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.
49,409 skills from 2,375 repositories · updated 1 hour ago
48,362 skills
- 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.ProductivityNo warnings★ 1K↓ —
- cn-lesson-planmohitagw15856/pm-claude-skillsUse when asked 帮我写教案, 写一份新课标教案, 教学设计, 单元教学设计, 大单元教案, or a lesson plan in the format Chinese schools expect. Produces a complete 教案 in Chinese with 教材分析, 学情分析, 教学目标 tied to the subject's 核心素养, 教学重难点, 教学方法, a timed 教学过程 with teacher and student activity, 板书设计, layered 作业设计 within the 双减 time limits, and 教学反思 prompts, with curriculum references marked to confirm against the current 课程标准.PlanningNo warnings★ 1.5K↓ —
- train-sentence-transformershuggingface/skillsTrain or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification), `SparseEncoder` (SPLADE, sparse embedding model for learned-sparse retrieval), and `MultiVectorEncoder` (ColBERT / late-interaction, per-token embeddings scored with MaxSim). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.OfficialProductivityNo warnings★ 11.3K↓ —
- ru-checkhashgraph-online/awesome-codex-pluginsFull Russian text quality check against the whole corpus. Triggers: вычитай, вычитай через ru-text, прогони ru-text, проверь текст по ru-text, ru-check, полная вычитка. Use when the user asks to proofread Russian text, or when a project gate names ru-text. Returns findings with the rule behind each and a proposed replacement; never edits a file. Self-initiated runs start with a fast triage and escalate on evidence; an explicit request always runs the full corpus.WritingNo warnings★ 1.5K↓ —Also in 1 other repo
- hri-workflowbrycewang-stanford/Awesome-Journal-SkillsUse to plan an ACM/IEEE HRI campaign backward from the full-paper deadline through the abstract-then-paper two-step, the rebuttal, the program-committee meeting, camera-ready, and the March conference, coordinating the parallel alt.HRI, Late-Breaking Reports, video, and Student Design deadlines.ProductivityNo warnings★ 1.4K↓ —
- steinwallhashgraph-online/awesome-codex-pluginsSteinWall cost, savings and safety information, and a security check for extensions. Use when the user asks what the coding agent costs today or this month, how much budget is left, what was blocked or saved, or before installing a skill, plugin or MCP server ("is this safe to install?", "check this skill").SecurityNo warnings★ 1.5K↓ —
- eacl-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing an EACL submission before its single ACL Rolling Review cycle deadline, covering ACL-template compliance, the 8-page long / 4-page short content caps, the mandatory Limitations section, the Responsible NLP checklist, anonymization, preprint and resubmission declarations, and the no-fallback-cycle timing trap.LegalNo warnings★ 1.4K↓ —
- ru-scorehashgraph-online/awesome-codex-pluginsScore Russian text 0.0–10.0 across five dimensions: typography, clean language, grammar, structure, precision for the reader. Triggers: оцени текст, ru-score, оценка качества текста, насколько хорош текст, балл за текст. Use when the user wants a number rather than a list of findings. Never edits a file.DesignNo warnings★ 1.5K↓ —Also in 1 other repo
- monthly-reviewhoangsonww/Claude-Code-Agent-MonitorCompile a month-over-month retrospective from Agent Monitor data — sessions, cost, token volumes, completion rate, top projects by working directory, and notable shifts versus the prior month. Uses daily_sessions/daily_events (365d) from analytics, the session list, and the pricing cost breakdown. Use when doing a monthly retrospective or planning the month ahead.EngineeringNo warnings★ 1.1K↓ —
- weekly-unstuckmohitagw15856/pm-claude-skillsA short weekly ritual that clears the mental backlog, picks the one thing that matters, and keeps you honest about your dependence on autopilot. Use when asked run my weekly reset, help me plan my week, my weekly check-in, or get me unstuck for the week. Produces a quick brain-dump and triage of what's on you, the single most important focus for the week, the stuck things and their tiny first steps, and a self-check on where you're coasting or over-relying — a recurring executive-function reset rather than a one-off fix.PlanningNo warnings★ 1.5K↓ —
- cav-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when planning a CAV (Computer Aided Verification) project timeline from venue and category selection through submission, the two-stage review with early reject and rebuttal, artifact evaluation by the AEC, and the LNCS open-access camera-ready, with backward-planning offsets for a verification-tool paper and honest handling of the single-annual-deadline cycle.ProductivityNo warnings★ 1.4K↓ —
- pnas-trackbrycewang-stanford/Awesome-Journal-SkillsUse to choose the PNAS submission track — Direct Submission (standard, editor-assigned, peer reviewed) vs Contributed Submission (an NAS member communicates their own paper). Covers eligibility, the editor/member role, the discontinued and legacy tracks, and how to pick. Unique to PNAS.ScienceNo warnings★ 1.4K↓ —
- creating-agent-skillsAgentWorkforce/relayUse when creating Agent Skills packages (SKILL.md format) for Codex CLI, GitHub Copilot, or Amp - provides the agentskills.io specification with frontmatter constraints, directory structure, and validation rulesPlanningNo warnings★ 1.1K↓ —
