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
- ca-adrarbiterForge/codeArbiterRecord user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.OtherNo warnings★ 149↓ —
- Pipeline HealthWYRE-AI/msp-claude-pluginsCRM pipeline health assessment against whatever CRM is discovered through the gateway: stage-velocity norms derived from closed-won deals, activity-based stalled-deal detection, raw and quality-adjusted pipeline coverage against a revenue target, and the CRM-less degradation rule (report nothing rather than fabricate figures).OtherNo warnings★ 52↓ —
- Strix•Nuclei 用法asdfgh1445/ctf-super-hubStrix Nuclei 命令手册,覆盖模板选择、高吞吐执行与自动化边界控制;触发名:strix-nucleiOtherNo warnings★ 840↓ —
- generalizeOutlineDriven/outline-driven-developmentUse when asked to derive the general rule a request carries as examples instead of a stated rule, then bound it. Not for ambiguity in a stated request: use askme. Read-only.OtherNo warnings★ 55↓ —
- close-doneOutlineDriven/outline-driven-developmentUse when the user wants to batch-close resolved or outdated tracker items. The agent never closes tracker items itself. Not for individual closure or items still under active work.OtherNo warnings★ 55↓ —
- 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↓ —
- wayfinderOutlineDriven/outline-driven-developmentUse when a greenfield project or large feature build will not fit in a single agent session. Don't use for implementation, remote credential changes, or work that fits in one session.OtherNo warnings★ 55↓ —
- heaptrackOutlineDriven/outline-driven-developmentUse when tracking heap allocations on Linux with heaptrack: allocation hotspots, peak heap, temporary allocations, leaks, or a diff of two runs via heaptrack_print. Not for heap errors: use valgrind.OtherNo warnings★ 55↓ —
- Axcient AppliancesWYRE-AI/msp-claude-pluginsAxcient x360Recover appliances: the physical/virtual hardware running local backups, its device roster, and the org-wide vs client-scoped list tools.OtherNo warnings★ 52↓ —
- issue-nowOutlineDriven/outline-driven-developmentUse when a human asks to compare one closed or stale tracker issue with current reality and mark it done or update it. Don't use for bulk issue reconciliation or multi-issue sweeps.OtherNo warnings★ 55↓ —
- 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↓ —
- Nutanix StorageWYRE-AI/msp-claude-pluginsThe Nutanix storage read surface across four namespaces: `storage_execute` for storage containers and volume groups, `volumes_execute` for iSCSI / NVMe-TCP volume group attachment state, `objects_execute` for the S3-compatible object store, and `files_execute` for virtual file servers and NFS/SMB shares — capacity, configuration, and attachment queries.OtherNo warnings★ 52↓ —
- valgrindOutlineDriven/outline-driven-developmentUse when running Valgrind Memcheck for heap errors, leaks, or uninitialised reads on an unmodified binary, or Cachegrind, Callgrind, or Massif profiling. Not for ASan builds: use sanitizers.OtherNo warnings★ 55↓ —
- io-uringOutlineDriven/outline-driven-developmentUse when building Linux servers with liburing, batching SQEs, multi-shot operations, provided buffer rings, registered files and buffers, or zero-copy send. Not for packet I/O: use af-xdp.OtherNo warnings★ 55↓ —
- capstoneOutlineDriven/outline-driven-developmentUse when the learner is ready to apply cleared concepts in a real project. Not for exercises or quizzes: use drill.OtherNo warnings★ 55↓ —
- 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↓ —
- show-meOutlineDriven/outline-driven-developmentUse when asked to show/diagram: comparison table, data record, metric card, stepper, mockup, numeric chart, interactive explainer. Modes: widget/chart/explainer. Not for audits: use show-me-your-work.OtherNo warnings★ 55↓ —
- Datto RMM SitesWYRE-AI/msp-claude-pluginsDatto RMM site management: site hierarchy and identifiers, proxy and patch-window settings, site-scoped device/alert queries, and create/update/delete operations for client locations.OtherNo warnings★ 52↓ —
- HaloPSA InvoicesWYRE-AI/msp-claude-pluginsHaloPSA invoices as a read-only MCP surface: listing by client or date range, filtering by payment and send status, retrieving line-item detail on a single invoice, and the reporting and reconciliation workflows built on them.OtherNo warnings★ 52↓ —
- 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↓ —
- SpamTitan ListsWYRE-AI/msp-claude-pluginsSpamTitan sender allowlists and blocklists: the add/remove/list action parameter, entry types, allowlisting trusted senders to prevent false positives, blocking unwanted senders and domains, and the scoping limit — neither manage tool takes a domain parameter.OtherNo warnings★ 52↓ —
- 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↓ —
- Keeper KSM Notation QueriesWYRE-AI/msp-claude-pluginsThe KSM notation string grammar accepted by `get_field`: the three-part `<record>/<type>/<field-path>` shape, the four field-path forms (plain, indexed, property, indexed-property), `field` vs `custom_field` vs `file` selectors, how the record segment is classified as a UID or a title, which characters the validator rejects outright, and how the returned value is masked.OtherNo warnings★ 52↓ —
- 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↓ —
andy-grove-intel
swaylq/master-skill
From the author
Andy Grove 视角. Intel 前 CEO, 《High Output Management》/《Only the Paranoid Survive》作者, Operator-Engineer 流派 (流派 B) 奠基者, OKR 之父 (John Doerr 的源头). 把 CEO 工作当工程系统管: 产出 = 组织产出, 经理杠杆率, OKR, 战略拐点 (SIP), 建设性对抗. 用途: 当用户问 "组织效率 / 中层管理 / OKR 怎么定 / 会议怎么开 / 什么时候该全力转向 (战略拐点判断) / 数据驱动经营" 类问题时, 用 Grove 的 经营科学镜片先把 "杠杆率在哪 + 拐点信号是噪音还是信号" 盘清楚再给判断. 当用户提到 "Andy Grove" "Grove" "High Output Management" "OKR 源头" "战略拐点" "strategic inflection point" "Only the Paranoid Survive" "经理杠杆率" 时使用. 即使用户只是说 "用 Grove 思路看一下" 也应触发.
Install
npx skills add swaylq/master-skill --skill andy-grove-intel -a claude-code
Installs to .claude/skills/andy-grove-intel/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Safety checks on SKILL.md
No warnings.
Why 82
Files (5)
- SKILL.md
- meta.json
- references/source-list.md
- references/thought-fingerprint.md
- references/voice-samples.md