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 3 hours ago
9,541 skills
- file-operationsmhattingpete/claude-skills-marketplaceAnalyze files and get detailed metadata including size, line counts, modification times, and content statistics. Use when users request file information, statistics, or analysis without modifying files.OtherNo warnings★ 689↓ —
- Blumira FindingsWYRE-AI/msp-claude-pluginsThe Blumira finding lifecycle: status and severity codes, resolution types, list filtering, enriched detail retrieval, assignment, and comment threads.OtherNo warnings★ 52↓ —
- HubSpot ContactsWYRE-AI/msp-claude-pluginsHubSpot contact records: core and MSP-relevant custom fields, lifecycle stages, lead status values, contact ownership, CRM search filter patterns, and associations to companies and deals.OtherNo warnings★ 52↓ —
- lov-fact-checklovstudio/skills用真人尽调思路校验用户提出的事实命题：拆解可验证问题、检索一手资料、 交叉验证证据链，并给出带置信度和不确定边界的结论。 Trigger when the user asks to fact-check, verify a claim, confirm whether something is true, source-check an answer, or mentions "事实校验", "帮我确认", "这是真的吗", "verify this", "fact check", "source check", "due diligence".OtherNo warnings★ 73↓ —
- conan-vcpkgOutlineDriven/outline-driven-developmentUse when adding C/C++ dependencies with Conan or vcpkg, managing binary compatibility, integrating with CMake via conanfile.txt or vcpkg.json, or choosing between Conan and vcpkg.OtherNo warnings★ 55↓ —
- Huntress AgentsWYRE-AI/msp-claude-pluginsHuntress endpoint agents: the agent lifecycle, organization and platform filters, health signals such as `last_seen_at` and version, fleet-audit workflows, and the errors returned for missing or empty agent results.OtherNo warnings★ 52↓ —
- lov-fill-web-formlovstudio/skillsFill web forms by fetching form fields from a URL, deep-searching the user's local knowledge base for relevant info, and generating a markdown document with all answers pre-filled. Use when the user provides a URL to a web form (conference application, speaker submission, event registration, profile form) and wants help filling it out from their existing materials. Also trigger when the user mentions "填网页表", "fill web form", "网页填表", "表单填写", "申请表填写", "conference application", "speaker submission", "讲师申请", "报名表", or provides a URL with "form", "feedback", "apply", "register", "submit" in the path.OtherNo warnings★ 73↓ —
- validatehashgraph-online/awesome-codex-pluginsFreshly 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.OtherNo warnings★ 1.4K↓ —Also in 2 other repos
- xs-transcriberkaraage0703/ai-assistant-workspace音声ファイルをテキストに文字起こしするスキル。mp3/wav/m4a/ogg/flac形式に対応。whisperベースのtranscriber_toolを使用し、tiny/base/small/medium/largeの5つのモデルから精度と速度のバランスを選択可能。長時間音声はバックグラウンド実行に対応。「文字起こしして」「音声をテキストに変換して」で使用。OtherNo warnings★ 137↓ —
- xs-bridge-ideaskaraage0703/ai-assistant-workspaceワークスペース内の遠い知識や活動をつないで、新しいアイデアを生成する思考支援スキル。過去記事・メモ・発信資産から企画や実装ネタを出したい時に使用。「アイデア出して」「知識をつないで」「一見関係ないものをつないで」で使用。OtherNo warnings★ 137↓ —
- xs-xangi-settingskaraage0703/ai-assistant-workspacexangiの設定確認・設定ファイル変更・反映再起動を行うスキル。最新仕様は対象cloneのxangiドキュメントを参照する。「このチャンネルでも応答して」「タイムアウト変えて」「設定確認して」で使用。OtherNo warnings★ 137↓ —
- xs-tech-news-curationkaraage0703/ai-assistant-workspaceRSSフィードからAI・技術系ニュースを選び、本文を確認して要約と注目理由を紹介するスキル。「テックニュース」「最新のニュース教えて」「技術ニュースまとめて」で使用。OtherNo warnings★ 137↓ —
- Liongard DetectionsWYRE-AI/msp-claude-pluginsLiongard's change and anomaly detection layer: detections generated by inspection-to-inspection comparison, detection types/severities/status lifecycle, configurable alert rules and notification channels, custom metrics with JMESPath expressions and threshold evaluation, and the platform timeline audit trail.OtherNo warnings★ 52↓ —
- guillotineOutlineDriven/outline-driven-developmentUse when dead, duplicate, superseded, or generated residue must leave more than one artifact class of a repo or subsystem, preserving behavior. Not for one enumerated record set: use clean-clean-cut.OtherNo warnings★ 55↓ —
- gsd-workstreamscoco-research/cocoUse when the user runs /gsd-workstreams or asks to list, create, switch, status, progress, complete, or resume parallel workstreams for concurrent milestone work. The active one is tracked in the GSD_WS variable.OtherNo warnings★ 795↓ —
- Datto RMM DevicesWYRE-AI/msp-claude-pluginsDatto RMM device management: identifiers (UID, hostname, MAC), device types and statuses, user-defined fields (UDF1-30), warranty data, and device lookup/update/delete operations.OtherNo warnings★ 52↓ —
- lov-thesis-polishlovstudio/skillsPolish and elevate MBA thesis / dissertation to national outstanding thesis quality (全国优秀论文). Performs comprehensive improvement: academic language, argument structure, logical rigor, innovation highlights, and formatting. Input: markdown thesis text. Output: polished full text. Also trigger when the user mentions "论文润色", "MBA论文", "优秀论文", "thesis polish", "dissertation improvement", "学术润色".OtherNo warnings★ 73↓ —
- gsd-set-profilecoco-research/cocoUse when the user wants to switch the GSD model profile for agents: quality, balanced, budget, or inherit. Runs the gsd-tools config-set-model-profile command and shows its output verbatim.OtherNo warnings★ 795↓ —
- minutes-tagsilverstein/minutesLightweight outcome tagging for meetings — won, lost, stalled, great, or noise. Use whenever the user says "tag this meeting", "mark that as a win", "that one was a loss", "tag yesterday's call as stalled", "mark this great", "that meeting was noise", "label that meeting", or any time they describe a meeting outcome in passing. Tagging takes 5 seconds and unlocks /minutes-mirror correlation analysis — the more meetings get tagged, the smarter mirror gets at telling the user what behavior patterns lead to wins. Surface this skill any time the user mentions a meeting result, win, loss, or wasted time.OtherNo warnings★ 1.6K↓ —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↓ —
- zig-crossOutlineDriven/outline-driven-developmentUse when building Zig or C for another platform with Zig: target triples, -mcpu features, zig cc cross-compiles, multi-target build.zig, bare-metal Cortex-M, or WebAssembly. Not GCC: use cross-gcc.OtherNo warnings★ 55↓ —
- roadrunner-scenario-authoringmatlab/matlab-agentic-toolkitProgrammatically author RoadRunner scenarios from MATLAB using roadrunnerAPI. Use when adding actors, creating routes, building scenario logic (phases, conditions, actions), placing vehicles/pedestrians, defining cut-in/crossing/ follow scenarios, or any programmatic scenario creation in RoadRunner. Triggers on: roadrunnerAPI, scenario authoring, add actor, create route, phase logic, cut-in scenario, pedestrian crossing, scenario from MATLAB.OtherNo warnings★ 1.2K↓ —
- Liongard SystemsWYRE-AI/msp-claude-pluginsLiongard systems — the assets discovered by inspections — plus their detail data (raw configuration JSON with historical snapshots), dataprint extraction via JMESPath expressions, and the v2 Asset Inventory identity and device profiles that correlate one entity across multiple inspectors.OtherNo warnings★ 52↓ —
- PagerDuty On-CallWYRE-AI/msp-claude-pluginsPagerDuty on-call model: schedules with rotation layers, restrictions, the computed final schedule, and overrides; escalation policy tiers and timeouts; on-call entry fields; and the schedule, escalation policy, and team MCP tools.OtherNo warnings★ 52↓ —
finishing-a-development-branch
arbiterForge/codeArbiter
OtherUpdated 7 hours ago
From the author
Open a PR or finish branch disposition; route CI watching and post-merge cleanup to their owners. Merge and discard need explicit authority.
Install
npx skills add arbiterForge/codeArbiter --skill finishing-a-development-branch -a claude-code
Installs to .claude/skills/finishing-a-development-branch/ · Each command fetches the skill straight from GitHub with the open skills CLI.
No download: this skill’s licence (AGPL-3.0) does not let us redistribute its files. The install commands fetch them from GitHub instead.
What it can touch
Instructions onlyNo network use seenLicence: AGPL-3.0
Safety checks on SKILL.md
No warnings.
Why 82
Security100
Provenance66
Maintenance100
Licence80
Adoption37
Files (1)
- SKILL.md