openspec-onboard
265Skill Claude CodeCodex
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
not rated 5 5mo ago A 26 tokens
copy · 78% MIT
Skill Claude CodeCodex
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
not rated 5 5mo ago A 32 tokens
copy · 75% MIT
Skill Claude CodeCodex
Integrate lifecycle hooks across AI coding tools (Claude Code, Gemini CLI, Cursor, OpenCode) and any CLI. Use when: (1) installing/removing hooks, (2) creating OpenCode plugins, (3) setting up auto-formatting, testing, notifications, security policies, (4) wrapping CLI tools without hooks API. Triggers on: "add hook"…
not rated 5 6mo ago A 186 tokens
original MIT
gitflow
268Skill Claude CodeCodex
Git Flow branching model - a philosophy for versioned releases, implemented with pure git commands (no tools required).
not rated 5 6mo ago A 25 tokens
original MIT
Skill Claude CodeCodex
A workflow for turning tables in PDF files into Excel workbooks, with one sheet per table and supporting images and quality notes. It uses MinerU, a tool that extracts content from PDFs, and needs an image-reading model to check the results.
not rated 5 21d ago A 132 tokens
original MIT
release-notes
270Skill Claude CodeCodex
Generate GitHub release notes for the demetra repo between two version tags. Use when asked to "create release notes", "write a changelog", "draft a release", or "build release notes" for a tag range such as v1.15.4..v1.16.7.
not rated 7 today A 65 tokens
AGPL-3.0
Skill Claude CodeCodex
Archive old wiki pages (default > 3 months) by extracting any.
not rated 7 today A 19 tokens
AGPL-3.0
Skill Claude CodeCodex
Create or update the wiki page for the current session - every invocation.
not rated 7 today A 20 tokens
AGPL-3.0
bgo
273Skill Claude CodeCodex
Automated Blender build-go workflow. Automatically builds, removes old version, installs, enables, and launches Blender with your extension/add-on. Use when you want to quickly test changes, execute complete build-to-launch cycle, or run custom packaging scripts with automatic Blender launch.
not rated 5 7mo ago A 56 tokens
debate
274Skill Claude CodeCodex
Structured adversarial analysis protocol. Quick single-agent modes (challenge, panel, pre-mortem, red team) plus a decision-review protocol where one agent proposes, one critiques, the proposer revises, and a binding/advisory judge panel decides ADOPT/REVISE/REJECT/ESCALATE.
not rated 5
changed today A 67 tokens
original MIT
patch-tracker
275Skill Claude CodeCodex
Track and verify custom patches to external dependencies. Register, audit, and verify patches survive updates. CRUD lifecycle for patch entries with post-update verification.
not rated 5
changed today A 33 tokens
original MIT
update-to-latest
276Skill Claude CodeCodex
Safety-critical operational pipeline for analyzing and executing OpenCode/OMO updates with explicit approval, patch preservation, rollback capability, and evidence-state discipline.
not rated 5
changed today A 33 tokens
original MIT
marimo-notebook
277adrunkhuman/marimo-opencode-skill
Skill Claude CodeCodex
Author interactive reactive Python notebooks with marimo. Covers interactive cell execution, reactive UI, SQL, state management, deployment, and export. For interactive notebooks, NOT Cell.run() API.
not rated 5 5mo ago A 43 tokens
original MIT
cc-hooks
278Skill Claude CodeCodex
Multi-agent hook system: author hooks once as rulesync-canonical hooks.json (HookDefinitionSchema), deploy via superskill install / superskill hook emit to Claude Code, Codex, OpenCode, Pi (pi-hooks), and Gemini CLI. Covers command, prompt, and http hooks, cross-platform event mapping, and safety invariants.
not rated 5 yesterday A 71 tokens
original Apache-2.0
diffler
279Skill Claude CodeCodex
Generate and deliver a graded comprehension quiz from the current Git branch diff, either in the local terminal or through Google Forms. Use when a user asks to prove, test, or verify understanding of branch changes, a feature branch, or a pull request.
not rated 4 11d ago B 53 tokens
original MIT
bundle-skills
280Skill Claude CodeCodex
Use this skill when the user wants to create, update, or plan a skill bundle CSV for the skillless project, especially prompts like "/bundle-skills frontend", "bundle skills for python", "make a react skill pack", "merge these skills into a list", or "find skills and create a category". This skill guides the agent…
not rated 4 1mo ago A 129 tokens
original MIT
find-skills
281Skill Claude CodeCodex
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
not rated 4 1mo ago A 67 tokens
copy · 81% MIT
fabled
282Skill Claude CodeCodex
Six-phase build discipline that turns one prompt into a complete, runnable deliverable with zero placeholders. Use for ANY non-trivial single-prompt build request — "build me…", "create an app/script/tool/site/game/bot/pipeline that…", "make a complete…", "write a program that…" — and whenever the user says…
not rated 4 1mo ago A 171 tokens
original MIT
llm-council
283Skill Claude CodeCodex
Run a decision through 5 independent AI advisors (Contrarian, First Principles, Expansionist, Outsider, Executor) that peer-review anonymously and synthesize a verdict. Trigger on 'council this', 'pressure-test this', 'war room this', or any high-stakes either/or choice. Skip for factual lookups, summaries, or simple…
not rated 4 10d ago A 85 tokens
markitdown
284Skill Claude CodeCodex
Convert multi-format documents (PDF, DOCX, PPTX, XLSX, images, audio, video, HTML, ZIP) into token-efficient Markdown using Microsoft MarkItDown for LLM ingestion and knowledge graph indexing.
not rated 4 10d ago A 48 tokens
playwright
285Skill Claude CodeCodex
Browser automation, web testing, dynamic scraping, and visual verification using Playwright and agent-browser CLI. Supports DOM snapshots with @eN element references, form interactions, and screenshot validations.
not rated 4 10d ago A 40 tokens
skill-dispatcher
286farhanic017/dynamic-skill-loader
Skill Claude CodeCodex
Universal MCP skill dispatcher for AI coding agents. Loads Claude Code, OpenCode, Cursor, Gemini-style, command, plain markdown, and GitHub-hosted skills on demand. Includes agent routing, active skill lifecycle tracking, external repo import, nested skill discovery, origin filtering, and hardened parsing for secure…
not rated 4 2mo ago A 68 tokens
GPL-3.0
oceanbase-query
287Skill Claude CodeCodex
Guide OpenCode to use OceanBase MCP for metadata-first OceanBase querying, SQL assistance, ER diagrams, metadata change review, and result documentation.
not rated 4 9d ago A 34 tokens
original Apache-2.0
Skill Claude CodeCodex
Create and cancel simple one-shot email follow-up reminders through Pipa. Use this when the user wants Pipa to email them a specific reminder at a future time, such as “email me tomorrow at 9 to follow up,” “remind me by email next Friday,” or “send me a reminder in two hours.” Also use it to cancel a previously…
not rated 3 today A 122 tokens
original MIT
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: