Skill-uri pentru agenți pe care le poți verifica înainte să le instalezi
Skill-uri SKILL.md publice din depozite GitHub cu peste 50 de stele și de la producători, scanate și evaluate. Instalează oricare dintre ele cu o singură comandă în Claude Code, Cursor, Codex, GitHub Copilot sau Gemini CLI.
45.604 skill-uri din 2.205 depozite · actualizat acum 10 ore
5.536 de skill-uri
- zup-hr-api-referenceDesko77/claude-code-skills-1cСправочник API конфигурации 1С:ЗУП 3.1 (Зарплата и управление персоналом) по кадровому учету. Используй при разработке/доработке на ЗУП 3.1, когда нужны методы КадровыйУчет, КадровыйУчетРасширенный, ЗарплатаКадры, ФизическиеЛицаЗарплатаКадры - получение кадровых данных сотрудников и физлиц, стажи, даты приема/увольнения, договоры ГПХ, совместители, штатное расписание, остатки отпусков, паспортные данные, склонение ФИО, представления СКД ЗУП. Также расчетная часть: средний заработок и его перерасчет, начисления (план видов расчета, регистр расчета), пособия и обмен с СФР (СЭДО), страховые взносы, регламентированная и статистическая отчетность, корректировка движений через ПереносДанных. НЕ использовать для БП, ERP, УТ, УНФ - только ЗУПInginerieFără avertismente★ 85↓ —
- 1c-code-reviewDesko77/claude-code-skills-1cРевью BSL-кода по каталогу дефектов: каждая находка получает идентификатор карточки, важность и ключ локации. Триггеры: ревью BSL, проверь код по антипаттернам, code review 1С, проверь код перед коммитом, а также вызов из команды закрытия задачи.InginerieFără avertismente★ 85↓ —
- trace-codesCalibre-Labs/reforge-ai-evalsTurn free-form notes from reading agent traces into trace codes: named, yes/no failure or quality patterns with definitions, examples and counts. Use this skill whenever someone has annotated traces or review notes and asks to "cluster my notes", "create trace codes", "find the failure modes", "do error analysis on these annotations", "what patterns are in these traces", or "what should we fix first". Also use to merge new notes into an existing set of codes. Output is a trace codes file, a labeling sheet for human review, and proposed rubric updates.InginerieFără avertismente★ 85↓ —
- apify-company-data-apiapify/awesome-skillsPull structured B2B company data from Clutch.co with the Clutch.co Agency API Actor (johnvc/clutch-agency-api). Give it company profile URLs or bare slugs and get one JSON record per company: name, website, rating, review_count, verification badges, min_project_size, hourly_rate, employees, founded_year, headquarters and every office location, languages, service_lines and focus_areas with percentages, industries, clients, cost_rating, most_common_project_size, pricing_by_service, and published packages. Each profile row can also carry LLM-ready markdown at no extra fetch, and verified client reviews as their own rows. Use when someone wants a company data api, to enrich a CRM with firmographics and service mix, pull B2B service provider records, or turn a list of agency profiles into structured company data as JSON. Billed per profile delivered with no start fee, and MCP-ready for Claude and other AI agents.InginerieFără avertismente★ 282↓ —
- eval-codeCalibre-Labs/reforge-ai-evalsWrite deterministic, code-based evaluator functions for an AI product. Use this skill whenever you need to write evaluators that check structural properties of AI outputs (format, count, presence, schema compliance) without calling another LLM. Also use when auditing existing code-based evaluators for brittleness, coverage gaps, or false positives.InginerieFără avertismente★ 85↓ —
- trace-review-appCalibre-Labs/reforge-ai-evalsDesign and build a custom trace review app for one AI product: a single-page tool where the team reads traces, writes notes, labels pass or fail, tags trace codes and exports the results for other skills. Built around that product's own trace shape, rubric and failure modes, and set up so reviewing becomes a habit (a queue, progress, streaks, quick keys). Use this skill whenever someone asks to "build a trace viewer", "make an annotation tool", "set up a review page for our traces", "make trace review less painful", "build a labeling app", or says the team isn't reading traces because the tool is clunky.InginerieFără avertismente★ 85↓ —
- bmad-walkthroughalvin-reyes/better-agentic-ideGuide a human review of a commit, PR, file, or directory. Use when invoked by nameInginerieFără avertismente★ 85↓ —Apare și în 1 alt depozit
- alreviewpaleo/alignfirstExecute the AlignFirst review protocol.InginerieFără avertismente★ 86↓ —
- code-janitorGulajavaMinistudio/awesome-copilot-idThe Ultimate Senior Fixer. Combines planning, specification, and coding into a single, high-speed execution mode for one-off tasks, ad-hoc fixes, and minor refactors. Fast-tracks standard SDLC workflows while strictly enforcing Karpathy-level meticulousness and Ponytail-level simplicity. Trigger via /code-janitor or when the user asks for a quick fix, cleanup, or fast minor feature outside the full SDLC pipeline.InginerieFără avertismente★ 87↓ —
- manage-flag-lifecycleharness/harness-skillsManage metadata and lifecycle for a Harness FME feature flag: update description, tags, owners, rollout status; assess archive readiness (usage, experiments, dependents); archive/unarchive; delete definitions in one environment; delete the flag. Supports single flags or explicit small lists (≤ 20). Use when asked to change flag metadata, archive a flag, check if a flag is safe to archive, unarchive a flag, or delete a flag/definition. Do not use for targeting changes (update-flag-targeting), creating flags (create-feature-flag), discovering stale flags across a project (discover-feature-flags), removing flag code (cleanup-feature-flags), or rollout pipelines (fme-pipeline). Trigger phrases: update flag description, flag metadata, archive flag, unarchive flag, delete flag, archive readiness, is flag safe to archive, flag lifecycle.InginerieFără avertismente★ 125↓ —
- manage-rolesharness/harness-skillsManage Harness RBAC roles, role assignments, permissions, and resource groups via MCP v2 tools. List, create, update, and delete custom roles. View role assignments and permissions for users, groups, and service accounts. Use when asked to manage access control, assign roles, check permissions, create custom roles, review RBAC configuration, onboard users, or audit access. Trigger phrases: manage roles, RBAC, role assignment, user permissions, access control, custom role, resource group, who has access, grant access, revoke access.InginerieFără avertismente★ 125↓ —
- inertia-react-developmentpromovaweb/specsfyDevelops Inertia.js v3 React client-side applications. Activates when creating React pages, forms, or navigation; using <Link>, <Form>, useForm, useHttp, setLayoutProps, or router; working with deferred props, prefetching, optimistic updates, instant visits, or polling; or when user mentions React with Inertia, React pages, React forms, or React navigation.InginerieFără avertismente★ 87↓ —Apare și în 3 alte depozite
- mcd-gitzhutoumeme/mcd-git用本地命令行 mcd-git（git mcd --json）帮用户点麦当劳：选门店、看菜单、加购物车（去酸黄瓜、少冰、套餐换搭）、自动凑套餐挑最省的券、核价、下单拿支付链接、查取餐码、再来一单、取消订单、领券（pull，先确认），以及生成 1024 吃麦贡献图（card）。用户提到点麦当劳、麦当劳到店 / 得来速 / 麦乐送、取餐码、再来一单、取消麦当劳订单、领麦当劳的券、吃麦贡献图时使用。下单、取消和领券都必须先把确认摘要给用户看，用户明确同意后才能带 --confirm 执行。InginerieFără avertismente★ 85↓ —
- bmad-agent-devalvin-reyes/better-agentic-ideSenior software engineer who implements stories and code changes. Use when the user asks to talk to Amelia or requests the developer agentInginerieFără avertismente★ 85↓ —Apare și în 1 alt depozit
- pseudocode-to-java-codeArabelaTso/Skills-4-SEConverts pseudocode descriptions and algorithm specifications into complete, executable Java code. Use this skill when you need to implement algorithms from pseudocode, translate algorithm descriptions to Java, generate Java code from specifications, convert textbook algorithms to working code, or create executable implementations from high-level descriptions. Preserves logic and control flow while handling Java idioms, data structures, and includes test cases for verification.InginerieFără avertismente★ 259↓ —
- summer-apiSummerEngine/summerSummer API game assets: models, estimate, one job or a batch, download the files.InginerieFără avertismente★ 88↓ —
- pi-setupwquguru/skillsThis skill should be used when the user wants to install or configure Pi Agent (@earendil-works/pi-coding-agent) with DeepSeek (built-in), Ant-Ling Ring-2.6-1T (single-model custom provider), and ZenMux (multi-model OpenAI-compatible aggregator including Gemini 3.5 Flash, inclusionAI Ling-3.0-flash, Claude, GPT), including auth, models.json, settings.json, a curated extension set, and known-pitfall fixes. Triggers on "配置 pi"、"setup pi agent"、"pi 装一下"、"配 ring/deepseek/gemini/zenmux/ling 到 pi".InginerieFără avertismente★ 94↓ —
- create-metricharness/harness-skillsCreate a Harness FME metric: helps decide what to measure, suggests candidate metrics from application code, resolves traffic type and event type IDs, drafts the payload, then creates. Use when asked to create or define a new metric, decide what to measure, or get metric suggestions from application code. Doesn't attach metrics to experiments (manage-experiments) or add the tracking call (instrument-metric). Trigger phrases: create/define a metric, new metric, what metrics should we create, suggest metrics.InginerieFără avertismente★ 125↓ —
- you-webyoudotcom-oss/agent-skillsSearch the live web and read full pages with You.com. Use whenever a task needs information newer than training data or from outside the codebase: current library docs and API references, changelogs and release notes, breaking changes, error messages, package versions, pricing, news, or any claim to verify with cited sources. Works keyless through the free MCP profile when no You.com credentials are configured.InginerieFără avertismente★ 94↓ —
- modular-code-enforcementArabelaTso/Skills-4-SEEnforces strict modular code architecture: SRP, no monolithic index files, no catch-all utils, 200 LOC hard limit. This rule is NON-NEGOTIABLE. Violations BLOCK all further work until resolved.InginerieFără avertismente★ 259↓ —
- manage-usersharness/harness-skillsManage Harness users, user groups, and service accounts via MCP. List and search users, create and manage user groups for team-based access, create service accounts for API automation, and view available permissions. Use when asked to list users, create a user group, manage service accounts, check who has access, or set up team permissions. Do NOT use for role assignments or resource groups (use manage-roles instead). Trigger phrases: list users, user group, service account, who has access, team permissions, add user to group, create service account.InginerieFără avertismente★ 125↓ —
- llm-cachingBagelHole/DevOps-Security-Agent-SkillsImplement multi-layer LLM caching with exact match, semantic similarity, and provider-side prompt caching. Reduce API costs by 30–70%, cut latency, and improve throughput using Redis, GPTCache, and provider caching APIs.InginerieFără avertismente★ 1,2 K↓ —
- debug-pipelineharness/harness-skillsDiagnose Harness pipeline executions via MCP. Analyzes any execution (failed or successful) to produce structured reports with stage/step breakdown, timing, bottlenecks, failure details, chained pipeline drill-down, and execution logs. Use when asked to debug a pipeline, investigate a failure, find out why a build failed, analyze pipeline errors, check execution logs, review execution performance, or find bottlenecks. Trigger phrases: debug pipeline, pipeline failed, why did my build fail, analyze failure, pipeline error, execution logs, fix pipeline, execution bottleneck, slow pipeline.InginerieFără avertismente★ 125↓ —
- ai-operationsharness/harness-skillsConfigure Harness AI-powered operations (AIDA) via MCP. Set up predictive failure analysis with ML models for memory leaks, disk exhaustion, connection pool saturation, and latency degradation. Configure intelligent alert correlation and noise reduction to reduce alert volume. Use when asked to set up predictive failure analysis, configure AI-powered alerting, reduce alert noise, or enable ML-based anomaly detection. Do NOT use for pipeline debugging (use debug-pipeline instead) or SLO management (use manage-slos instead). Trigger phrases: AIDA, predictive failure, alert correlation, noise reduction, anomaly detection, AI ops, predictive analysis, alert fatigue, ML alerting, intelligent alerting.InginerieFără avertismente★ 125↓ —