstraction layer, test per model and harness, canary changes, and roll back regressions.
mouadja02/skills
Stars: 13Claude CodeCodexAlso use for async Python patterns, Pydantic schemas for LLM structured outputs, retry strategies for LLM calls, background AI jobs, or any service combining FastAPI and LLMs. If Python + AI backend is in scope — use this skill
mouadja02/skills
Stars: 13Claude CodeCodexUse when turning GitHub issues or bug reports into reproducible coding-agent repair loops with sandboxed execution, focused tests, patch generation, and regression verification.
mouadja02/skills
Stars: 13Claude CodeCodexUse when long-lived agents, project memories, system prompts, or playbooks are repeatedly summarized, rewritten, or optimized and risk losing domain detail, provenance, or execution learnings.
mouadja02/skills
Stars: 13Claude CodeCodexUse when designing or auditing long-term memory for persistent AI agents. Stores immutable source evidence before canonical facts, links beliefs to provenance, applies novelty-aware ADD/UPDATE/NOOP write gating, keeps uncertain merges explicit, separates retrieval from answer generation, supports deletion, and evaluates memory failures layer by layer.
mouadja02/skills
Stars: 13Claude CodeCodexWrites and reviews dbt projects targeting Snowflake: models, schema.yml metadata, sources, tests, macros, and project structure. Use when building or reviewing dbt models, generating dbt YAML, or applying dbt best practices.
mouadja02/skills
Stars: 13Claude CodeCodexConverts ETL pipeline metadata (Informatica IICS, PowerCenter XML, and similar) into clean dbt models, SQL, and YAML rather than a mechanical one-to-one translation. Use when migrating legacy ETL mappings to dbt.
mouadja02/skills
Stars: 13Claude CodeCodexWrites and reviews Snowflake-specific SQL: QUALIFY, FLATTEN, VARIANT/OBJECT/ARRAY handling, streams, tasks, stages, and warehouse-aware patterns. Use when generic SQL is not enough on Snowflake — semi-structured data, incremental pipelines, or Snowflake DDL.
mouadja02/skills
Stars: 13Claude CodeCodexBuild hyper-personalized, narrative-driven, single-file portfolio/pitch websites in the style of anass.pro. Use when the user asks for a "site like anass.pro", a one-recipient candidacy/pitch site, a behavioral-engineering landing page, a single-file storytelling portfolio with a pixel-art game hero, custom cursor, typewriter text, procedural Web Audio SFX, scroll-revealed scenes, or a dark purple narrative interface that addresses one named reader. Trigger on phrases like "personal pitch site", "one-page candidacy", "narrative portfolio", "scrollytelling pitch", "pixel-art hero", "interactive landing for X", or any request to recreate / clone / adapt anass.pro.
mouadja02/skills
Stars: 13Claude CodeCodexGenerates SaaS boilerplate: authentication, database schemas, billing, API routes, and CI/CD. Use when bootstrapping a new full-stack SaaS product rather than wiring those pieces by hand.
mouadja02/skills
Stars: 13Claude CodeCodexTurns any codebase into branded, presentation-ready SVG diagrams and an optional smooth animated HTML slide deck. Analyzes a repository in any language (Markdown, Python, Rust, dbt, SQL, JS/TS, Java, Go, ...), extracts its architecture / flow / story, and generates eye-friendly 16:9 diagrams plus a polished, professional presentation. Use when the user asks to visualize, diagram, document, illustrate, or present a codebase, architecture, pipeline, or project; to build slides or a deck about a repo; or to produce diagrams from code. Defaults to the company brand palette (#03045e, #0077b6, #00b4d8, #90e0ef, #caf0f8) and writes to docs/diagrams/ and docs/presentation.html.
mouadja02/skills
Stars: 13Claude CodeCodexGenerate polished reveal.js HTML presentations from a codebase — analyses repo, plans narrative, writes slides with branding, code demos, architecture diagrams, and speaker notes. Invoke when user says "create slides", "build a presentation", "generate a deck", "make slides for this tool/project".
mouadja02/skills
Stars: 13Claude CodeCodexAlso use when the user wants to visualize agent workflows, ETL pipelines, dbt lineage, API flows, or system integrations. If the words diagram, chart, flow, architecture, visualize, or draw appear in a visual context — use this skill
mouadja02/skills
Stars: 13Claude CodeCodexAlso use when documenting an AI agent system, a data pipeline, or producing technical reference material for a team. If the output is a technical document other than a README — use this skill
mouadja02/skills
Stars: 13Claude CodeCodexUse when asked to write, generate, update, or improve a README.md, add documentation to a project root, or create an onboarding document for a repository. Also use when the user says "document this project", "write the docs", or "create a README" for a Python tool, FastAPI backend, React app, CLI, dbt project, monorepo, or AI agent system. If the output is a README.md — use this skill.
mouadja02/skills
Stars: 13Claude CodeCodexAsk which skill or flow fits your situation. A router over the skills in this repo.
Jarvvski/jjfx
Stars: 41Claude CodeCodexReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
Jarvvski/jjfx
Stars: 41Claude CodeCodexDiagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
Jarvvski/jjfx
Stars: 41Claude CodeCodexScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
Jarvvski/jjfx
Stars: 41Claude CodeCodexGrill me about specs for the workflows I want to build, within this workspace.
Jarvvski/jjfx
Stars: 41Claude CodeCodexBuild a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
Jarvvski/jjfx
Stars: 41Claude CodeCodexCreate a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe incremental steps.
Jarvvski/jjfx
Stars: 41Claude CodeCodexTest-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
Jarvvski/jjfx
Stars: 41Claude CodeCodex