技能与智能体开发
5,949 个结果
- Google CalendarkrokodillusWHEN a step reads or creates Google Calendar events: the secret iCal address, the Calendar API with a service account, or an Apps Script bridge
- Improve Convex PluginConvexSend THIS coding session's transcript (Claude Code or Codex) to the Convex quickstart backend (anteater) for an AI post-mortem that improves the whole system — the runbook, bootstrap script, and skills.
- Inline Plan DevsentimonyYou MUST use this when executing an existing implementation plan directly in the current agent session, including resuming interrupted execution. Covers task-by-task implementation, plan drift, and verification. Not for subagent-driven execution.
- Integrate Atlas ChatcognitedataException path. Use integrate-fusion-agent for Atlas/chat/agent. Only when the user explicitly requires in-app useAtlasChat and connectToHostApp cannot provide the EOS sidebar (standalone app, always rejects). Triggers: useAtlasChat, in-app atlas chat, embedded chat, vendored atlas-agent. Not for generic "add a chat".
- JiradpetersenMANDATORY skill for ANY acli jira command. YOU MUST use this skill for ALL Jira queries - both initial searches AND follow-up queries. NEVER run acli jira commands directly outside this skill. This includes viewing tickets, comments, attachments, sprints, boards, searches, and ANY other acli jira operation.
- Microsoft TeamskrokodillusWHEN a step posts a message to Microsoft Teams: how to set up the webhook for a channel, a group chat or one person, and how to tell that Teams accepted a post apart from Teams delivering it
- Monorepo ChangesetRadiusDecide whether a change to any released plugin or package in this monorepo needs a Changeset, then draft, create, or review its release note and semantic version bump. Use when assessing pull requests, diffs, commits, user-facing changes, changelog entries, release notes, shared-code impact, future plugins, or whether to propose the `pr:no-changeset` label.
- Parallel AgentssentimonyYou MUST use this when several units of work might run concurrently through agents - independent investigations, specialist reviews, repository analyses, or plan tasks that look unrelated - covering whether they are genuinely independent, which mutable state needs isolation, how wide the wave should be, and how results are reconciled before integration.
- Payanagentchoniv05PayanAgent is a marketplace where AI agents discover, hire, and pay each other using USDC on Base via x402. 24,000+ services are buyable today — the whole x402 ecosystem in one catalog, one buy route, no signup. Use it to buy capabilities you lack, monetize what only you can do, post bespoke work, or check any seller's trust score via their signed-receipt history.
- pixeltable/pixeltable-skillPixeltable技能合集Agent skill, plugin and MCP server for building multimodal AI apps with Pixeltable in Claude Code, Cursor, Codex and Gemini CLI. Tables, computed columns, embedding search, UDFs and 30+ AI providers.
- Prath ModeprathamdbyRoute a goal to a skill or delivery chain.
- PythonrukikotooExecute Python scripts and code using the user's Anaconda Python installation at C:\Users\29165\anaconda3\python.exe. Use this skill when the user needs to run Python code, execute Python scripts, install Python packages, or perform any Python-related tasks.
- Rss Agent Viewerbrooksy4503AI agent-friendly CLI RSS/Atom feed viewer with discovery, search, and OPML import/export. Use when an agent needs to manage RSS feeds, read articles, or run feed discovery from the terminal. Triggered by: "read RSS feeds", "view RSS", "RSS reader CLI", "rss-viewer", "discover RSS feeds", "import OPML", "search feeds", or "discover-search feeds".
- Skill 071legendtklAdvanced techniques for mining biomedical data to uncover hidden patterns and relationships in health research.
- SlackkrokodillusWHEN a step posts a message to Slack: how to set up an incoming webhook for one fixed channel, how to post to it, and what makes a post fail
- spacefast/pluginsSpacefast技能合集Official Spacefast plugins for AI coding assistants.
- Subagent Plan DevsentimonyYou MUST use this when executing an existing implementation plan through coordinated subagents, including resuming interrupted orchestration. Covers task delegation, review, verification, and integration. Not for inline plan execution or unrelated parallel investigations.
- Tmb Agent SetuptrustmybotInspect, install, or remove TrustMyBot's two fixed project-level Codex Agents. Use only when the user explicitly invokes $tmb:tmb-agent-setup and confirms the exact project-local file changes.
- Tmb BrotrustmybotInspect a Git project with TMB's project-local inventory and world model, clarify a request, and capture an approved local planning issue plus Bro-authored decisions. Use only when the user explicitly invokes $tmb:tmb-bro for repository understanding or planning; stop before implementation, task orchestration, review, or delivery.
- Tmb CheatcodetrustmybotWhen bro hits a wall — a task leans on a capability the project plainly lacks — and an existing published skill, MCP toolkit, or plugin would close the gap better than hand-rolled code. Bro names the gap, calls cheatcode_search for ranked candidates, judges which best fits this task and codebase, and recommends it for the Human to approve.
- Tmb Concerns ProtocoltrustmybotHow bro raises a concern when doubting the Human's plan — surface inline via discussion_append + ask, or spawn a consultant in analysis-only mode for technical disagreement. Always surface disagreement; always yield to the Human's call, and when the Human said not to ask, record the concern with the recommended default as a decision and proceed. Loaded when bro genuinely disagrees with a request.
- Tmb Docs ConventionstrustmybotLoaded when editing prompt files (agents, skills, CLAUDE.md, workflow markdown) or updating user-visible docs. Carries the editing judgment — what to delete, what to preserve, and where ripples land when a rename or restructure happens.
- Tmb Push GatetrustmybotBro's push-gate orchestration — reaping unsigned commits, spawning pr-reviewer per task, and the all-pass push + PR-create + post-merge cleanup path. Loaded by bro when the push hook blocks or the Human asks for review-before-push.
- Tmb Swe ChecklisttrustmybotSWE's self-review heuristics — load only when about to atomic-close. Mechanical patterns (bare except, missing timeout, mutable defaults, etc.) are caught by the plugin's code-quality-lint hook; this skill carries the spec-fidelity and scope discipline judgment.