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.
49.361 de skill-uri din 2.397 de depozite · actualizat acum 15 minute
49.361 de skill-uri
- experiment-designrampstackco/claude-skillsA discipline for designing experiments (A/B tests, multivariate, holdouts) so the results actually answer the question you asked. Hypothesis writing, sample size, duration, segment analysis, running discipline, matching a result to a pre-committed decision rule, and the common failure modes that produce confidently wrong shipping decisions. Use this skill whenever the user is planning a test that has not run yet: framing a hypothesis, sizing the sample, setting duration, choosing guardrails, or deciding whether something is worth testing at all. Triggers on design an experiment, experiment plan, A/B test, split test, multivariate test, holdout, experiment hypothesis, sample size, minimum detectable effect, MDE, test duration, guardrail metric, no peeking, pre-committed decision rule, is this worth testing. Use `experimentation-analytics` instead when the test has already run and the question is how to read the result panel.DesignFără avertismente★ 1 K↓ —
- tddhashgraph-online/awesome-codex-pluginsTest-Driven Development enforcer. Red→Green→Refactor cycle with no production code without a failing test first. Use for new features and bug fixes.TestareFără avertismente★ 1,5 K↓ —
- 02-rl-rewardagentscope-ai/OpenJudgeBuild RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies based on RL algorithm, task type, and cost; aggregating multi-dimensional pointwise scores into a scalar reward; pairwise tournament reward for GRPO on subjective tasks (net win rate across group rollouts); generating preference pairs for DPO/RLAIF; and normalizing scores for training stability. Use when building reward models, scoring rollouts for GRPO/REINFORCE, generating preference data for DPO, or doing Best-of-N selection.ProductivitateFără avertismente★ 1,1 K↓ —
- assemble-ppmpluginmicrosoft/power-platform-skillsAssemble the final `.ppmplugin` binary bundle for a PAM native extension and verify its contents. First **reconciles** the manifest's declared `entrypoints` against the binaries actually staged — if the manifest declares a platform with no built binary it gates (build it / ship without it / stop) rather than shipping a broken bundle. Then re-runs the plugin's upload-compatibility checks on the reconciled manifest, zips the manifest plus whichever of `android/<PascalName>Plugin.dex` and `ios/<PascalName>Plugin.framework/` are present into `ppmplugin/<name>.ppmplugin`, and verifies the archive layout with `jar tf` (exactly the manifest + the shipped binaries — nothing missing, nothing extra). Output: a statically verified `.ppmplugin` file on disk. Prereqs: `jar` (JDK). Run after /generate-ppmplugin-manifest and the build skill(s).AlteleFără avertismente★ 1,1 K↓ —
- metric-designagentscope-ai/OpenJudgeUse when the user has evaluation principles or a dataset but needs help choosing the right graders, designing evaluation metrics, creating LLM-as-judge prompts, combining multiple metrics into a composite score, or building an automated evaluation pipeline. Also use when the user mentions grader selection, metric design, judge prompt engineering, rubric design, evaluation pipeline code, or "how to evaluate [X] automatically." Outputs executable OpenJudge pipeline code.DesignFără avertismente★ 1,1 K↓ —
- oma-pdffirst-fluke/oh-my-agentConvert PDF files to Markdown using opendataloader-pdf. Extracts text, tables, headings, lists, and images with correct reading order. Use for PDF parsing, PDF to Markdown conversion, document extraction, and AI-ready data preparation.DocumenteFără avertismente★ 1,4 K↓ —
- cn-fupanmohitagw15856/pm-claude-skillsRun a 复盘 (fupan), the structured project review widely used in Chinese companies: review the goal, assess the result, analyse why, and draw rules for next time, with a blame-free tone and owned actions. Use when asked 帮我做复盘, 项目复盘, 活动复盘, 复盘会怎么开, or a fupan or retrospective in Chinese. Produces the 复盘 document in Chinese with goal versus result, root causes split into controllable and uncontrollable, lessons stated as reusable rules, and an action list with owners and dates, plus a meeting agenda.RedactareFără avertismente★ 1,5 K↓ —
- workhashgraph-online/awesome-codex-pluginsUse for execution, debugging, verification, planning, and shipping when the user's Emulo working profile should guide the task. Do not use for design/UI/UX work, marketing or social writing, or Emulo setup/mining.DesignFără avertismente★ 1,5 K↓ —Apare și în 2 alte depozite
- adhd-output-stylefcakyon/claude-codex-settingsThis skill should be used when the user asks for "ADHD output", "fewer output tokens", "short numbered steps", "limited working memory formatting", or explicitly invokes "adhd-output-style".ProductivitateFără avertismente★ 1,2 K↓ —
