Loading…
Showing 9301–9330 of 10002 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| worktreepappcorn/universeCreate, list, and remove git worktrees so several branches can be open at once without anyone switching a branch out from under anyone else — the default way to work when agents and humans share a repository. Modes: a new branch in its own checkout, an existing PR checked out for review, list, remove, prune. Worktrees land in a sibling directory, each with its own dependencies and its own local config, copied rather than symlinked. Backed by a zero-dep Node script. Use when the user says "worktree", "check out that PR locally", "work on two branches at once", "haz un worktree", "spin up a branch in parallel", or needs the current checkout free without losing what is in it. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| crear-agentepappcorn/universeTe guía para crear TU propio agente: un ayudante de IA con un trabajo claro, que sabe dónde buscar la información y qué no debe hacer nunca. Primero te entrevista y después escribe el agente contigo. En Claude Code crea el archivo del subagente en `.claude/agents/`; en Claude Desktop o claude.ai arma el equivalente (un Proyecto con instrucciones, conocimiento y skills). Úsala cuando digas "quiero crear un agente", "hazme un asistente para X", "necesito un ayudante que se encargue de Y", "configurar mi IA", "make me an agent", "crear un subagente", o pidas mejorar un agente que ya tienes, incluso si describes el trabajo sin decir la palabra agente. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| crear-asistentepappcorn/universeTe guía para crear TU propio asistente personal en Claude Code: un asistente con nombre y tono propios, que conoce tus metas y tu foco, recuerda en una carpeta de notas tuya (estilo segundo cerebro) y delega en especialistas pequeños. Ofrece dos caminos, armarlo con un script o armarlo paso a paso con una entrevista. Úsala cuando digas "quiero mi propio asistente", "crea mi asistente personal", "configura mi Claude para mi vida y mi trabajo", "quiero un segundo cerebro con IA", "ayúdame a organizarme con Claude", "build my own assistant", o cuando pidas conectar tu correo, calendario, Notion u Obsidian a un asistente, aunque no digas la palabra asistente. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| crear-skillpappcorn/universeTe guía para enseñarle a TU Claude una tarea repetitiva, creando una skill propia. Te entrevista sobre la tarea que haces siempre igual, escribe contigo el archivo SKILL.md (con una buena descripción para que Claude la use sola), y te dice cómo instalarla en Claude Desktop (como .zip) o en Claude Code (carpeta .claude/skills/). Úsala cuando digas "quiero crear una skill", "enséñale a Claude a hacer X", "esto lo hago siempre igual y quiero automatizarlo", "cómo hago que Claude recuerde mi formato", "make me a skill", "convierte este proceso en una skill", o cuando describas una tarea que repites cada semana, aunque no digas la palabra skill. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| tribeunaltribeunal/mcp-serverUse when a decision needs more than one opinion — a dispute between two parties, a verdict or ruling someone will act on, a team decision nobody can settle, a poll or a vote, an arbitration clause, an escrow release waiting on who is right, or any question better answered by a jury of people and AI agents than by a single model, even if they never say Tribeunal | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| using-tribeunaltribeunal/mcp-serverUse when a session first reaches for Tribeunal's tools, when a request involves cases, juries, verdicts, tribes or share links and it is unclear which workflow applies, or when a Tribeunal tool call is refused and the reason needs interpreting. Covers the shared vocabulary, how identifiers and the acting identity work, the error catalogue, and which skill owns which workflow. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| mtp-playlistimkohenauser/mtpCreate an MTP music sequence using the Mapping the Prompt (MTP) framework: default 20-track playlist, 10-track Side A/B half, extended multi-cycle sequence, or reduced source-limited mapping. Invoked explicitly to build a structured musical arc from a theme, genre, artist, album, era, scene, or sound world, optionally anchoring specific tracks to named MTP nodes. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| blakean-sceneaugchan42/inkstoneConvert abstract symbolic concepts into Blakean embodied scene prompts — Blake's 8 compositional patterns, body grammar, and figure types. Use when visualizing oracular or symbolic ideas as figures; for ink-painting scenes from verse, see verse-to-prompt instead. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| codex-reviewaugchan42/inkstoneRun an independent code review of any git scope — uncommitted changes, a commit range, a merge commit, a PR, or specific paths — via Codex CLI, opencode, or context-blind subagents, then triage every finding with an explicit disposition. Use when asked to "review this diff", "codex review", "review PR N", "review the merge commit", or to get a second opinion on changes before or after merge. For reviewing implementation plans rather than code, see plan-review-loop. