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.
49,501 skills from 2,391 repositories · updated 32 minutes ago
10,572 skills
- alterlab-torch-geometricUpdatedAlterLab-IEU/AlterLab-Academic-SkillsGraph Neural Networks with PyTorch Geometric (PyG) — node and graph classification, link prediction, GCN, GAT, and GraphSAGE layers, heterogeneous graphs, and molecular property prediction. Use when building or training GNNs for geometric deep learning on graph-structured data. Part of the AlterLab Academic Skills suite.OtherNo warnings★ 84↓ —
- cachebeatARahim3/cachebeatKeep the Anthropic prompt cache warm by firing a tiny heartbeat only after N minutes of true session inactivity (any exchange resets the clock), so the next real turn reads the conversation at cached price / cached quota instead of a full uncached re-read. The heartbeat is a background Stop hook this skill registers (asyncRewake) - it re-arms itself after every turn, with no tool calls and no permission prompts. Use when the session may sit idle (training runs, CI, downloads, the user stepping away) longer than the cache TTL. Args - idle threshold in minutes (default 50), optional max hours (default 8), or "stop".OtherNo warnings★ 85↓ —
- visant-refineUpdatedpedrojaques99/visant-skills-publicOne shared anatomy for charts, gauges, sparklines, simulation sliders, metric tiles and control panels, so a screen looks designed, not assembled. Use on "add a chart", "simulator slider", "control panel", "inspector", "polish this", "gráfico", "painel de controles", "burilar o painel", "refinar".OtherNo warnings★ 82↓ —
- 1c-form-addUpdatedDesko77/claude-code-skills-1cДобавить управляемую форму к объекту конфигурации 1СOtherNo warnings★ 89↓ —
- 1c-erf-initUpdatedDesko77/claude-code-skills-1cСоздать пустой внешний отчет 1С (scaffold XML-исходников)OtherNo warnings★ 89↓ —
- 1c-web-stopUpdatedDesko77/claude-code-skills-1cОстановка Apache HTTP Server. Используй когда пользователь просит остановить веб-сервер, Apache, прекратить веб-публикациюOtherNo warnings★ 89↓ —
- 1c-cf-validateUpdatedDesko77/claude-code-skills-1cВалидация конфигурации 1С. Используй после создания или модификации конфигурации для проверки корректностиOtherNo warnings★ 89↓ —
- mac-ops0xDarkMatter/claude-modsmacOS workstation diagnostics: kernel panics, failing drives, launchd startup audit, wake reasons, TCC denials, APFS snapshots. Triggers on: mac is slow, won't boot, kernel panic, login loop, drive failing, launchd, TCC permissions, Full Disk Access, Gatekeeper, sysdiagnose.OtherNo warnings★ 80↓ —
- rust-ops0xDarkMatter/claude-modsRust development patterns, ownership, async, error handling, and ecosystem. Use for: rust, cargo, ownership, borrow checker, lifetime, tokio, serde, trait, Result, Option, async rust, crate, derive, impl, enum, pattern matching, Arc, Mutex, Send, Sync, thiserror, anyhow, clap, axum, sqlx, reqwest, rayon, tracing.OtherNo warnings★ 80↓ —
- evals-ops0xDarkMatter/claude-modsBuild and run evals for LLM and agent systems: golden datasets, LLM-as-a-judge with bias control, trajectory/step/outcome scoring, adversarial refuters, and CI regression gates. Triggers on: eval, evals, eval harness, golden dataset, golden set, LLM-as-a-judge, judge rubric, judge bias, judge calibration, Cohen kappa, agreement with human labels, pass@k, pass^k, trajectory eval, step-level eval, tool-call accuracy, regression gate, eval CI, blocking vs advisory eval, faithfulness score, DeepEval, Braintrust, Opik, Langfuse, AgentOps, did my prompt change make it worse, is my agent getting better.OtherNo warnings★ 80↓ —
- portless-ops0xDarkMatter/claude-modsPortless local-dev HTTPS proxy: replaces port numbers with named URLs (Caddy/nginx alternative for local dev). Triggers on: portless, local https proxy, named localhost URL, custom TLD, portless alias, portless.json, local CA trust, boot persistence, monorepo routing, Tailscale dev sharing.OtherNo warnings★ 80↓ —
- 1c-config-indexUpdatedDesko77/claude-code-skills-1cИндекс XML-выгрузки конфигурации 1С в один JSON - какие объекты есть, их реквизиты, табличные части, измерения и ресурсы регистров, экспортные методы общих модулей. Нужен другим навыкам для проверок, где объект сверяется с остальной конфигурациейOtherNo warnings★ 89↓ —
- 1c-web-unpublishUpdatedDesko77/claude-code-skills-1cУдаление веб-публикации 1С из Apache. Используй когда пользователь просит убрать публикацию, удалить веб-доступ к базеOtherNo warnings★ 89↓ —
- 1c-xdto-validateUpdatedDesko77/claude-code-skills-1cВалидация пакета XDTO 1С. Используй после создания или модификации пакета XDTO для проверки корректностиOtherNo warnings★ 89↓ —
- 1c-form-decompileUpdatedDesko77/claude-code-skills-1cДекомпиляция управляемой формы 1С (Form.xml) в JSON-черновик формата /form-compile. Используй когда нужно декомпилировать форму, преобразовать Form.xml в JSON, получить DSL из существующей формы для анализа или доработкиOtherNo warnings★ 89↓ —