- minutes-searchsilverstein/minutesSearch past meeting transcripts and voice memos for specific topics, people, decisions, or ideas. Use this whenever the user asks "what did we discuss about X", "find that meeting where we talked about Y", "what did Alex say", "did we decide on", "what was that idea about", or any question that could be answered by searching their meeting history. Also use for "do I have any notes about" or "check my meetings for".PlanificareFără avertismente★ 1,6 K↓ —Apare și în 1 alt depozit
- resumemohitagw15856/pm-claude-skillsWrite a sharp, achievement-led resume/CV that passes ATS and earns the interview. Use when asked to write or rewrite a resume or CV, turn experience into a resume, or tailor a resume to a job. Produces a clean, single-column, ATS-friendly resume — summary, experience as quantified accomplishment bullets, skills, and education — ready to export as a designed PDF.DocumenteFără avertismente★ 1,5 K↓ —
- build-android-binarymicrosoft/power-platform-skillsCompile a PAM control's Android Kotlin module into the runtime-loadable DEX for a `.ppmplugin`. Creates a staged Gradle build with the pinned wrapper and `react-android` compile dependency, verifies manifest/module/package alignment and runtime-loading constraints, builds the release AAR, then runs `d8 --min-api 24`. Writes `ppmplugin/staging/android/<PascalName>Plugin.dex` and surfaces actionable Gradle or d8 failures. Requires JDK 17+ and Android SDK Build-Tools 35.0.0; `d8` is located from the SDK and system Gradle is optional. Run after /generate-ppmplugin-manifest and before /assemble-ppmplugin.RedactareFără avertismente★ 1,1 K↓ —
- 00-academic-routeragentscope-ai/OpenJudgeUse when the user wants help with academic papers or citations but it's unclear which specific workflow fits — reviewing a paper, checking a BibTeX file for fake references, or benchmarking multiple LLMs on reference-recommendation accuracy. Also use when the user mentions paper review, peer review, BibTeX verification, citation checking, reference hallucination, or academic literature accuracy and hasn't specified which of those three tasks they mean. This skill is the entry router for the academic-eval suite: it asks one diagnostic question then routes to the right sub-skill.ȘtiințăFără avertismente★ 1,1 K↓ —
- minutes-x1-send-meetingsilverstein/minutesSend one of the user's own Minutes meetings to their X1 household for review. Use when the user wants a meeting's summary, decisions, action items, and open questions to reach X1 so they can confirm what belongs in their household record. X1 asks the user to approve the send, and nothing reaches the household record until they confirm each item. Never use it for a restricted meeting, a transcript, or someone else's meeting.InginerieFără avertismente★ 1,6 K↓ —Apare și în 1 alt depozit
- videohashgraph-online/awesome-codex-pluginsUse when a brief has to become a film. Turns a one line ask into a Claude Design prompt written in the animations-v3 engine's own language, plus the built piece.jsx and a contact sheet to look at before anyone renders. Covers reference roles, the kit, the storyboard gate, the motion floor, and the verification commands. Do not use for backend work, UI design, or marketing copy alone.MediaFără avertismente★ 1,5 K↓ —Apare și în 1 alt depozit
- verify-cli-runreticlehq/reticleProve that a command-line tool actually did what it said, instead of trusting its exit code and its output. Snapshots the filesystem before and after, names the expected consequence in advance, and returns one of four verdicts with what could not be seen. Use after running a build, a migration, a scaffolder, a formatter, a codegen step, or an AI coding CLI; when a command printed success and you are about to report "done"; when you are about to write "exit code 0, so it worked"; or when a tool claims it edited files. Needs nothing installed.InginerieFără avertismente★ 1,2 K↓ —
- helphashgraph-online/awesome-codex-pluginsShow KERNEL help. The unified skill system, state operations, agents, current plugin status. Triggers: help, how, what, skills, commands.AlteleFără avertismente★ 1,5 K↓ —
- ticket-authoringrampstackco/claude-skillsWrite complete, ready-to-pull work items for an issue tracker: bugs, tasks, stories, spikes, and epics, each with the fields, attachments, and done test its type requires. Use this skill whenever the user wants to write a ticket, create a Jira issue, Linear issue, or GitHub issue, file a bug report, write a user story or acceptance criteria, scope a spike, open an epic, or break work into tasks. Triggers on write a ticket, create an issue, file a bug, bug report, user story, spike, epic, task breakdown, turn this into tickets, break this down, acceptance criteria, definition of ready, ready for dev, backlog item, capitalization stage. Also triggers when the user pastes a PRD, a spec, or a bug description and asks what to do with it, even if they never say the word ticket.TestareFără avertismente★ 1 K↓ —
