AI去痕迹改写
20065Skill Claude CodeCodex
A Chinese-language rewriting skill that removes 45 listed signs of AI-generated writing while preserving the original formatting.
not rated 2 4mo ago A 68 tokens
director-pass
20066Skill Claude Code
An agentic, vision-driven final QA/repair pass — a Claude "director" WATCHES the finished short (a contact sheet of frames sampled across the whole clip + the transcript + the sidecar plans) and decides, in natural language, what is broken ANYWHERE (cold open, dead/rambling tail, a tonally-wrong b-roll match, a…
not rated 2 2mo ago A 271 tokens
context-bridge
20067Skill Claude CodeCodex
Cross-session task memory and stagnation detection for Claude Code, backed by a local context-bridge server that auto-starts on session start. Use when hook output tagged [context-bridge] appears, when the user says "checkpoint", "sync context", or "remember this for next session", when a task keeps reappearing…
not rated 2 2mo ago A 89 tokens
original MIT
agent-discussion
20068Skill Claude CodeCodex
Use when Codex needs read-only external feedback for planning, architecture review, code discussion, strategy review, or decision support.
not rated 2 2mo ago A 29 tokens
original Apache-2.0
skill-version-manager
20069Cifferni/skill-version-manager
Skill Claude CodeCodex
Local version management for installed skills. Provides version archiving, history viewing, and rollback capabilities. Use when you need to manage local skill versions, revert changes, or save snapshots of modified skills.
not rated 2 2mo ago A 43 tokens
resume-optimizer-pro
20070AskAboutAI/Resume-enhancer-skills
Skill Claude CodeCodex
Run this skill whenever a user wants to optimize their resume for a specific job. Triggers on: "optimize my resume", "tailor my resume for this job", "ATS check", "rewrite my resume", "match score", "keywords missing from my resume", "help me apply for this role", "is my resume good enough for this job", "resume…
not rated 2 3mo ago A 182 tokens
pr-review
20071Skill Claude Code
Give or respond to PR reviews with structural awareness via mache. Review mode: review-prep diagrams + impact analysis, parallel analysis agents, one consolidated GitHub review. Respond mode: address reviewer comments.
not rated 2
changed 17d ago A 43 tokens
original Apache-2.0
humanize-prose
20072Skill Claude CodeCodex
Revise academic, analytical, or essay prose so it reads as human-authored rather than AI-generated by 2026-era detectors. Use this skill whenever a draft scores high on GPTZero, Turnitin AI, Originality.ai, Copyleaks, Winston AI, or any other AI-detection tool; whenever the user says "this reads too AI," "humanize…
not rated 2 5mo ago A 282 tokens
original MIT
switch-api
20073Skill Claude CodeCodex
A project configuration tool for switching Claude Code between saved API connections or back to a Claude subscription account. An API connection is a service and set of credentials that lets software use a model.
not rated 2 2mo ago A 234 tokens
original MIT
caveman
20074Skill Claude CodeCodex
Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens"…
not rated 2 2mo ago A 102 tokens
copy · 73% MIT
juanjuan-team
20075Skill Claude CodeCodex
A multi-agent workflow in which several software agents work on a complex task in assigned roles, such as planning, architecture, coding, review, and documentation. It also supports different levels of automation and keeps backups and project memories.
not rated 2 1mo ago C 334 tokens
atelier-direction
20076Skill Claude Code
Atelier suite — the art-direction brain. Decide the design direction BEFORE writing any frontend code: which aesthetic, which "world" (production vs award-grade), the concept, the palette mood, type voice, motion budget, layout archetype, and signature moment. Produces a Direction Doc scaled to the task (a one-line…
not rated 2 3mo ago A 257 tokens
grokkable-output
20077conorbronsdon/grokkable-output
Skill Claude CodeCodex
Make agent output efficiently grokkable — replies, reports, status updates, and summaries a human can parse in one pass. Use this skill whenever writing a user-facing report of work done (debugging findings, migration status, audit results, investigation summaries, task completions), whenever asked "what did you…
not rated 2 8d ago A 154 tokens
original MIT
skill-creator
20078Skill Claude CodeCodex
Use this skill when a contributor wants to build, author, scaffold, verify, or submit a new skill to the SELAT skill hub (selat-skills) — e.g. "create a skill", "build a selat skill", "add a skill to the hub", "contribute a skill", "how do I write a manifest.json", "verify my skill", "submit my skill", "wrap an MPP…
not rated 2 today A 133 tokens
original Apache-2.0
herald
20079Skill Claude CodeCodex
Pre-spec ideation consultant. Turns raw material (docs, images, prompts, read-only source code) into a consolidated idea + implementation proposal (feasibility, gap analysis, integration design, risks), separating what the systems do TODAY (cited fact) from the proposal (marked speculative), then hands it off as a…
not rated 2 3mo ago B 225 tokens
original Apache-2.0
system-architecture
20080Skill Claude CodeCodex
Use when understanding module dependencies, function call chains, or the FileSystemPort abstraction layer of the NoteMD Pro pipeline.
not rated 2 4mo ago A 27 tokens
original MIT
structured-memory
20081Skill Claude CodeCodex
Use whenever persistent agent memory is read, written, or has grown past its budget - the first time memory is consulted in a session, whenever something worth remembering appears, and whenever MEMORY.md or a topic file exceeds its size budget. Implements a two-tier structure (slim MEMORY.md index linking memory-.md…
not rated 2 21d ago A 88 tokens
LGPL-3.0
minicode_contributing
20082Skill Claude CodeCodex
Guide for contributing to the minicode-sdk project. Use this skill when the user wants to contribute code, fix bugs, add features, or improve documentation for the minicode-sdk project.
not rated 2 8mo ago A 42 tokens
original MIT
landed
20083stranma/claude-code-python-template
Skill Claude Code
Post-merge lifecycle. Verifies merge CI, optional deployment checks, cleans up branches, and prepares next phase.
not rated 2 5mo ago A 26 tokens
original MIT
plan-insights
20084Skill Claude CodeCodex
You are an expert at analyzing project delivery metrics from GitHub data. You produce actionable reports on milestone progress, delivery pipeline health, and stale work — giving PMs the data they need to make sprint decisions.
not rated 2 6mo ago A 0 tokens
original MIT
xiaohongshu-finance
20085Skill Claude CodeCodex
A writing and chart-making guide for creating finance and investing posts for Xiaohongshu, a Chinese social platform. It covers topics such as stocks, funds, property, gold, crypto, and economic data.
not rated 2 1mo ago A 169 tokens
original MIT
project-setup
20086ZOO-AiiiPM/claude-project-skill
Skill Claude Code
A project setup system for Claude Code that creates and checks shared project documents, rules, notes, and workspace conventions.
not rated 2 4mo ago D 5 tokens
original MIT
project-docs
20087Skill Claude CodeCodex
Software development project documentation management and progress tracking. Use when: (1) Initializing a new software project and need to create all required documentation (MRD, PRD, Technical Plan, Roadmap), (2) Updating project roadmap after completing tasks, (3) Getting a summary of current project progress, (4)…
not rated 2 8mo ago A 97 tokens
original MIT
deep-review
20088Skill Claude Code
Comprehensive code review — architecture + correctness. Scope with args — diff (default), branch, all, path, or IDE selection. Delegates to reviewer agent for large scope.
not rated 2 4d ago A 39 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: