Showing 5221–5250 of 10202 skills
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
Hazmi35/turnfleet
External skill interface for integration with external systems
plurigrid/asi
Optimizes and polishes an existing AI/LLM prompt the user has already written — fixing wording, grammar, structure, redundancy, and clarity — while strictly preserving the original intent, role, scope, capabilities, constraint strength, and every technical detail (commands, paths, URLs, parameters, code blocks). Use whenever the user invokes /prompt-optimizer with a prompt (no extra instruction needed), or pastes a prompt and asks to optimize, refine, polish, clean up, simplify, tighten, restructure, make more professional, or "fix the wording" of it, even without the word "prompt" — e.g. "make this system message clearer", "让这个提示词更专业". Do NOT use for writing a brand-new prompt from scratch, for merely executing a prompt the user provides without asking to optimize it, for polishing ordinary prose (emails, articles, essays), for optimizing source code, or for explaining/teaching prompt-engineering theory.
talki-io/prompt-optimizer
Use this skill whenever the user wants to operate on git worktrees — create, enter, list, remove, or garbage-collect — including parallel agent sessions, side-by-side PR reviews, benchmarking multiple branches, or isolating a dirty tree from a fresh checkout. Trigger even when "worktree" is not said — phrasings like "spin up a fresh copy of branch X", "run claude in a clean checkout", "try this patch without touching my changes", or "open PR-123 side-by-side with main" all qualify. Do NOT trigger for conceptual or educational questions about git worktree (e.g. "what's the difference between git worktree and git clone?") — those are answered from general git knowledge, not this skill.
HikaruEgashira/gh-wt
Front-door skill for the Apideck MCP server — 330 unified-API tools across 10 domains plus 4 intent-grouped workflow tools, exposed via dynamic discovery. Use when the user is building an MCP-based agent (Claude Code, OpenAI Agents SDK, Pydantic AI, LangChain) and wants to integrate with any of the 200+ SaaS connectors Apideck covers. Hosted at mcp.apideck.dev/mcp; stdio transport via `npx -y @apideck/mcp` for local development.
apideck-libraries/api-skills
Task playbook for fetching a month-end financial snapshot via the Apideck MCP server's `apideck-month-end-close-check` workflow tool. Use when the user asks for a P&L, balance sheet, aged creditors, or aged debtors view at a point in time. Read-only, idempotent, returns partial snapshots when some reports aren't supported by the connector.
apideck-libraries/api-skills
Task playbook for converting a hired ATS applicant into an HRIS employee via the Apideck MCP server's `apideck-onboard-employee` workflow tool. First cross-unified-API workflow — requires both ATS and HRIS connections active on the consumer. Optionally moves the applicant to a "hired" stage in the ATS to close the loop.
apideck-libraries/api-skills
Task playbook for paying a vendor bill via the Apideck MCP server's `apideck-pay-bill` workflow tool. Use when the user asks to settle, pay, or close a known accounts-payable bill in QuickBooks, Xero, NetSuite, or any other connected accounting service. Covers confirmation prompts, partial payments, payment-method capitalization quirks, and the AP-vs-AR routing decision agents routinely get wrong.
apideck-libraries/api-skills
Task playbook for recording a customer payment against an invoice via the Apideck MCP server's `apideck-receive-customer-payment` workflow tool. Use when the user says a customer paid an invoice and wants the accounting service updated. AR mirror of `apideck-pay-bill` — same shape, opposite ledger side. Different unified endpoint, different counterparty (customer vs supplier), different allocation type.
apideck-libraries/api-skills
Create and maintain AGENTS.md files for project onboarding and grounding. Use when initialized in a new project, when project structure changes significantly, or when creating subfolder-level AGENTS.md files for complex monorepos.
AndrewBrown-USDA/aigb-skills-usda
Translate legacy HelixDB HQL (.hx QUERY/RETURN syntax) into direct v3 SDK requests (Rust or TypeScript, with Go and Python spellings of the same AST). Use when the input contains HQL concepts such as typed node, edge, or vector sources; AddN/AddE/AddV; Out/In/OutE/InE; FromN/ToN; WHERE/EQ/GT/EXISTS; SearchV/SearchBM25; GROUP_BY/AGGREGATE_BY; ORDER/RANGE; UpsertN/UpsertE; ShortestPathBFS; RerankRRF; Embed; or .hx files. Maps upserts to one conditional write batch and BFS paths to shortest_path, and flags HQL features with no v3 equivalent (reranking, inline embedding, weighted paths, advanced math, EXISTS-in-WHERE, schema defaults, macros). When the target is Helix Cloud, always use helix-mcp first.