- jlcpcbhashgraph-online/awesome-codex-pluginsJLCPCB PCB fabrication and assembly — BOM/CPL generation, basic vs extended parts, assembly constraints, design rules, ordering workflow. Use with KiCad for JLCPCB manufacturing. Use this skill when the user mentions JLCPCB, wants to order PCBs or assembled boards, needs prototype bare PCBs and stencils, wants to know JLCPCB design rules and capabilities, or is asking about PCB manufacturing costs or turnaround times. For gerber/CPL export, stencil ordering, and BOM management, see the `bom` skill.DesignFără avertismente★ 1,5 K↓ —
- company-watchhashgraph-online/awesome-codex-pluginsWatches a company or topic on podcasts and YouTube: what was said lately (shows, counts, momentum, quotes), then an Arcmira monitor to keep following it.AlteleFără avertismente★ 1,5 K↓ —
- ponderNouhashgraph-online/awesome-codex-pluginsConvergent multi-pass deliberation and code review ledger that enumerates units, grades every unit against a lens rubric, runs four-perspective deliberation (Skeptic, Builder, Dreamer, Empath), records append-only finding deltas, verifies phantom-unit removals across all historical paths, and enforces 1.00 coverage and zero-churn convergence before stopping. Use when the user says "ponder <anything>" ("ponder the UI", "ponder our error handling", "ponder this PR"), "run a ponder audit", "grade every unit with the ponder ledger", "run four-voice Skeptic/Builder/Dreamer/Empath deliberation", or asks for a coverage-gated multi-pass lens audit across files or screens where stopping early would miss units. Also use to resume or recover a ponder session in flight - "where were we in the ponder", "carry on pondering", or an existing .ponder/ directory - by running ponder status rather than starting over.DesignFără avertismente★ 1,5 K↓ —
- officehashgraph-online/awesome-codex-pluginsRun a Homie studio's live games from its back office - who is playing right now in every room (players, bots, round, uptime), announce a line to players in-game, kick or mute a player, close a room, set players per room, and each game's launch state (private, invite-only beta with invite links and codes, public). The owner confirms anything that takes something away with one tap. Use when someone asks who is playing, wants to talk to their players, remove or silence a player, run a closed or invite-only beta, hide or launch a game, make invite codes, or run the studio's Lounge (its community room, with play nights, moderators and kept chat).AlteleFără avertismente★ 1,5 K↓ —
- tsa-complianceSushegaad/Claude-Skills-Governance-Risk-and-ComplianceExpert TSA cybersecurity compliance advisor for critical infrastructure owners and operators. Use this skill whenever a user asks about TSA Security Directives for pipelines, freight railroads, passenger rail, public transit, or bus operators; the TSA Cyber Risk Management Program (CRMP); Cybersecurity Implementation Plan (CIP); Cybersecurity Operational Implementation Plan (COIP); Cybersecurity Assessment Plan (CAP); incident reporting to CISA; designation of a Cybersecurity Coordinator; Critical Cyber Systems (CCS); OT/IT network segmentation; the TSA November 2024 NPRM; or any directive in the SD Pipeline-2021 series, SD 1580-21-01 (freight rail), or SD 1582-21-01 (public transit/passenger rail). Also trigger for questions like "are we covered by TSA directives?", "what does the TSA require for pipeline cybersecurity?", "how do I build a CIP?", "what must I report to CISA?", or any request involving transportation critical infrastructure cybersecurity compliance.JuridicFără avertismente★ 1 K↓ —
- the-vibe-checkmohitagw15856/pm-claude-skillsHarden a vibe-coded app before strangers use it — the audit for prototypes built fast with AI: exposed secrets, missing auth checks, unvalidated input, data with no deletion path, and the five embarrassing holes every weekend build has. Use when someone says 'Claude built my app, is it safe to launch', 'harden my prototype', 'vibe check my project', or before putting real users on a hackathon build. Produces a ranked findings list with fixes, a launch-blocker line, and a 'what I'd break first' attacker's tour. Defensive review of YOUR OWN app.InginerieFără avertismente★ 1,5 K↓ —
model-savings
hoangsonww/Claude-Code-Agent-Monitor
DateActualizat acum 10 ore
De la autor
Estimate the dollars saved by routing eligible Claude Code work to a cheaper model family, using the Agent Monitor pricing engine. Re-prices each model's token mix at the target family's rates and quantifies the delta. Uses /api/pricing (rates), /api/pricing/cost (current per-model spend), /api/sessions, and /api/analytics. Use when hunting for cost cuts or comparing model tiers.
Instalare
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill model-savings -a claude-code
Se instalează în .claude/skills/model-savings/ · Fiecare comandă descarcă skill-ul direct de pe GitHub cu utilitarul open source skills.
Descarcă .zip
Identic octet cu octet cu commit-ul scanat, cu licența depozitului și un fișier SOURCE.txt.
La ce are acces
Doar instrucțiuniNu am văzut acces la rețeaLicență: MIT
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 88
Securitate100
Proveniență77
Întreținere100
Licență100
Adopție49
Fișiere (2)
- SKILL.md
- agents/openai.yaml