- 1c-meta-decompileUpdatedDesko77/claude-code-skills-1cДекомпиляция объекта метаданных 1С в JSON-заготовку формата meta-compile. Используй когда нужно получить черновик DSL-описания нового объекта по образцу другого. Не сохраняет UUID/модули/формы.OtherNo warnings★ 89↓ —
- qiskitKalarisLabs/research-agent-skillsBuild, simulate, transpile, and execute quantum circuits with Qiskit and IBM Quantum Runtime. Use for Qiskit 2.x circuits and operators, V2 Sampler or Estimator primitives, target-aware transpilation, local or noisy simulation, IBM QPU execution, Runtime sessions or batches, error mitigation, and Qiskit ecosystem packages.OtherNo warnings★ 99↓ —
- yeetPaulRBerg/agent-skillsUse for GitHub PR/issue/discussion workflows: create/update PRs, issues, or discussions and post issue or discussion comments; triggers include yeet.OtherNo warnings★ 104↓ —
- fact-checkscdenney/open-science-skillsFact-check manuscript claims against their cited sources in a per-source Markdown knowledge base. Use to audit claim support, overclaiming, direction, scope, and misattribution after source intake is complete.OtherNo warnings★ 69↓ —
- qualtrics-opsscdenney/open-science-skillsOperate or audit a live Qualtrics survey via the v3 APIs without breaking fielding: publish gating, quotas, flow routing, embedded data, panel-vendor redirects, read-back verification, and a read-only pre-fielding audit. Use when publishing or patching a fielding instrument, when a quota counts but never blocks, or before launch.OtherNo warnings★ 69↓ —
- citation-checkscdenney/open-science-skillsAudit a manuscript's citations for fabricated sources, DOIs that resolve to the wrong work, in-text and reference-list mismatches, style, and claim support, verified against Crossref and OpenAlex. Use to check citations, references, a .bib file, or DOIs.OtherNo warnings★ 69↓ —
- survey-data-auditscdenney/open-science-skillsAudit fielded survey response data for registered elements, data quality, bot and AI-automation screening, and sample integrity, and emit an appendix-ready quality report. Use at soft launch or after fielding, before outcomes are analyzed.OtherNo warnings★ 69↓ —
- qualtrics-opsscdenney/open-science-skillsOperates or audits a live Qualtrics survey through the v3 APIs without disrupting fielding. Covers publish gating, quotas, flow routing, embedded data, panel-vendor redirects, read-back verification, and a read-only pre-fielding audit. Use when publishing or patching a fielding instrument, when a quota counts without blocking, when configuring panel-vendor redirects or flow gates, or when auditing a survey before launch for consent gates, force-response completeness, quotas and redirects, anti-bot instrumentation, and language-arm symmetry.OtherNo warnings★ 69↓ —
- citation-checkscdenney/open-science-skillsAudits a manuscript's citations for fabricated or nonexistent sources, DOIs that resolve to a different work, mismatches between in-text citations and the reference list, APA 7 or journal style, and whether each source supports the claim it is attached to. Checks entries against Crossref, OpenAlex, and DataCite and labels anything it could not verify NOT CHECKED. Use to check citations, references, a .bib file, or DOIs, or when a source may be AI-invented. Figures and tables go to figure-table-audit.OtherNo warnings★ 69↓ —
nemotron-policy-generator
NVIDIA/skills
OtherUpdated 6 hours ago
From the author
Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-Content-Safety. Produces a Markdown policy, JSON taxonomy, and drop-in inference prompts. Maps rough words or an existing policy to V2 categories, adding custom categories or topic-following rules.
Install
npx skills add NVIDIA/skills --skill nemotron-policy-generator -a claude-code
Installs to .claude/skills/nemotron-policy-generator/ · Each command fetches the skill straight from GitHub with the open skills CLI.
No download: this skill’s licence (Custom or unclear) does not let us redistribute its files. The install commands fetch them from GitHub instead.
What it can touch
Instructions onlyNo network use seenLicence: Custom or unclear
Safety checks on SKILL.md
- Contains hidden text (invisible characters, long comments or encoded blobs)Medium
Why 77
Security80
Provenance83
Maintenance100
Licence45
Adoption57
Files (13)
- BENCHMARK.md
- SKILL.md
- assets/nemotron_policy_generator.html
- assets/nemotron_system_prompt_template.txt
- assets/policy_json_schema.json
- assets/policy_md_template.md
- evals/EVAL.md
- evals/evals.json
- references/content_safety_taxonomy.md
- references/policy_patterns.md
- references/target_models.md
- skill-card.md
- +1 more