Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 272,428 indexed, measured the same four ways as everything else here.
Repairs a scratchboard kanban board that reads a repo's markdown tickets wrong, and names the field an agent writes to move a card. Use when tickets are missing from the board, when the board shows them in the wrong lanes or in Unmapped, when scratchboard reports it cannot read a ticket format, or when writing a…
Use when working against a test suite, spec, or graded harness you do not own - especially inside an automated loop scored on how many tests pass - and tempted to change the tests, weaken assertions, hardcode expected outputs, special-case inputs, or overfit the visible examples to turn things green.
Use when helping a user lightly replicate and learn from an empirical economics, management, finance, or accounting paper from public paper materials, create a clean replication project structure, extract variables/data/models, draft basic Stata replication steps, explain code and tables, record reproducible outputs…
Guide Claude through a structured application security audit covering threat modeling, testing, pipeline review, dependency risk, and vulnerability management.
Generate a polished frontend reference screenshot through a configurable GPT-image-2-compatible generations endpoint, save and show versioned previews inside the project, revise selected previews through a configurable /images/edits endpoint, and reproduce only the user-approved design as functional frontend code with…
A set of instructions for researching investment opportunities using bottleneck theory. The method looks for lower-level suppliers that larger technology companies cannot easily replace.
Generate a "building in public" update from recent Linear activity and freeform notes. Use when the user wants to share what they've shipped, write a dev update, post about recent work, or draft a "here's what we built" post. Triggers on "farm-stand", "what did I ship", "write an update", "building in public", "what…
Unified observability gateway for AI agents — Prometheus, Loki & more, with anomaly detection. Runs locally from the @thotischner/observability-mcp npm package. Needs 3 environment variables to run.
★not rated 6 4d agoA
tokens not measured
originalApache-2.0
Complete Zillow property data toolkit via the zillapi API. Looks up any US property by address, zillow.com URL or zpid and returns price, Zestimate, rent Zestimate, photos, schools, taxes, price history and listing agent contact; also searches for sale, for rent and sold listings by location and filters. Use when the…
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to $TMPDIR (or /tmp). Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser…
A structured way to guide an AI through difficult problems one step at a time, while keeping the problem bounded and allowing earlier judgments to change.
A Russian-language checkpoint and session-closing procedure that records the verified state of ongoing work in a HANDOFF file. A HANDOFF file is a written task record containing what is done, what remains, blockers, statuses, and journal entries.
Locate clarity gaps, business-model breaks, fundraising-story gaps, pitch-deck blockers, and likely investor questions in idea-stage through Series A startups. Use for founder-side review of a startup idea, pitch deck, fundraising material, VC-lens request, investor-meeting preparation, or funding-path fit. Review…
A 5-stage escalation framework for legitimate account holders whose recovery has failed through standard platform support — covering platform legal channels, state Attorneys General, the FTC, congressional offices, and attorney engagement. Use this skill when a user describes losing access to a social media or…
Provide a standalone Simplified Chinese Windows app and CLI workflows to assess C: drive health, clean a fixed allowlist of regenerable junk, find large user files, detect exact duplicates with SHA-256, and relocate or recycle explicitly approved ordinary user files without breaking Windows or installed applications.…
Use this skill when the user wants to share, install, inspect, publish, claim, or troubleshoot agent skills with Skilo links, refs, bundles, or tool-native skill directories.
A tool for creating Japanese-language PDF documents with embedded Japanese fonts, vertical writing, business templates, and inkan images. An inkan is a Japanese personal or company seal.
Drive the Resonate server from the shell — start a server (serve / dev), create/resolve/search Durable Promises, create and delete cron schedules, manually invoke a function via invoke, walk a call-graph with tree, and inspect or recover tasks (tasks). Reach for this when the agent needs to poke a running Resonate…
Use when preparing a clean 15-20 min academic talk (journal club, group meeting, seminar, conference talk) from 1-2 source papers, with LaTeX Beamer slides that prioritize white space, sparse text, readable figures, and defensible source attribution. Also use when incorporating recorded talks, videos with captions…
GCC (Saudi Arabia, UAE, Qatar, Bahrain, Kuwait, Oman) market entry intelligence for non-GCC founders of operating or scaling B2B / B2G startups. Use this skill whenever the user mentions Saudi Arabia, KSA, UAE, Dubai, Abu Dhabi, Sharjah, Doha, Qatar, Bahrain, Manama, Kuwait, Oman, Muscat, MENA, GCC, Gulf, Khaleej…
★not rated 6 4mo agoA341 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: