Loading…
Showing 9991–10020 of 10056 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| suno-v6-songwriterMJorgin/suno-v6-cookbookCreate evidence-labeled Suno v6 songs, local lyric edits, source-based workflows, and safe multimodal prompts without automation or credentials. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| image-skillbookAlbertAZ1992/image-skillbookCompare Image Skillbook treatments and route an image request to the most suitable installed style Skill. Use when the user wants help choosing an AI photo treatment, wants several styles compared, or names Image Skillbook without choosing a style. Do not use for ordinary image conversion or when a specific style Skill is already named. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| maintain-llm-wikiGodModeAI2025/SkillSafeWerkstattCreate, maintain, inventory, migrate, recover, quality-review, optionally clean, release, or export an evidence-linked SkillSafeWerkstatt Markdown wiki. Use whenever the user wants to initialize or extend this wiki, ingest documents as Markdown, curate claims, clusters or concepts, clean metadata, restore files, record who reviewed which pages, resolve a OneDrive or SharePoint conflict copy, publish a release, or export a frozen read-only knowledge skill or an Open Knowledge Format bundle in Claude Code, Claude Cowork, or Codex. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| query-llm-wikiGodModeAI2025/SkillSafeWerkstattSearch, filter, inventory, and answer from a verified SkillSafeWerkstatt release with claim-level source locators and read-only quality assessment. Use whenever the user asks about this wiki, requests original sources or citations, compares current and historical claims, filters metadata, inspects schema drift, or checks wiki quality without modifying it in Claude Code, Claude Cowork, or Codex. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| diagram-makerbestdeejay-design/agent-skillsГенерация диаграмм из текстового описания: flowchart, sequence, architecture, ER-схемы, bar, line, pie, scatter в синтаксисе Mermaid или HTML (Chart.js). Вход — natural language описание, выход — готовый код Mermaid + рекомендация по рендерингу (mermaid.live / mermaid-cli / MCP) или интерактивный HTML-график. Триггеры: 'диаграмма', 'diagram', 'mermaid', 'flowchart', 'блок-схема', 'sequence diagram', 'архитектура', 'ER-схема', 'нарисуй схему', 'draw a diagram', 'схема', 'architecture diagram', 'bar chart', 'line chart', 'pie chart', 'scatter plot'. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| plan-skillbestdeejay-design/agent-skills | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| skill-feedbackbestdeejay-design/agent-skillsCapture and aggregate real-world usage feedback for Agent Skills so the Skill Quality Gate loop can keep improving them over time. Use it whenever a skill misfires or underperforms: a skill triggered wrongly (wrong trigger), failed to auto-load on a relevant request (near-miss / description gap), produced a wrong, broken, or low-quality output (output issue), or the user manually corrected its result (manual correction). Also use it to review accumulated skill feedback before running skill-forge, or to close the feedback loop that raises skill quality. Writes one structured JSON object per line to feedback/<skill>/YYYY-MM-DD.jsonl and can summarize them into a report/export that feeds skill-forge's Optimize-description step. Trigger phrases: 'skill feedback', 'log skill feedback', 'skill triggered wrongly', 'near-miss trigger', 'wrong trigger', 'output issue', 'manual correction', 'improve skill', 'skill quality', 'feedback loop'. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| skill-suggesterbestdeejay-design/agent-skillsSkill recommendation for AI agents from the agent-skills library. Reads the master catalog index.json (default ~/Projects/agent-skills/index.json, override with env AGENT_SKILLS_INDEX or --index), scores triggers and descriptions, returns top-5 with relevance plus up to 3 combos for multi-step tasks. Supports ad-hoc apply: prints SKILL.md paths so the agent can read and apply a skill's instructions directly even if it is not installed. Triggers: 'какой скилл использовать', 'skill suggestion', 'suggest skill', 'рекомендовать скилл', 'recommend a skill', 'which skill', 'подобрать навык'. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| stelejohnwangwyx/steleDurable project and task state kept as plain markdown in the repository - a PROJECT_CONTEXT.md of standing facts, a generated TASKS.md census, and one file per task holding its goal, current state, failed attempts and steps. Every step is written before the work it describes rather than at session exit, so a session killed by a rate limit or a crash still leaves the next agent — in any harness — enough to carry on. Invoke only when stele is named — the user asks to manage(init) a project with it, asks to resume or continue where it left off, or a project instruction file points at a stele/ directory and tells you to load this skill. Otherwise do not invoke. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| setup-agency-skillsJehudaRajasa/skillsConfigure `.agents/config.yml` — the tracker and workflow states the other agency skills read. Run once per project, before the rest. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| normalizextieume/testcaseRewrites a casual, rambling everyday prompt into a compact engineering prompt — structured sections, imperative instructions, explicit escalation and done criteria — ready to paste into an AI or in front of a slash command like /goalrun. Use when the user says "chuẩn hóa prompt", "viết lại prompt này", "làm prompt cho gọn", "prompt này dài quá", "rewrite this prompt", "turn this into a proper prompt", "clean up my prompt", "make this a technical prompt", "prompt for /goalrun", or pastes a long informal instruction and asks for a version to send to an AI. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| self-improveThis-HW/hiway-kitPropose improvements to agent/skill/rule definitions from accumulated feedback-ledger defects and eval reports. Proposal-only - applies changes exclusively after evals show no regression AND the user approves. Trigger with /self-improve. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| agent-creatorThis-HW/hiway-kitCreate a Claude Code sub-agent definition for this project or user. Use when the user asks to create a new custom agent or a specialized sub-agent for a recurring task. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| cross-engine-reviewThis-HW/hiway-kitReach an evidence-backed decision between sessions running on different agent engines. Use when a call is high-stakes enough that one engine's blind spots are a real risk, and a second session with different tool access can bring evidence the first cannot. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| harness-exportThis-HW/hiway-kitExport the kit's host-neutral rules to every harness entrypoint file (AGENTS.md, GEMINI.md) so non-Claude-Code harnesses (Codex, OpenCode, Copilot, Gemini CLI, Pi, Hermes) follow the same discipline. Use when a repo is worked by more than one agent harness, or after changing rules/. Trigger with /harness-export. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| session-historyThis-HW/hiway-kitSearch explicitly selected local Codex or Claude JSONL session logs to recover past work with source file and line evidence. Use when the user asks about earlier coding sessions or decisions. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| skill-forgeThis-HW/hiway-kitDistill a hard problem you just solved into a reusable skill draft - proposal-only, behind a three-condition threshold. Use after finishing a non-trivial task whose procedure would otherwise die with the session. Trigger with /skill-forge. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| using-hiway-kitThis-HW/hiway-kitSession-start meta-skill (hook-injected). Kit workflow chain and plan file rules. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| dual-readccai40359-wq/multiagents-workflowDual-channel document reading — the main agent reads, one subagent per file reads independently, then cross-compare (match/addition/conflict). MUST USE for close reading, analysis, or fact extraction from documents/PDFs/contracts/manuals/reports/long files — triggers include "read carefully", "don't miss anything", "cross-check", "用子agent读", "双读". Essential when extracting key facts (numbers, limits, clauses, rules). Not for browsing a table of contents, reading a code diff, or merely confirming a file exists. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| job-search-planficilcom/otame4-work-skillsLay out how a job search will actually run alongside a current job: the hours available each week and what they go to, how weekday daytime slots for interviews will be found, which routes to use (direct applications, job boards, scout sites, agents, referrals, public employment services) and what each one discloses to whom, how to keep the search from reaching the current employer through public profiles or workplace equipment, a single tracker of every application's stage, next action, and deadline, and a date and conditions for reviewing, reducing, or pausing the search. Use when someone has decided to start looking, or to gather information while employed, and asks how to fit it in, which routes to use, whether the applications they are running fit the time they have, or how to keep track of them; do not use to decide whether to change jobs, to pick or rate employers or job postings, to predict outcomes, or to send applications, publish profiles, or contact agents on the user's behalf. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| resume-draftficilcom/otame4-work-skillsAssemble a Japanese shokumu-keirekisho (career history document) from an experience inventory, choosing between reverse-chronological, chronological, and skills-based layouts, mapping the target posting's requirements to the experiences that can support them, and drafting the summary, work history, skills, and self-PR so that each sentence stays within what its evidence supports and confidential details are abstracted. Use when a user wants to write or rebuild a whole shokumu-keirekisho for a specific posting or as a general version, or wants to decide which experiences to include and in what order; do not use to invent experience, numbers, titles, or qualifications, to predict whether it will pass screening, to fill in a rirekisho form, or to submit it anywhere. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| offer-declineficilcom/otame4-work-skillsWork out the order and the loose ends before turning down an offer or withdrawing from a selection process: whether the offer being kept is actually settled in writing, whether each decline is mid-selection, post-offer, or after acceptance, who besides the employer has to be told when the application came through an agent, a school recommendation, or a referral, which reply deadlines have passed, and what documents, expenses, or borrowed items are still outstanding. Use when a user holds more than one offer and needs to decline the rest, wants to withdraw from a process they are no longer pursuing, or has been asked to turn down other employers as a condition; do not use to decide whether to decline, to rule on what declining after acceptance means legally, or to send any message. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| scout-message-triageficilcom/otame4-work-skillsSort incoming scout messages and agent-forwarded openings by what they actually disclose: whether the employer is named at all, which of pay, location, employment type, and duties are stated, whether the message refers to the applicant's own history or reads as a mass send, whether a stated salary is an offer or a "up to" figure, and whether the same employer has arrived through more than one route. Use when a user has a backlog of scout messages and wants to know which ones can be researched, what to ask before replying, and what to settle before handing over a resume; do not use to rate how promising an opening is, to judge an employer or an agent, or to reply on the user's behalf. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| ghidra-iterative-reGeReV/ghidra-iterative-reUse when reverse-engineering a game (or any binary) in Ghidra via MCP or PyGhidra - establishes the apply-cascade-verify loop, the SourceType trust model that stops an agent corroborating its own guesses, invariant bracketing against Ghidra's silent collateral damage, and the game-specific evidence sources worth sweeping before any analysis. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| de-kansverkennererwinblom/open-ai-skills-nlVerken vóór er één concreet concept is kansen voor nieuwe producten, diensten, proposities en procesinnovaties vanuit een sector, doelgroep, probleem, trend, technologie, verandering of bronnenverzameling. Gebruik deze skill voor opportunity discovery, innovatiescans, white-space-analyse en het vertalen van signalen naar enkele testbare businesskansen. Gebruik hem niet om bestaande pilotresultaten te beoordelen, synthetische klantreacties te maken of een product daadwerkelijk te bouwen; stuur gekozen kansen daarvoor door naar de passende vervolgstap. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| de-klantverkennererwinblom/open-ai-skills-nlAdviseer een bruikbare voorlopige richting voor een product- of dienstidee met virtuele klantperspectieven. Verken mogelijke klantsegmenten, gebruikssituaties, alternatieven, bezwaren, positionering, prijs, invoering en testprioriteiten. Gebruik deze skill voor een snelle scan of diepgaande scenarioverkenning en ontwerp een echte vervolgtest. Houd aangeleverde feiten, scenario-aannames en virtuele richtingssignalen zichtbaar apart; claim geen waargenomen klantgedrag, marktvalidatie of betalingsbereidheid vanuit simulatie. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| image-genbehzadsp/claude-code-image-genGenerate images from text prompts through OpenAI (gpt-image-2.5), Google Gemini (gemini-3-pro-image), Higgsfield, Black Forest Labs FLUX, or any OpenAI-compatible endpoint such as xAI Grok or Recraft. Use when the user asks to generate, create, render, or make an image, hero image, illustration, logo concept, OG image, poster, thumbnail, or social card, when a project has placeholder images to replace, or when the user names an image model or asks which image providers are available. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| create-research-experiment-repoShiba-hua/create-research-experiment-repo为委托实验执行者开展工作的科研负责人,对齐报告、图表、目录和审批职责,获批后构建可追溯的实验管理仓库。适用于 Coding Agent、人类实验员或实验设备团队;不代替具体学科的实验设计与安全规程。 | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| sunyuchen-skillkangarooking/sunyuchen-skill当用户明确要求模仿 sunyuchen、这篇《我的女友景甜》样本或同类“数字冷开场、后勤细节、短对话、情绪留白、物件回环”风格写作时调用;也用于把故事、人物稿、产品案例、创业复盘、告别文或长社交帖改成克制而有叙事张力的版本。 可处理整篇创作、素材改写,也可只修开场、场景细节、转折、节奏或结尾。 不适用于单纯总结、普通文案润色、需要严格中性表达的事实报道;不得编造现实人物私生活、违法行为、医疗、生育或金钱往来。 Triggers: sunyuchen/小作文/冷叙事/数字反差/后勤细节/留白/回环/仿写/style imitation/cold narrative/callback | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| human-maintainabilityhmr-BH/HMAPAssess a programming project's HUMAN maintainability (HMAP): 0-100 score, nine-tier verdict, per-dimension scores, and file:line evidence — built to catch vibe-coding / AI-generated slop, including semantic incoherence (name/contract/concept/vocabulary drift). Triggers: assess maintainability / rate this project / code quality score / readability score / AI slop detection / vibe coding check / semantic consistency check / HMAP / human maintainability / 评估项目可维护性 / 给项目打分 / 代码质量评估 / 可读性评分 / AI屎山检测 / vibe coding 体检 / 是否适合人类维护 / 语义一致性. Anti-trigger: the user asks to fix, refactor, optimize, or write code — that is a different task; this skill only assesses, never modifies. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |