Showing 5311–5340 of 10204 skills
Job search and career discovery through your agent. Search the open tech job board directly, or star the companies that match your stack for an ongoing feed of their roles, all by talking. Backed by company-level tech stack data derived from the roles each company is hiring for now.
remoet-labs/agent-skills
Write or update a HANDOFF.md so a fresh agent can continue this work. Use when the user says "handoff", "compact this", "context is full", or "/clear and continue".
laguagu/claude-code-nextjs-skills
Find currently permitted installed Canvas skills and plugins for a task, especially internal policies, procedures and workflows. Read their exact authorized instructions. Find tools through the selected MCP or Composio connection. Browse external catalogs when the user asks to add capabilities.
canvascoding/canvas-notebook
把一句话需求做成带配乐和字幕的 MP4 短视频:讲解、科普、产品介绍、数据播报、知识卡片,20 到 90 秒,横屏或竖屏。只需要填一份 video.json,一条命令出片;能把实拍素材的片段剪进去,能导出 Final Cut Pro 和剪映的工程接着剪;不用视频生成模型,Windows、macOS、Linux 通用。Use this whenever the user wants a video made from a sentence, topic, text or data — "做个视频"、"生成一个短视频"、"讲解视频"、"宣传片"、"动画视频"、"make a video / explainer / short clip" — even if they give only a topic; also for cutting clips of existing footage into a video ("剪辑"、"混剪"、"把这段视频剪进去") and exporting a Final Cut Pro / 剪映 (CapCut China) project. Not for AI-generated footage.
li2092/one-prompt-video
提炼会话进展或技术方案,生成交接快照(.agent/handoff/)并输出引导 Prompt,支持当前项目交接或派生到目标目录/仓库。当用户提到“交接”、“handoff”、“生成交接文档”、“换个窗口/Agent 接着做”,或要求“把方案交接到某个目录/工作树”时使用。不适用于读取快照恢复任务(使用 dbk-pickup),也不适用于写 commit message 或代码总结。
DBinK/dbk-handoff
Orchestrator for parallel Linear Issue implementation. Analyze milestones and dependencies, then delegate implementation to sub-agents in optimal order and concurrency
usk6666/yorishiro-proxy
Voice, music and sound on Mira AI through its MCP server: text to speech with library voices and emotion tags in 70+ languages, multi-voice dialogue, music timed to the cut, a soundtrack the model writes by watching the clip, sound effects, voiceover and captions on a finished clip, transcripts, clean audio and stems. Use it for "voiceover", "narration", "text to speech", "TTS", "dialogue", "podcast", "music", "soundtrack", "jingle", "beat", "sound effect", "SFX", "captions", "subtitles", "transcript", "clean audio", "noise removal", "stems". NOT for the picture itself (mira-generate).
Global-AI-Group-Inc/content-generation-skills
Code-quality gate and coding guardrail for AI coding agents. Always invoke when you finish editing and prepare to hand control back, even if the user did not explicitly ask. Trigger on commit, push, PR, or phrases like any slop, remove slop, review my code, run aislop, or score my code. Scans with aislop, fixes what is mechanical, addresses the rest in-session in the project style, then reports what changed.
scanaislop/skills
Build and run an eval harness for an LLM agent or prompt, with scoring and a regression gate.
timurgaleev/vibestack
Independent second opinion from the Claude Code CLI: review a diff, challenge it adversarially, or consult.
timurgaleev/vibestack
Get a second opinion from the Codex CLI: diff review with a pass/fail gate, adversarial challenge, or consult.
timurgaleev/vibestack
Pair a remote agent with your browser: generate a setup key and instructions so it can connect over HTTP.
timurgaleev/vibestack
Tune which questions vibestack skills ask you: set never-ask or always-ask per question and view your profile.
timurgaleev/vibestack
Exploit validation skill for authorized environments, attack-surface review, and bounded proof-of-impact workflows.
TanKimGwan/linmas
Convene a council of AI coding agents before finalizing a plan. The agent you're talking to — whichever CLI is the lead (claude, codex, cursor, gemini, grok, opencode) — drafts a plan, presents it independently to every other agent CLI installed on the machine, each member gives ONE reply per turn, and the lead revises the plan for X turns before answering. Trigger words: council, convene the council, consult the other agents, ask the council, ask codex/cursor/gemini/grok what they think, second opinion from other agents, N turns of deliberation, deliberate before planning.
markphelps/skills
Use Hermes Agent for Hermes-owned skills, memory, connected services, messaging, browser workflows, schedules, and external automation. Prefer the installed hermes_* MCP tools; use the CLI only as a fallback.
TheBlueHouse75/hermes-action-bridge
Prioritise Confluence customers for conversion, retention, win-back or pause using lifecycle, feedback, license, usage and conversation evidence. Draft follow-ups and update the tracker within the user's authorised scope; reuse existing query skills.
ZenUml/conf-app
"뷰어로 보여줘 <경로>"·"<문서> 렌더해서 보여줘"·"볼트 뷰어 열어줘"·"knowledge viewer"· "지도로 보여줘 <경로>"·"연결 그래프 보여줘" 같은 요청에 볼트 읽기 뷰어(projects/knowledge-viewer)를 띄우고 요청한 문서를 브라우저 패널에서 연다. 서버는 launch.json 항목 knowledge-viewer(8778)로 올리고, 주소는 /v/<path>?agent=claude&src=local#<anchor>. "PR #n 보여줘 [경로]"·"PR n 리뷰 모드로 열어줘"면 src=pr:<n> 으로 그 PR 의 볼트를 연다. 뷰어에 등록된 앱을 열 때는 GET /api/apps 의 title 로 id 를 찾아 앱 화면 /apps/<id> 를 연다. 원본 문서를 고치지 않는다. private/는 로컬 기본값으로 보이고, 숨기는 것은 사용자가 시킬 때만이다.
lemoncloud-io/doki
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".
ZenUml/conf-app
Decide whether an agent session may merge a PR on ZenUml/conf-app without asking (non-destructive rule), and operate the daily auto-lane merge job (classify a diff, dry run, backtest, kill switch). Use when a PR is green and the next step is "merge or ask", when asked "can this be auto-merged", "why did the auto lane skip PR N", "run the auto-lane dry run", "自动合并", "非破坏性", or before proposing any automation that merges.
ZenUml/conf-app
Rank active ZenUML Lite tenants on two independent 0-100 scores — Opportunity (upsell candidate) and Risk (disengagement) — to decide which clients to focus on. Use whenever the user asks "which clients should we focus on", "who's a good upsell candidate", "which tenants are at risk of churning", "health score", or wants a ranked list of Lite tenants by engagement strength or fragility. Scope: Lite only, active tenants only (macro_viewed > 0 in the scoring window). For a SINGLE named tenant's paid status/profile use the `tenant` skill instead; for lifetime revenue/renewals/overdue payers use `marketplace`.
ZenUml/conf-app
List ZenUML (and other) macros on any Confluence page in render order, with their customContentId, type, title, and ADF localId — and fetch a chosen macro's stored body (DrawIO XML / Mermaid / PlantUML / ZenUML DSL / OpenAPI). Two operations, one skill. Use whenever investigating a customer page, locating which macro to inspect/reproduce, correlating "the third diagram on page X" to a specific customContentId, or extracting a stored macro source for rebuild. Triggers on "what macros are on this page", "find the macro at <URL>", "fetch the macro source", "extract macro XML", "rebuild this customer's macro", or any starting step of a customer-page investigation.
ZenUml/conf-app
Writes a handover document so another person, another agent, or a different tool can pick up multi-session work cold. Use when handing work to someone else, switching tools, or pausing work that will not resume in the same session.
ash1794/vibe-engineering
Routes to the right vibe-engineering skill for the current task and lists the full catalog. Use when the user asks which skill to use, asks what vibe-engineering can do, or is unsure how to approach a task.
ash1794/vibe-engineering
Runs a multi-phase project from an orchestrating main thread that plans, routes and verifies but does not build. Defines a few long-lived workstreams, each owning a file area end to end in its own worktree, and routes every follow-up to the owning agent instead of spawning a one-off. Covers base-SHA recording, rebase-before-commit, stale-checkout detection, and shared-machine hygiene (ports, processes, measurement noise). Use when a project spans several phases or sessions with three or more agents working at once.
ash1794/vibe-engineering
Fix the agent's own environment when skill-miner surfaces infra-class failures - broken or over-broad hooks, permission-mode denials, wrappers, sandboxing, expired CLI auth. Use when session mining shows hook errors ("No stderr output", repeated "BLOCKED" on legitimate commands), denied permissions, or environment breakage that no skill could fix. The rule is that infra failures get fixed in the environment, never worked around with skills.
getedgehq/skills
Turn your own local ChatGPT, Claude Code, and Codex conversation history into a 4:5 AI DNA helix still and 12-second film. Use when someone asks to make or share their AI DNA from their chat history.
getedgehq/skills
Build a private local "<your-name>-clone" skill that makes your AI work and sound like you: your writing voice, how you decide, judge work and report, and how you talk, learned from your own agent rules, notes and sent writing. Use when someone wants to clone themselves, make their AI think like them, or turn their working style into a reusable skill.
getedgehq/skills
Reviews the user's past Claude Code conversations from a wellbeing perspective — sentiment, tone, emotional arc, recurring patterns — and generates a supportive, science-grounded report in both Markdown and HTML. Default lookback is 48 hours across all projects. Uses recognised emotion frameworks (Plutchik, Ekman, Russell's circumplex, Pennebaker linguistic markers) and cites the science behind every observation. Learns the user's baseline tone over time so future reports flag genuine shifts, not noise. Use when the user asks for an emotional/wellbeing recap, mood check, sentiment review, or wants to understand their own ups and downs across recent work sessions.
mostafa-drz/claude-skills
Scans the current conversation for patterns worth turning into a reusable skill or memory rule — feedback you've given Claude, workflows you've walked through, corrections, best practices, recurring setups. Proposes candidates, classifies each as skill (multi-step workflow) or memory (single rule), cross-checks against existing skills + MEMORY.md to avoid duplicates, then hands off to /skill-creator (for skills) or writes the memory entry directly. Use when the conversation contains reusable knowledge you don't want to teach Claude again — "we just figured this out, capture it", "turn this into a skill", "save this workflow", "from experience to skill".
mostafa-drz/claude-skills