HelixDB/skills
微信发信能力:通过 Windows 桌面微信发送文本、图片URL或本地文件。适合各类 Agent 在本机直接发送一次性消息。触发词:给[某人]发微信、通知[某人]、把这个用微信发给[某人]、用微信发个图片、把本地文件发给[某人]
LAVARONG/wechat-automation-api
Prevent destructive operations using Claude Code hooks. Three modes — cautious (warn on dangerous commands), lockdown (restrict edits to one directory), and clear (remove restrictions). Uses PreToolUse matchers for Bash, Edit, and Write.
rohitg00/pro-workflow
Prepare the whole requested scope for implementation with research, a completed product interview, a reviewed specification, bounded tasks, and an execution prompt suited to its size. Explicit invocation requests durable planning records; ordinary read-only planning stays read-only. Stop before implementation. If context was compacted while this workflow governed, reopen this file and the SkipHow CTO skill before the next consequential action.
mzored/SkipHow
JeecgBoot UniApp3 移动端 CRUD 代码生成器。Use when user asks to generate UniApp3/mobile/APP CRUD pages, create mobile list/form pages, or says '生成移动端代码', '生成APP页面', 'uniapp代码生成', '移动端CRUD', '生成uniapp页面', '手机端页面', '移动端模块', 'generate uniapp code', 'mobile CRUD', 'uniapp page', 'APP端代码', '生成小程序页面', '生成H5页面'. Also triggers when user mentions generating mobile pages for an existing backend module, or wants to add mobile support to JeecgBoot modules. Even if user just says '给XX模块加个移动端页面' or '做个手机端的XX功能', this skill should trigger.
jeecgboot/skills
The OpenSite persistent long-term memory store. Provides a hierarchical filesystem tree for all agent memories across four cognitive layers: episodic (session history), semantic (project/tech/user knowledge), procedural (decisions, workflows, conventions), and working (active session state). Use this skill to directly read, write, search, or inspect memory entries. For automated session capture use memory-write; for context retrieval before a task use memory-recall; for periodic maintenance use memory-consolidate.
opensite-ai/opensite-skills
Runs a background maintenance agent that consolidates, deduplicates, decays confidence, and compresses old sessions in the memory store. Run this skill periodically (weekly or monthly) to keep the memory store lean and high-signal. Also useful after large batches of memory-write operations. Prevents the store from growing stale or bloated over time.
opensite-ai/opensite-skills
Compress project context into HANDOFF.md with workflow state, analysis checkpoint, next gate, verification, current hypothesis, freshness anchors, optional gotcha references, and a resume packet for the next agent session.
tmusser/ai-engineering-skills
Compress routine agent responses to reduce token usage while preserving commands, file paths, assumptions, risks, verification details, and next actions.
tmusser/ai-engineering-skills
Coordinate multi-agent work through a tool-neutral contract for authoritative tasks, isolated execution, ownership, handoffs, evidence, acceptance, and archives. Use with harness-workflow for engineering delivery and load matching operations-management standards for operational effects.
ai-workspace-lab/xworkspace-core-skills
需求事实来源(Source of Truth)与 Issue/PR 溯源关联标准。用于确定"这次要做什么"的权威载体、把 Issue → 分支 → commit → PR → CI → 部署 → tag 串成双向可导航的溯源链、约束 Agent 自行取用上下文(而不是要人类粘贴需求与报错日志)、以及处理范围漂移与跨仓需求扇出。任何"派发一个任务就自主开工"的闭环执行都必须先遵守本标准。
ai-workspace-lab/xworkspace-core-skills
Compile one Markdown role file into native subagent profiles for Antigravity, Claude Code, Codex, Copilot, Cursor, Gemini CLI, Grok, Kilo, and OpenCode.
fmind/agent-supagents
Reconcile App Store Connect subscriptions and in-app purchases with RevenueCat products, entitlements, offerings, and packages using asc and RevenueCat MCP. Use when setting up or syncing subscription catalogs across ASC and RevenueCat.
The-Artificer-of-Ciphers-LLC/skills-from-the-artificer
Mandatory regression analysis before committing a bug fix. Use before any fix commit, after any change to a guard, condition, ownership check, or flow-control trigger, or after an agent proposes a fix. Prevents the fix-break-fix cycle by tracing every callsite, actor, and follow-up action that depends on the changed condition, and by escalating to a redesign after repeated review findings.
The-Artificer-of-Ciphers-LLC/skills-from-the-artificer
Quick-reference card for OpenSpec in the-grid (the 12 wired skills, spec format, CLI). Use when the user asks "how do I use openspec", "how do I add specs to this repo", "what are the openspec commands" or "which openspec skill do I want".
oneafrikan/the-grid
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
plurigrid/asi
Retro the current session. Score it against session shapes, flag token waste with next-turn fixes, and propose wire-ins into the skills this conversation actually called.
renzrollon/shippable-skills
Use when an abstract symbol such as a chakra, sephirah, alchemical stage, rune, or hexagram needs reusable character and action blocks for image generation with a separately chosen visual style. For a complete Blakean image prompt, see blakean-scene.
augchan42/inkstone
Funding rounds, investments, and acquisitions in the Diffbot Knowledge Graph by company, investor, acquirer, round series, amount, date, or the company's industry. MUST USE skill when the answer involves a list of investment deals: deal flow, a company's funding history, an investor's portfolio activity, M&A lists, or the largest deals in a period. Rows are investment deals. Triggers on: funding rounds, raised, Series A, venture funding, funding history, deal flow, deal size, investments in, acquisitions, M&A, acquired for, valuation round.
diffbot/diffbot-skills
Runs a raw DQL (Diffbot Query Language) query against the Diffbot Knowledge Graph. The general-purpose layer beneath the entity-specific Diffbot skills: use it for entity types and query shapes they do not cover, such as products, patents, job posts, facet aggregations, cross-entity queries, an id filter from entity resolution, or ontology lookups. Triggers on: dql, query knowledge graph, search diffbot, diffbot kg, ontology lookup, facet query, entity types, raw dql.
diffbot/diffbot-skills