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| critic-loopaugchan42/inkstoneRun an independent critic loop on generated work that is not code or a plan — images, renders, ASCII or canvas art, video stills, frames and shorts, covers, copy. A fresh-context critic scores each round against a rubric written before round 1, starts with a blind read (it says what it sees before it is told what was intended), lists every gap, and the loop stops on a threshold, a stall rule or a round limit. Use when asked to "critic loop", "have a critic score this", "get an independent critic", or before showing generated visuals or copy to the owner as ready. For code, see codex-review; for implementation plans, see plan-review-loop. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| deepen-taskaugchan42/inkstoneReframe a task or rewrite a prompt for greater rigor when asked for a deeper approach, expert methods, or more ambitious use of AI. Identify missing expert work, primary evidence, concrete methods, and independent validation. Use altitude and range only where they improve the user's goal. For reviewing an existing implementation plan, see plan-review-loop; for unclear marketing copy, see marketing-clarity. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| deliver-changeaugchan42/inkstoneUse when asked to deliver a development change using deepen-task and verify-change, including changes with visual deliverables. For verification alone, use verify-change; for standalone code review, use codex-review; for standalone visual criticism, use critic-loop. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| image-to-sceneaugchan42/inkstoneConvert a generated image's original prompt (Yilin ink paintings, Records card plates) into a motion prompt for image-to-video APIs, and run it on Replicate or the QwenCloud Token Plan (HappyHorse 1.1). Use when animating a generated image — requires that original prompt as input; never guess from a description alone. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| verify-changeaugchan42/inkstoneVerify an implemented change by mapping intended behavior to executable checks, running those checks, and handing off concrete evidence and gaps. Use when asked to verify agent-generated code, prove a change works, or prepare a verification handoff when code volume exceeds human reading capacity. This is implementation verification; use codex-review for an adversarial Codex review of Opus-generated code. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| verse-to-promptaugchan42/inkstoneConvert classical Chinese verses into image generation prompts — ink painting (default), stipple, or tech-noir variant. Use when visualizing Yilin, I Ching, Tang poetry, or classical Chinese text; for video motion prompts, see image-to-scene. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| voice-calibrationaugchan42/inkstoneInteractive voice profiling — asks writing prompts in terminal, collects live responses, and distills a reusable voice profile for content generation. Use when calibrating tone for social posts, newsletters, or any written output. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| horse-raceqiao/horse-raceCompetitive multi-agent problem solving: spawns multiple Claude Code sub-agents in parallel git worktrees to independently solve the same programming task, then cross-pollinates their solutions through improvement rounds where each agent sees and learns from all others' diffs, and finally selects the best solution through Borda count consensus voting with independent judges. Use this skill whenever the user says 'horse race', 'race', 'compete', 'multi-agent', wants to compare multiple approaches to a problem, or wants higher-quality solutions through competitive iteration. Also triggers when users want parallel implementations, solution tournaments, or A/B comparisons of code approaches. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| play-fishing-frenzyunchartedgg/play-fishing-frenzyPlay Fishing Frenzy autonomously — an AI agent that fishes, cooks, dives, completes quests, and optimizes your economy. Built on Ronin blockchain with full wallet, NFT, and token integration. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| deep-researchmayrsascha/deep-research-skillGenerate a structured Deep Research prompt and copy it to clipboard. Use when complex analysis or extensive research is needed — the user then pastes into their preferred deep research tool (Gemini, Perplexity, ChatGPT, etc.). | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| skill-creatorjavalenciacai/QASkillsGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| user-story-static-verifierjavalenciacai/QASkillsSkill for static verification and analysis of user stories in agile development, ensuring they meet best practices like INVEST criteria and detecting common defects (ambiguity, omission, inconsistency, inaccuracy, non-testability, scope creep). | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| memorySomeStay07/claude-memory-skillUnified project memory management: update, prune, reflect, and maintain knowledge. Combines conversation