Showing 8881–8910 of 10205 skills
Use when implementation work is about to touch code (branch before the first commit), when a built task needs to ship as a pull request, when defining how branches, commits, and PRs map to plan tasks, or when parallel agents share one repository. Triggers on "create a branch", "commit this", "open a PR", "ship this task", "how do we merge", task start or completion during an implementation plan, worktree setup, or noticing commits landing directly on main.
affectionatec/agentic-engineering
Use when a task or milestone claims completion and must be verified before being marked done, when acting as a verifier sub-agent checking a producer's work, or when a "done" claim needs evidence. Triggers on "verify this task", "is this actually done", "acceptance check", "run verification", any completion claim, any 🔍 → ✅ status transition, or dispatching a maker-checker review loop.
affectionatec/agentic-engineering
Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.
x402agent/SolanaOS
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
x402agent/SolanaOS
GEPA-style measured evolution of a learned skill under ~/.config/opencode/skills. Use this skill when the `evolution_status` tool or `optimize_skill` tool returns a skill with high use_count AND non-zero failure rate, OR when the user asks to evolve/improve/optimize/refine a specific skill, OR when the self-improving-skills plugin's `optimize_skill` tool was called (it returns the procedure pointer; this skill provides the actual reasoning). This is the companion axis to `skill-distiller` — distiller ACQUIRES skills, this skill IMPROVES them by reflective mutation grounded in failure traces.
okdk7788/opencode-self-improving-skills
Surface the user's unknown unknowns before they start work in an unfamiliar area (new codebase area, domain, or tool). Produces a read-only blindspot briefing plus advice on how to prompt better. Use when the user says "blindspot pass", "盲区扫描", "unknown unknowns", asks what they don't know or might miss before diving in, says "我刚接手这块代码", "开工前帮我看看有什么坑", or merely describes facing unfamiliar territory — the statement is the request. Not for finished or pre-merge work (use change-quiz), nor for interviewing the user (use interview-me); mixed requests start here — brief, then hand off.
GreatMark/fable-field-guide-skills
Master index for the fable field-guide family (8 finding-unknowns skills): routes to the right skill and defines the artifact contract they share. Use when the user says "field guide", "which of these skills", "该用哪个 skill", "这套流程怎么用", "finding unknowns 工具怎么选", asks which of these skills applies or how the family fits together, or is stuck and can't say what they need — "不知道从哪下手", "where do I even start", "你都会什么", "装了哪些技能"; also read when unsure which finding-unknowns skill fits the current situation.
GreatMark/fable-field-guide-skills
CSlawyer1985/legal-skillhub
Sync the yaah marketing website (website/index.html) with the current project state — features, CLI commands, skills, agents, hooks, and installation instructions. Use this skill whenever the user adds, removes, or changes a feature, CLI command, hook, skill, agent, MCP server, or LSP provider AND the website should reflect that change. Also use when the user explicitly asks to update, sync, or refresh the website, or says things like 'update the site', 'keep the website current', 'reflect this on the website', or 'the website is out of date'.
dirien/yet-another-agent-harness
Protect AI-agent tasks from indirect prompt injection and untrusted tool output by tracing instruction provenance, separating data from authority, constraining source-to-sink flows, and confirming sensitive disclosure or action. Use when reading webpages, issues, emails, documents, logs, MCP results, or third-party skills while tools can access private data or mutate state; do not use for ordinary trusted inputs with no external-content boundary.
CHENG-LIANG1/badass-skills
Create a concise handoff document so a fresh agent or new session can continue the current work. Use only when the user explicitly asks for a handoff, continuation brief, or context transfer.
ykorovko/dotagents
Watch a tutorial or demo video and generate a Claude Code skill from it. Activated when user says "create a skill from this video" or similar.
mnvsk97/eyeroll
Research, filter, compare, and synthesize scientific papers across arXiv, OpenAlex, ACM Digital Library, DBLP, Semantic Scholar, PubMed, SSRN, and publisher landing pages. Use when the agent needs to do literature discovery, find top or recent papers, build a reading list, compare methods or results, trace citation graphs, summarize evidence, or produce properly attributed paper recommendations and literature reviews.
marciob/skill-research-papers
Create, disable, and enable domain skills. Generates project-specific SKILL.md files via a short interview.
mataeil/OODA-loop
Score GitHub Issues using the RICE framework and propose a priority ordering. Strategize phase skill — turns raw issues into a ranked action plan written to agent/state/backlog.json.
mataeil/OODA-loop
Monitor service health endpoints and detect anomalies. Observe phase skill — reads config.health_endpoints, checks availability, records baseline metrics.
mataeil/OODA-loop
Core XMTP Agent SDK setup and patterns. Use when creating new agents, handling messages, setting up middleware, or configuring environment variables. Triggers on agent setup, XMTP configuration, message handling, or middleware implementation.
xmtplabs/xmtp-agent-examples
File attachment handling for XMTP agents. Use when sending or receiving images, files, or any encrypted remote attachments. Triggers on file upload, image sending, or remote attachment handling.
xmtplabs/xmtp-agent-examples
Patterns for handling commands, validating input, and filtering messages in XMTP agents. Use when implementing slash commands, validators, or message filters. Triggers on command handling, input validation, or type guards.
xmtplabs/xmtp-agent-examples
Token transactions and wallet integration for XMTP agents. Use when sending USDC, creating transaction requests, or handling transaction confirmations. Triggers on USDC transfer, wallet calls, or transaction reference.
xmtplabs/xmtp-agent-examples
Group conversation management for XMTP agents. Use when creating groups, managing members, setting permissions, or sending welcome messages. Triggers on group creation, member management, or permissions.
xmtplabs/xmtp-agent-examples
ENS and Web3 identity resolution for XMTP agents. Use when resolving domain names, extracting mentions, or fetching Farcaster profiles. Triggers on ENS resolution, Farcaster lookup, or mention extraction.
xmtplabs/xmtp-agent-examples
Emoji reactions and thinking indicators for XMTP agents. Use when adding reactions to messages or showing processing state with thinking emoji. Triggers on emoji reactions, thinking indicator, or message acknowledgment.
xmtplabs/xmtp-agent-examples
业务诊断助手适合市场营销、运营、产品、销售在用户提出“这件事该怎么做”这类问题,需要快速拆解目标、判断重点并形成可执行结果时使用,帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。
skillsaiagent/aiskills
Cross-platform local decision routing for AI coding agents using Laya and Laya-MLX. Use for fast task classification, complexity estimation, model escalation hints, tool-use routing, and lightweight risk assessment. Advisory only.
wangmiaozero/laya-router-skill
Fetch real estate data from 30+ property portals worldwide using the RealtyAPI REST API. Covers Redfin, Realtor.com, Zillow, Trulia, Homes.com, Apartments.com, HotPads, Auction.com, StreetEasy (US), Centris (Canada), Rightmove, Zoopla (UK), Idealista, SeLoger, Immobiliare, Immowelt, ImmoScout24, Funda, Otodom, Cian (Europe), Bayut, Dubizzle, Property Finder (Middle East), 99.co (Asia), Domain, Flatmates (Australia), and Airbnb, Vrbo, Agoda, Trip.com, Tripadvisor (short-term/vacation). Use when the user asks to look up, search, fetch, or extract property listings, home/rental details, price or tax history, valuations and estimates, comparables, market and rent trends, agents, foreclosures/auctions, or any real estate data for an address, area, or portal. Also use when the user mentions RealtyAPI, a real estate API, MLS data, or a specific property portal.
realtyapi/realtyapi-skills
Run the repo's markdown lint checks over changed files before a PR. On demand, in Claude Code or any session with a shell.
esscott1/job-search-assistant
Run the repo's markdown lint checks over changed files before a PR. On demand, in Claude Code or any session with a shell.
esscott1/job-search-assistant
Run the repo's markdown lint checks over changed files before a PR. On demand, in Claude Code or any session with a shell.
esscott1/job-search-assistant
用户要求复盘当前 Codex 与 Claude Code 的协作、收集连接器迭代日志、分析主控 token 偏高或生成桥接脱敏证据包时使用。只采集当前主控及关联执行会话,不用于继续派发业务任务、修复连接或一般模型价格咨询。
lordfine/codex-claude-bridge