技能与智能体开发
5,949 个结果
- intercom/claude-plugin-externalIntercom技能合集Intercom plugin for Claude Code
- interview-skillYong-yuan-XRun JD- and resume-based technical, comprehensive, or HR interview simulations and coaching for developers with 0–3 years of experience; review user-provided interview records or retest weak areas. Use for job interview practice and reflection, not real hiring decisions.
- Jackin Checkout Prjackin-projectUse only when the user explicitly requests this skill. Switches the current jackin❯ repo onto a pull request's branch via gh pr checkout, guarding the working tree first.
- Jackin Create Prjackin-projectUse only when the user explicitly requests this skill. Opens a pull request for a small jackin❯ change with the correct body shape and auto-selected verify-locally blocks.
- Jackin Goal Promptjackin-projectUse only when the user explicitly requests this skill. Distills a jackin❯ roadmap item — plus optional plan files — into a self-contained /goal prompt capped at 4000 characters.
- Jackin Merge Prjackin-projectUse only when the user explicitly requests this skill. Runs the jackin❯ pre-merge gate, retires the roadmap item into docs, and squash-merges a pull request.
- Jackin Release Checkjackin-projectUse only when the user explicitly requests this skill. Runs the jackin❯ release-readiness gates.
- Jackin Researchjackin-projectUse only when the user explicitly requests this skill. Produces a standalone multi-page research dossier on the jackin❯ docs site, drawing on web and codebase evidence.
- Lambda Memory CapturenicolasfmeloUse when saving a decision or note in Lambda Memory, recording relevant work evidence, or publishing a source-backed revision or correction automatically.
- Lambda Memory PurgenicolasfmeloUse when the user explicitly asks to delete or forget Lambda Memory evidence, or configure source retention; identify exact authorized sources and explain cascading deletion before destructive action.
- Lambda Memory RecallnicolasfmeloUse when consulting Lambda Memory for prior decisions, preferences or work evidence; automatic scoped retrieval with source attribution, leaving use or ignore to the main agent.
- Lambda Memory ReviewnicolasfmeloUse for optional Lambda Memory lifecycle inspection, rejection, explicit conflicts or guarded resolution; automatic publication never requires this review step.
- Lambda Memory RuntimenicolasfmeloUse when setting up, connecting to or diagnosing the local Lambda Memory service, its MCP bridge and the OMP hooks extension; project binding, idle processing and blocked sources.
- Lambda Memory TimelinenicolasfmeloUse when recording, revising or retracting a curated decision in the Lambda Memory timeline, or checking which captured decisions are not yet on it.
- Langsmith Fetchlangchain-aiFetches LangSmith traces for debugging agent behavior. Use when troubleshooting agent issues, reviewing conversation history, or investigating tool calls.
- Leader 1 1 PrepehnruizBuild a prep brief for a recurring 1:1 with a skip-level or senior leader. Pulls the last meeting's notes, the tickets you touched since, recent chat threads with that leader and any drafts they are waiting on, then drafts a fixed five-block agenda with a carry-forward list and an after-action step.
- Legal Process ParserlucianummExamina processos e anexos por página, identifica a medida processual cabível, pesquisa fontes jurídicas e prepara teses, análises ou minutas rastreáveis. Use para leitura integral, atualização, consulta, prova, prazo ou peça solicitada; não protocola nem certifica mérito ou autenticidade.
- LigasseraneLi — Knowledge Manager for Ane's library and MEL Wiki. Use when Ane needs to catalog, retrieve, or reorganize documents in the personal knowledge library, or query/maintain the MEL Wiki. Handles INGEST, QUERY, LINT, PROGRAMMES, and Obsidian vault-survey operations. Does not answer domain questions — retrieves and organizes knowledge for other agents and Ane.
- Mimi CbtwhoamimiGuides the user through CBT-informed (cognitive behavioural therapy) self-help exercises with clear guardrails, such as noticing thoughts, spotting thinking traps and reframing them. This is supportive reflection, not a replacement for a professional therapist or crisis care. Use when the user wants to work through anxious, negative or stuck thoughts, or asks for a CBT exercise.
- Mimi Pr ReviewwhoamimiPrepares and reviews a GitHub pull request end to end — checks the branch is ready, runs Anthropic's multi-agent code review, then summarises findings by severity and fixes them on request. Use when the user wants a pre-merge review of their own changes or asks whether a branch or pull request is ready.
- Mimi TutorwhoamimiTeaches the user English vocabulary, grammar and usage — explores a word's meaning, nuance, alternatives and etymology, explains rules with examples, sets short practice exercises and tracks recurring mistakes. Use when the user wants to understand or learn a word or rule rather than just get a correction.
- Mimi WorldwhoamimiProvides background on the user's directory organisation, home gadgets and personal computer-science projects, such as REST FastAPI services, MCP servers, machine learning, custom PyTorch models and Kaggle hackathons. Use when a task needs context about the user's own projects, devices or file layout, or when the user refers to their work without explaining it.
- New ToolquircedelafuenteCreate a new Ask Q tool (an MCP server) so the assistant can do something new, e.g. "create a tool for my gym's website", "make a tool to check my bus times", "build a tool that books padel courts". Use whenever the user asks for a new capability, integration or tool, or to change an existing one in ~/.askq/tools.
- NiulaiRZX00牛来口癖，始终生效。像用「喵~」结尾那样，每条回复都挂上牛来语气。用户说 hi / hello / 嗨 / 你好 / 牛来 / niulai / 妈～妈 时也启用。自称牛来，用户是妈妈。纯文字，不画图。