- debugging-websocket-issuesAgentWorkforce/relayUse when seeing WebSocket errors like "Invalid frame header", "RSV1 must be clear", or "WS_ERR_UNEXPECTED_RSV_1" - covers multiple WebSocketServer conflicts, compression issues, and raw frame debugging techniquesEngineeringNo warnings★ 1.1K↓ —
- agentlas-stormagentlas-ai/Agentlas-OSRun a force-robust Stormbreaker loop — route to real agents, execute a verified pipeline to completion.OtherNo warnings★ 1.6K↓ —
- rfc-writermohitagw15856/pm-claude-skillsWrite an engineering RFC (Request for Comments) for a technical decision, architectural change, or significant implementation approach. Use when asked to write an RFC, document a technical proposal, create a design doc, write an architecture decision for review, or produce a technical specification for team feedback. Produces a complete RFC document covering problem statement, motivation, proposed solution, alternatives rejected, implementation plan, migration plan, security and performance implications, observability changes, rollout plan, and open questions.WritingNo warnings★ 1.5K↓ —
- vis-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing IEEE VIS evaluations, covering how to match evidence to the contribution type (perceptual study, controlled user study, algorithm benchmark, design-study validation, qualitative work), controlled experiment design with power and effect sizes, CVD-safe and perceptually grounded encoding choices, task taxonomies, and provenance so a TVCG reviewer trusts the result.DesignNo warnings★ 1.4K↓ —
- closed-loophuytieu/COG-second-brainRun one task through the V-model verification loop: CP-2 plan → CP-3 build → CP-3v component verify → CP-4 integration verify (full lane) → CP-5 acceptance. The worker never grades its own homework; evidence rows trace back to AC-n. Opt-in: invoke with /closed-loop or by asking for the closed loop, proper verification, or an evidence trail. Ordinary work does not run this.PlanningNo warnings★ 1.3K↓ —Also in 1 other repo
- oma-docsfirst-fluke/oh-my-agentCheck documentation references, sync docs to code changes, and detect translation drift. Use for documentation maintenance in a repository.EngineeringNo warnings★ 1.4K↓ —
- cvpr-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing the experimental program of a CVPR paper, covering benchmark and baseline selection under matched-compute fairness, the ablation study reviewers treat as mandatory, qualitative and failure-case evidence, efficiency metrics tied to the Compute Reporting Form, and generalization tests beyond a single dataset.TestingNo warnings★ 1.4K↓ —
- fse-supplementarybrycewang-stanford/Awesome-Journal-SkillsUse when deciding what belongs in an ESEC/FSE paper body versus its anonymized artifact and appendices, covering the ACM-template page budget, the rule that decision-critical evidence stays inside the reviewed pages, double-anonymous supplementary material, and how to split an empirical-SE paper between body and package.ScienceNo warnings★ 1.4K↓ —
- warranty-claimmohitagw15856/pm-claude-skillsGet a broken product repaired, replaced, or refunded under warranty — with the claim message written, the proof to attach, and the consumer-law backstop for when 'out of warranty' isn't the whole story. Use when asked to make a warranty claim, my [product] broke and it's still under warranty, the manufacturer won't honor the warranty, or how do I get this fixed for free. Produces a ready-to-send claim message, the exact evidence to include, the repair-vs-replace-vs-refund position, and an escalation ladder for when the first answer is no.LegalNo warnings★ 1.5K↓ —
- five-mindsmohitagw15856/pm-claude-skillsAnswer a question five completely different ways — as five independent minds with clashing worldviews — then converge on what survives. Use when asked for multiple perspectives, look at this from every angle, what would different people think, or give me a range of views not one answer. Produces five genuinely distinct takes (each committed to one worldview, not hedged), the tensions between them made explicit, and a final synthesis that keeps what's strongest — deliberately widening the range before narrowing it.OtherNo warnings★ 1.5K↓ —
- dac-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing the empirical evaluation of an ACM/IEEE Design Automation Conference (DAC) Research Manuscript, covering standard EDA benchmark suites (ISPD, EPFL, ISCAS/ITC, TAU, CircuitNet, OpenROAD flows), fair state-of-the-art baselines, QoR/PPA reporting with runtime, per-benchmark honesty, ablations that isolate the mechanism, and contamination-aware ML-for-EDA evaluation.DesignNo warnings★ 1.4K↓ —
build-flow
microsoft/power-platform-skills
OtherUpdated 12 hours ago
From the author
Autonomously build a complete Power Automate flow from a description. Use when you need to generate a full flow definition and create it. Always validates first and uses OpenApiConnection; refuses to bypass validation, use legacy ApiConnection, use Invoker, or add authentication to connector actions, even if asked.
Install
npx skills add microsoft/power-platform-skills --skill build-flow -a claude-code
Installs to .claude/skills/build-flow/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyNo network use seenLicence: MIT
Safety checks on SKILL.md
No warnings.
Why 88
Security100
Provenance77
Maintenance100
Licence100
Adoption49
Files (1)
- SKILL.md