Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
46,100 skills from 2,198 repositories · updated 4 hours ago
9,541 skills
- timeline-creatormhattingpete/claude-skills-marketplaceCreate HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.OtherNo warnings★ 689↓ —
- blender-materialsCheshireJCat/blenderCreate and assign PBR materials in Blender via Principled BSDF — metals, glass, plastic, fabric, skin, organics. Covers physically-based material recipes with real-world values, Coat layer (varnish/car paint), Sheen (cloth), Subsurface scattering (skin/wax), Transmission (glass), and procedural patterns (wood grain, marble, fabric weave). Use whenever the user asks to "make it look like X material", "give it a metallic finish", "apply a wood texture", "make this glass / plastic / brushed steel / leather / skin", or any look-development request. Make sure to use this skill even if the user does not say "material" — also covers "make it shiny", "matte finish", "looks like copper", "rough surface". Works with any geometry; pairs with blender-lighting (materials only look right under proper lighting).OtherNo warnings★ 63↓ —
- chronology-builder-andrew-birdlawve-ai/awesome-legal-skillsBuilds a litigation chronology from the disclosure bundle itself — every entry attributed to its source document, behind a CPR 31.22 implied-undertaking check, because documents disclosed in English proceedings may only be used for those proceedings. Adds a privilege screen and case-theory significance tagging, so the output is court-facing work product, not a loose timeline. Use when the user asks to build a chronology or timeline from a disclosure bundle, a matter file, or witness statements, or says 'build the chron', 'what happened when', or needs a Statement of Facts ready timeline.OtherNo warnings★ 911↓ —
- strategy-sessionTserenTserenov/FMT-exocortex-templateСтратегическая сессия — диспетчер. День-0 (маркер IWE-INITIAL-NEEDED или нет Strategy.md/WeekPlan) → initial flow (цели, неудовлетворённости, первый WeekPlan). Первая сессия календарного месяца или прямая просьба пилота о полной сессии → полный monthly flow (стратегическая сверка + линза калибра). Остальные дни → короткий weekly flow (требует черновик от session-prep). Триггеры — «проведём стратегическую сессию», «первая стратегическая сессия», «strategy session», «давай стратегировать».OtherNo warnings★ 63↓ —
- Huntress EscalationsWYRE-AI/msp-claude-pluginsHuntress SOC escalations: how an escalation differs from an incident, escalation priority levels, the list/get/resolve tools, escalation-to-incident correlation, and the already-resolved and not-found error cases.OtherNo warnings★ 52↓ —
- rwd-cohort-analysisawslabs/hcls-agent-skillsReal-world data cohort analysis pipeline for claims and EHR data — cohort identification with ICD-10, NDC, and CPT codes, medication adherence metrics (PDC/MPR), propensity score estimation and balance diagnostics, Kaplan-Meier survival curves, and Cox proportional hazards models. Use when the user mentions claims data, cohort identification, ICD-10 codes, NDC codes, CPT codes, medication adherence, PDC, MPR, propensity score, SMD balance, Kaplan-Meier, Cox model, Schoenfeld residuals, survival analysis on claims, or real-world evidence pipeline.OtherNo warnings★ 68↓ —
- scenario-godot-gameplayUpdatedscenario-labs/skillsUse when building gameplay systems in Godot 4.7: enemy AI that patrols, chases and attacks, state machines, behavior trees (LimboAI), NavigationAgent3D pathfinding and avoidance for 100 to 1000 enemies, 'agents stack up' or 'path is empty', hitbox and hurtbox combat, fast bullets going through walls, save and load, inventory, quests, dialogue (Dialogue Manager), input remapping, procedural dungeons, or measuring agent counts and frame time headless.OtherNo warnings★ 1.2K↓ —
- discovery-sessionTserenTserenov/FMT-exocortex-templateРазговор-распаковка неудовлетворённостей (discovery-стратегирование). Сократический разбор сырой рефлексии и заметок на триаду Проблема/Неудовлетворённость/Эмоция → состояние пилота → приоритеты месяца (WHAT/WHY). Роль R1 Стратег, метод DP.METHOD.053. Триггеры — «разбери неудовлетворённости», «помоги со стратегией месяца», «что для меня сейчас важно», «/discovery-session».OtherNo warnings★ 63↓ —
- ev-vs-gasmohitagw15856/pm-claude-skillsCompare an EV against a comparable gas car on total cost — upfront gap after incentives, energy vs fuel per year, maintenance delta, and the crossover year when the EV pulls ahead (or doesn't). Use when asked is an EV worth it, EV vs gas total cost, when does an EV pay for itself, or should my next car be electric. Produces the year-by-year cumulative comparison from the script, the crossover year, the per-mile energy math, and the honest not-modeled list.OtherNo warnings★ 1.5K↓ —
- motherduck-share-datamotherduckdb/agent-skillsCreate, consume, or manage MotherDuck data shares, including audience grants, table filters, and refresh policy.OtherNo warnings★ 62↓ —Also in 1 other repo
- vdvTserenTserenov/FMT-exocortex-templateВДВ-скилл — генератор и аудитор описания стадийного процесса по 6 принципам Вход·Действие·Выход. Используй для построения описания нового процесса (/vdv build) или проверки готового описания (/vdv audit).OtherNo warnings★ 63↓ —
- motherduck-manage-guidesmotherduckdb/agent-skillsRead or maintain MotherDuck Guides for business definitions, join rules, and reusable warehouse conventions.OtherNo warnings★ 62↓ —
- ConnectWise Automate MonitorsWYRE-AI/msp-claude-pluginsConnectWise Automate monitor management: monitor types (internal, remote, agent, SNMP, script), categories, threshold configuration, templates, assignment methods (computer/group/client), and status evaluation.OtherNo warnings★ 52↓ —
- motherduck-share-datamotherduckdb/agent-skillsCreate, consume, or manage MotherDuck data shares, including audience grants, table filters, and refresh policy.OtherNo warnings★ 62↓ —
- scenario-blender-hairUpdatedscenario-labs/skillsUse when grooming hair or fur in Blender with hair curves, such as a character hairstyle, animal fur, procedural fur in geometry nodes, or hair cards and mesh hair for games. Also covers the Essentials hair node assets (Interpolate, Clump, Curl, Frizz, Noise, Trim), density masks, bald spots, parting lines, strand shading in Cycles or EEVEE, and slow grooms. Use it too when a hair script misbehaves headless, for example stale modifier inputs or curve sculpt brushes that do nothing.OtherNo warnings★ 1.2K↓ —
- motherduck-exploremotherduckdb/agent-skillsFind and understand MotherDuck databases, tables, columns, shares, and sample data, including which tables hold a given kind of data. Use first when a MotherDuck workspace or schema is unfamiliar.OtherNo warnings★ 62↓ —
- motherduck-connectmotherduckdb/agent-skillsSet up or troubleshoot MotherDuck connections, the MotherDuck MCP server in AI clients, authentication, client runtimes, and read scaling.OtherNo warnings★ 62↓ —
- motherduck-manage-guidesmotherduckdb/agent-skillsRead or maintain MotherDuck Guides for business definitions, join rules, and reusable warehouse conventions.OtherNo warnings★ 62↓ —Also in 1 other repo
- mentor-participant-briefNewTserenTserenov/FMT-exocortex-templateПомощник наставника МИМ: по имени, нику или пересланному сообщению участника находит его среди потоков, доступных этому наставнику, собирает одну сводку по обязательному шаблону (переписка, заметки, ступень, квалификация, активность, чек-лист, баллы — у каждого поля источник и дата или причина отсутствия), предлагает черновик ответа и после подтверждения фактической отправки сохраняет текст заметкой. Используй, когда наставник или админ МИМ пишет о конкретном участнике практикума или консультации: «помоги ответить ученику…», «что известно о …», «подготовь ответ участнику», пересылает сообщение участника.OtherNo warnings★ 63↓ —
- Hermes Tweetagentskillexchange/skillsUse Hermes Tweet when Hermes Agent needs a native X/Twitter plugin for reading posts, exploring public data, and running explicitly gated tweet actions through Xquik.OtherNo warnings★ 58↓ —
- beat-hintermann-taa-perspectiveswaylq/master-skillBeat Hintermann (Kantonsspital Baselland, Switzerland) 视角. 踝关节置换 (TAA) HINTEGRA 假体设计师 + 20 年长期 follow-up 数据 + Patient selection 派. 调用此 skill 时, 用 Hintermann 框架做终末期踝关节炎 / 置换 vs 融合 / 长期 follow-up 决策.OtherNo warnings★ 174↓ —Also in 1 other repo
- motherduck-ducklakemotherduckdb/agent-skillsDecide whether DuckLake fits a MotherDuck workload and operate it safely. Use whenever DuckLake, open table formats, or customer-owned buckets come up.OtherNo warnings★ 62↓ —Also in 1 other repo
- motherduck-load-datamotherduckdb/agent-skillsLoad files, object storage, dataframes, or external databases into MotherDuck with bulk ingestion. Use for any import of data into MotherDuck.OtherNo warnings★ 62↓ —Also in 1 other repo
- Warranty TrackingWYRE-AI/msp-claude-pluginsEndpoint hardware warranty status across whatever RMM platforms (Datto RMM, NinjaOne, N-central, Kaseya VSA, ConnectWise Automate, Atera, SuperOps, Syncro, Action1, ImmyBot) and documentation tools (IT Glue, Hudu) are connected: the reliability spread between OEM-resolved and hand-entered warranty fields, serial/asset-tag cross-referencing when RMM data is missing or stale, and the expired / expiring-soon / covered / unknown bucketing.OtherNo warnings★ 52↓ —
validate
hashgraph-online/awesome-codex-plugins
OtherUpdated 17 hours ago
From the author
Freshly judge whether a finished change and its claims meet original acceptance: PASS, FAIL or NOT_PROVEN. Use when: asked for a go/no-go, sign-off or independent verdict.
Install
npx skills add hashgraph-online/awesome-codex-plugins --skill validate -a claude-code
Installs to .claude/skills/validate/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Runs bundled scriptsNo network use seenLicence: APACHE-2.0
Safety checks on SKILL.md
- Ships scripts we have not reviewedLow
Why 82
Security85
Provenance78
Maintenance100
Licence100
Adoption51
Files (8)
- SKILL.md
- references/mechanics.md
- references/validate.feature
- tests/check_contract_corpus.py
- tests/test_evidence_cli.py
- tests/test_validate.py
- tests/validate.py
- tests/validate.sh