Tooling for running AI coding agents in production workflows.
Skill Claude CodeCodex
Manually trigger a Hermes-style review of the current session to consider memory and skill updates. Use when the user says "review this session", "what should we learn from this", "save what we learned", "improve from this conversation", or "run the review". The same review fires automatically on Stop, this is for…
Skill Claude CodeCodex
Multi-model AI consultation and research using cursor-agent. Supports CONSULTATION (single query to specific model), RESEARCH (parallel multi-agent queries), and DELIBERATION (multi-round debate). Use when user says 'ask gpt', 'ask opus', 'consult gemini', 'do research on', 'deliberate on', or wants second opinions…
Skill Claude CodeCodex
Syncs Claude Code plugins to Cursor skills and commands directories.
Skill Claude CodeCodex
This skill should be used when the user asks to "create a diagram", "draw an architecture diagram", "visualize a flow", "make a system diagram", "generate a D2 diagram", or mentions D2, architecture diagrams, flow diagrams, sequence diagrams, or system visualization.
Skill Claude CodeCodex
Searches past Claude Code sessions stored in /.claude/. Use when user explicitly asks about previous sessions, chat history, or past conversations, such as "what did I work on last 2 weeks?", "search my history for X", "what projects did I touch last month?", or "show my Claude Code history".
Skill Claude CodeCodex
Logo design generation pipeline using Gemini image generation API. Generates diverse prompt variations, calls the API in parallel, reads and evaluates resulting images, scores them against a rubric, and iterates through refinement stages. Use when user says 'design a logo', 'create a logo', 'logo for', 'brand…
Skill Claude CodeCodex
Multi-layer memory system for sessions, daily rollups, and per-project knowledge via /recall, /rollup-day, /note-session commands.
Skill Claude CodeCodex
This skill should be used when the user says "grill me", "grill with docs", "stress-test this plan", "interview me", "interrogate this design", "poke holes in this", "am I missing anything", or wants to align on what to build before building it. Interviews the user one question at a time until every branch of the…
Skill Claude CodeCodex
This skill should be used when the user says "create a PEP", "update PEP", "PEP status", "document this", "spike", "investigate", "explore", "look into", "scout", "research", "scope out", "figure out", or references PEP-.md files. Manages PEP (Project Enhancement Proposal) documents covering both investigation ("I…
Skill Claude CodeCodex
Generate user-impact QA test scenarios from a code change, in the style of a human QA tester probing real failure states. Use this whenever the user wants QA help on a commit, diff, branch, or PR; asks "what should I test here", "what would break", "what would a user hit"; wants to bootstrap or grow a failure-mode…
Skill Claude CodeCodex
This skill should be used when the user asks to "create a skill", "add a skill to a plugin", "add a skill to a repository", "scaffold a skill", "write a new skill", "improve skill description", or needs guidance on skill structure, progressive disclosure, or skill development best practices.
Skill Claude CodeCodex
This skill should be used when the user asks to "clean up tests", "clean up code", "tidy up tests", "remove dead tests", "organize test files", "fix test structure", or mentions test hygiene, test bloat, removing temporary tests, or following test best practices. Unlike the code-review skill (which reviews a diff for…
Skill Claude CodeCodex
This skill should be used when the user says "diagnose this", "debug this", "why is this failing", "this is broken", "track down this bug", or reports something throwing, crashing, returning wrong output, or a performance regression. A disciplined diagnosis loop for hard bugs: build a feedback loop, reproduce…
Skill Claude CodeCodex
Review code comments in a diff and remove or trim AI slop, bloat, and noise, keeping only comments that earn their place. Use when the user says "review the comments", "remove slop comments", "deslop the branch", "trim the comments", "do we need this comment", "we added too many comments", "can we cleanup comments"…
Skill Claude CodeCodex
This skill should be used when the user asks to "refactor this package", "reorganize this code", "split this file", "this code is a mess", "too many files", "simplify this module", "restructure this", or mentions god structs, god components, god classes, package organization, module structure, or code that is hard to…
Skill Claude CodeCodex
Reviews code changes for quality issues. Use when user says "review my changes", "review the diff", "review my code", "check for issues", "sanity check", or asks to find holes, gaps, or simplification opportunities.
Skill Claude CodeCodex
This skill should be used when creating or editing documents, diagrams, handover docs, PEPs, or any substantial written output. Also activates when the user says "evaluate this", "run in a loop until good", "rate this out of 10", "is this 10/10", "loop until fixed", "keep improving", or asks for iterative quality…
Skill Claude CodeCodex
Trim CLAUDE.md and AGENTS.md files to reduce context cost. Apply the "less is more" finding from empirical research on agentic coding context files. Use when user says "trim our context files", "lean up CLAUDE.md", "optimize our agents.md", "reduce context", "our CLAUDE.md is too long", or asks to audit instruction…
Skill Claude CodeCodex
This skill should be used when writing documentation, PR descriptions, handover docs, PEPs, Confluence pages, or any prose output. Activates when the user asks to "write a document", "create a handover", "update the docs", "write a PR description", "draft a PEP", or any task producing written content. Enforces…