scanning, deduplication, contradiction detection, confidence scoring, and consistency checks in a single skill. Usage: /memory update [topic] — scan conversation, persist learnings /memory prune [type] — find duplicates, contradictions, stale entries /memory reflect — focused correction capture from conversation /memory status — show memory layout, sizes, health Triggers: "/memory", "update memory", "clean memory", "remember this", "memory update", "memory prune", "memory status" | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| arxiv-paper-searchtopprismdata/cultivating-ml-agentUse when encountering a new ML technique not covered by existing 43+ skills, when needing citations for a paper/report, when comparing recent (last 6 months) approaches to a known problem, or when the existing knowledge feels stale. Triggers on phrases like "latest paper on X", "SOTA in Y", "what does the literature say about Z". | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| autogluon-preset-strategytopprismdata/cultivating-ml-agentAutoGluon preset selection strategy: when to use medium/good/high/best_quality, when EDA is unnecessary, and how to tune within a preset. Validated on s6e7 (AG high_quality 600s → OOF=0.8739, LB=0.87458, gap=0.0007 — perfect alignment). Use when: (1) Deciding which AutoGluon preset to start with, (2) Wondering whether to do manual EDA before fitting, (3) Wanting to know which hyperparameters to tune first, (4) Deciding time budget for tabular training. Differs from `autogluon-first` (which says "just use best_quality"): this skill explains the preset tradeoffs and where manual intervention pays off vs not. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| claudeceptiontopprismdata/cultivating-ml-agentExtract reusable knowledge from work sessions into new Claude Code skills. Use when: (1) /claudeception command to review session, (2) "save this as a skill" or "extract a skill", (3) "what did we learn?", (4) After non-obvious debugging, workarounds, trial-and-error discovery, or counterintuitive solutions. Do NOT trigger for routine fixes or straightforward tasks with obvious solutions. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| context-engineeringtopprismdata/cultivating-ml-agentUse when context window is getting crowded, when dealing with long training logs, or when preparing prompts with mixed-priority content (system / task / skills / examples). Triggers when assembling prompts >4000 chars, or when observing "Lost in the Middle" symptoms (model ignores mid-prompt content). | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| kaggle-cognitive-cost-optimizationtopprismdata/cultivating-ml-agentUse when: (1) You have limited daily submission quota and 50+ skill files to explore, (2) Most Kaggle experiments cost 1 quota each but only the 1-2 BEST actually matter for your final score, (3) You waste hours doing redundant experiments because the EXISTING public kernels (rank 4-9 players) have already solved 80% of the problem, (4) You're tempted to re-submit "to see what happens". Key insight from 4+ months, 20+ competitions: **0.6 × BEST_PUBLIC ≥ 0.8 × OPTIMAL_OWN**, i.e. the best public kernel + small tuning > optimal own work in 90% of cases. Most Kaggle competition success comes from picking the right public kernel and spending quota wisely, not from complex custom work. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| knowledge-crystallization-feedback-looptopprismdata/cultivating-ml-agentUse when: (1) You've completed a competition or experiment and want to extract reusable knowledge, (2) Your agent keeps repeating the same mistakes across competitions because lessons weren't crystallized, (3) You have 50+ memory files but can't find relevant knowledge when starting a new task, (4) You need to decide what to remember vs what to forget. Covers the complete crystallization cycle: Experiment → Identify Outcome → Extract Pattern → Classify (feedback/ learned/project/reference) → Store with triggers → Activate on match. Includes the "3-layer architecture" (L1 core, L2 domain skills, L3 cross-domain principles) and the "forgetting protocol" for stale knowledge. Validated across 4+ months, 20+ competitions, 109+ crystallized memories. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| mem0-dynamic-graph-memorytopprismdata/cultivating-ml-agentUse when extracting entities and relationships from text, when building dynamic knowledge graphs, when wanting to upgrade from static OKF to entity-aware memory, or when analyzing papers/discussions for concepts. Triggers when ingesting new papers, processing Kaggle writeups, or when existing skills can't capture connections between concepts. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| memory-hierarchy-managementtopprismdata/cultivating-ml-agentUse when context window is getting crowded, when agent needs to recall past experiences, or when starting a long-running task that spans multiple sessions. Triggers when you have 43+ skills and can't fit them all in context, when you need to decide "what should be in working memory right now", or when persisting new learnings for future sessions. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |