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.
45,433 skills from 2,188 repositories · updated 14 minutes ago
9,729 skills
- external-assembly-integrated-auditionT8mars/minimax-h3-prompt-skill-T8Create original short videos using the 外部装配｜逐件安装到整机动作验收 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user wants this causal, camera, motion, rhythm, or payoff structure with new subjects and surfaces.OtherNo warnings★ 307↓ —
- stata-helpbrycewang-stanford/Auto-Empirical-Research-SkillsLook up Stata command documentation and display formatted help text.OtherNo warnings★ 4.8K↓ —
- i2brycewang-stanford/Auto-Empirical-Research-SkillsScreening Assistant - AI-PRISMA 6-dimension screening with Groq LLM (100x cheaper) Supports two project types with different confidence thresholds Use when: screening papers, PRISMA screening, inclusion/exclusion criteria Triggers: screen papers, PRISMA screening, inclusion criteria, exclusion criteria, AI screeningOtherNo warnings★ 4.8K↓ —
- dependency-verificationathola/claude-night-marketVerifies a package exists before install, defending against hallucination and slopsquatting. Use when adding, recommending, or installing a package.OtherNo warnings★ 343↓ —
- voice-to-souljmagly/aiwgGenerate a SOUL.md from an existing AIWG voice profileOtherNo warnings★ 225↓ —
- supply-chain-advisoryathola/claude-night-marketAudits dependency supply chains for bad versions, lockfile drift, and artifact integrity. Use when adding deps, handling incidents, or releasing a plugin.OtherNo warnings★ 343↓ —
- metacognitive-self-modathola/claude-night-marketAnalyze and improve the improvement process. Use for detecting regressions and meta-optimization.OtherNo warnings★ 343↓ —
- resilience-retryrrezartprebreza/spring-boot-skillsUse when adding retries, backoff, or concurrency protection to Spring Boot 3 / Spring Framework 6 services. Covers Spring Retry or Resilience4j selection, proxy behavior, and transaction limits.OtherNo warnings★ 325↓ —
- figurebrycewang-stanford/Auto-Empirical-Research-SkillsEconometrics skill for generating publication-quality figures for top economics journals. Activates when the user asks about: "econometric figure", "publication figure", "journal figure", "AER figure", "QJE figure", "event study plot", "coefficient plot", "coefplot", "binned scatter", "binscatter", "RDD plot", "parallel trends plot", "kernel density", "distribution plot", "time series plot", "map", "figure formatting", "academic plot", "论文图表", "学术图", "系数图", "事件研究图", "散点图", "分布图", "趋势图", "回归可视化"OtherNo warnings★ 4.8K↓ —
- remotionlingxling/awesome-skills-cnGenerate walkthrough videos from Stitch projects using Remotion with smooth transitions, zooming, and text overlaysOtherNo warnings★ 319↓ —
- object-handoff-festival-vlog-escalationT8mars/minimax-h3-prompt-skill-T8Create original short videos using the 节庆物件接力｜品尝、游戏、奖品到高空景观逐级升级 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user wants this causal, camera, motion, rhythm, or payoff structure with new subjects and surfaces.OtherNo warnings★ 307↓ —
- progressive-loadingathola/claude-night-marketImplements hub-and-spoke lazy loading to minimize token usage in large skills. Use when building multi-module skills that need conditional on-demand loading.OtherNo warnings★ 343↓ —
- vast-gpubrycewang-stanford/Auto-Empirical-Research-SkillsRent, manage, and destroy GPU instances on vast.ai. Use when user says "rent gpu", "vast.ai", "rent a server", "cloud gpu", or needs on-demand GPU without owning hardware.OtherNo warnings★ 4.8K↓ —
- doctorbrycewang-stanford/Auto-Empirical-Research-SkillsSystem diagnostics and health checks for Diverga plugin. OpenClaw-style Check-Report-Fix pattern with 5-layer diagnostics. Triggers: /diverga:doctor, diverga doctor, system check, diagnose, 진단OtherNo warnings★ 4.8K↓ —
- continuous-emotion-escalation-conceal-residueT8mars/minimax-h3-prompt-skill-T8Create original short videos using the 情绪压力曲线｜压抑、峰值、遮挡与残余 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user wants this causal, camera, motion, rhythm, or payoff structure with new subjects and surfaces.OtherNo warnings★ 307↓ —
- methodology-curatorathola/claude-night-marketSurface expert frameworks. Use when creating or evaluating skills, hooks, or agents.OtherNo warnings★ 343↓ —
- agent-expenditureathola/claude-night-marketTracks per-agent token usage and flags waste in parallel dispatch. Use when evaluating parallel agent efficiency or after a multi-agent run.OtherNo warnings★ 343↓ —
- helpbrycewang-stanford/Auto-Empirical-Research-SkillsDiverga help guide - displays all 24 agents across 9 categories, commands, and usage examples. Triggers: help, guide, how to use, 도움말OtherNo warnings★ 4.8K↓ —
- run-miniature-pursuit-foraging-routeT8mars/minimax-h3-prompt-skill-T8Create original short videos using the 微缩逃亡｜巨物追赶到资源补给 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user wants this causal, camera, motion, rhythm, or payoff structure with new subjects and surfaces.OtherNo warnings★ 307↓ —
- night-market-config-catalogathola/claude-night-marketCatalog every config axis, its defaults and guards. Use when adding or auditing configuration. Do not use for running gates; use night-market-operations.OtherNo warnings★ 343↓ —
- action-first-outputathola/claude-night-marketShapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.OtherNo warnings★ 343↓ —
- add-yourself-to-team-langfuselangfuse/langfuse-docsAdd a new team member to Langfuse's canonical team data and shared team table. Use when onboarding a new employee who needs to appear on the website team, press, about, careers, or handbook pages.OtherNo warnings★ 247↓ —
- lateral-movement-readinesszero-lab-ai/skillsReviews an already-supplied lateral movement candidate for exact upstream map binding, authorization, non-production isolation, containment, telemetry, stop control, rollback, cleanup ownership, custody, tool governance, and a separate-validation handoff. Use before transferring a candidate to a lab validation team.OtherNo warnings★ 281↓ —
- training-dataericrisco/rsc-harnessUse when assembling or curating the corpus a fine-tune trains on — turning raw examples into the JSONL shape a trainer expects (instruction, conversational, preference-pair or binary-label), matching the data to the model's chat template, generating synthetic or distilled examples, deduplicating and decontaminating against eval sets, and quality-filtering. NOT cleaning tabular rows, nulls and dtypes (that is `data-cleaning`), NOT building a retrieval corpus of chunks and embeddings (that is `embeddings-search`), NOT running the trainer or picking hyperparameters (that is `finetuning`).OtherNo warnings★ 255↓ —
single-decision-impact-return-lockup
T8mars/minimax-h3-prompt-skill-T8
OtherUpdated Oct 18, 2026
From the author
Create original short videos using the 单次决策兑现｜准备—执行—后果—回归 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user wants this causal, camera, motion, rhythm, or payoff structure with new subjects and surfaces.
Install
npx skills add T8mars/minimax-h3-prompt-skill-T8 --skill single-decision-impact-return-lockup -a claude-code
Installs to .claude/skills/single-decision-impact-return-lockup/ · 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 85
Security100
Provenance70
Maintenance100
Licence100
Adoption41
Files (4)
- SKILL.md
- agents/openai.yaml
- references/summary.md
- references/template.md