Top Agent Skills

Atlas turns your STATED NEED into a real systems atlas by SCANNING your actual sources (Azure via `az`, git repos, local dirs) and process/data mining them, THEN enriching against the Atlas knowledge graph. Use this skill when asked to inventory/map your real systems, scan your cloud + repos + directories, mine the real processes or data they contain, or collect their real constraints/gotchas. (atlas, scan my systems, inventory our azure account, map my repos, real systems atlas, process mining, data mining, collect nuances, system discovery)

Analyze processes, identify workflows, define boundaries and scope, and map process requirements for specialization creation.

Direct Figma API interactions for design asset management. Fetch files and components, extract design tokens, export images, manage comments, and access version history.

Marketing skills router: match marketing intent to a sub-skill, then Read its Entry file under skills/<name>/ (e.g. ads/ads.md). Covers CRO, copywriting, SEO/AEO, paid ads, ad creative, analytics, email/SMS, pricing, launches, video/image generation, and growth loops. Use for any marketing request — campaigns, content, optimization, measurement.

Run STORM phase 3 — per-section article writing. This skill should be used when the user asks to "write the article sections", "draft the storm article", or invokes /storm:write. Writes each outline section in parallel with inline citations grounded in the research sources.

Run STORM phase 2 — outline generation. This skill should be used when the user asks to "generate an outline for a storm article", "draft a wikipedia-style outline", or invokes /storm:outline. Produces a draft outline from parametric knowledge then refines it using the research information table.

Begins a hotfix for a production issue using git-flow. This skill should be used when the user asks to "start a hotfix", "create hotfix branch", "fix a critical bug", "git flow hotfix start", or wants to begin a hotfix. Accepts either an explicit version or a natural-language description of the fix.

Starts working on a new feature branch using git-flow. This skill should be used when the user asks to "start a feature", "create feature branch", "begin new feature", "git flow feature start", or wants to start a new feature. Accepts either a branch name or a natural-language description.

Finalizes a release and merges it into main and develop with a tag using git-flow, then prunes stale branches and worktrees. This skill should be used when the user asks to "finish a release", "merge release branch", "complete release", "git flow release finish", or wants to finalize a release.

Reviews SwiftUI code for best practices on modern APIs, maintainability, and performance. This skill should be used when the user asks to review SwiftUI code, check for deprecated iOS/macOS APIs, validate data flow patterns, or audit accessibility compliance in Swift projects.

Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".

Generate Image (gemini / openai backends)

This skill should be used when the user asks to "validate a plugin", "optimize plugin", "check plugin quality", "review plugin structure", or "run plugin optimizer".

This skill should be used when the user asks to "reflect on skills from memory", "audit marketplace skills against memory", "从记忆中检查 skills 的问题", "反思并修改 skill", "apply memory feedback to skills", or wants to turn accumulated memory feedback about this marketplace's skills into concrete skill fixes. Reads the project's persistent memory, re-verifies each known skill problem against current code, then fixes the skill or corrects the stale memory.

Cut a Han release: update CHANGELOG.md with the changes since the last release, bump every plugin that changed, tag every plugin as {plugin-name}--v{version} so a version-constrained dependency can resolve, and publish a GitHub release whose notes attribute every merged pull request to its author, credit every closed issue to the person who opened it, the people who contributed to it, and the people who worked on the fix, and link back to the full changelog for that version. Han ships as a parent meta-plugin (`han`) plus child plugins (`han-core`, `han-github`, `han-reporting`, and any future `han-*` extension); the skill versions each plugin independently and tags each one independently, with the release attaching to the parent's tag. Use when releasing, cutting a release, shipping a new Han version, publishing release notes, or tagging a version. Reads each plugin's target version from its plugin.json; when a plugin has not been bumped past the latest tag yet, it proposes a semantic-versioning bump and conf

Turn a work-items.md file (produced by /plan-work-items) into Linear issues, one per slice, in a single target Linear team. Use when you want to publish work items as Linear issues, create implementation tickets to track in Linear, or push a broken-down plan into a Linear team. Requires a configured Linear MCP server and a target team. Reads the team's real workflow states, labels, Projects, and members and resolves every option against them before creating anything; defaults each issue to the team's initial state, unassigned, uncategorized, with no parent or Project unless you ask. Links within-file `Depends on` relationships as native Linear "blocked by" relations and annotates the source file so re-runs resume cleanly. Does not produce the work-items file itself — use plan-work-items first. Does not post to Jira — use work-items-to-jira. Does not post to GitHub — use work-items-to-issues.

Builds a feature implementation plan from an existing feature specification (or equivalent context) through a facilitated team conversation. Use when the user wants to plan how to implement, build, deliver, or ship a feature that has already been specified. Does not specify what the feature should do — use plan-a-feature first. Does not design the contract for an interface — use design-an-api. Does not refine or stress-test an already-written plan — use iterative-plan-review. Runs its resolution rounds to completion and holds its questions until after they finish; to review each round as it lands, use pairing.

Surfaces Han's shared standard for explaining technical work to a reader who will not implement it into the calling skill's own context, so the caller writes its escalations, confirmation turns, and stops as a concrete outcome the reader could observe rather than as a mechanism. Use when a skill is about to ask a person a question, stop for an input, or explain a technical consequence to someone who will not open the code. Governs what a run says to a person in a turn, where readability-guidance governs the shape of a written deliverable. Runs in the caller's context and hands control straight back; it does not produce a deliverable of its own, rewrite anything, or judge the caller's work. Carries guidance only and adds no self-check step.

OI-3 spike harness — heavy consumer skill, INLINE arm. Builds an incident post-mortem and sources the readability standard mid-workflow via an inline (non-forked) guidance skill. Use only when explicitly invoked by the spike harness with a TRIAL_ID and data path.

Readability Review

Verify a Jira issue against the current repository state, then post a Jira comment with a PASS, PARTIAL, FAIL, or BLOCKED verdict. Works in two modes: (a) feature-branch mode, comparing a checked-out branch to its base ref; or (b) main/trunk mode, verifying that an issue is already implemented on the current default branch (typical for stories that have already merged). Use when a user asks whether a branch or merged change completes a Jira ticket, or needs a Jira-visible verification comment.

Provide the shared fan-out engine used by provider-specific Jira and GitHub batch presets to enqueue child workflows with inherited runtime and stable evidence.

Implement bounded remaining work for an issue-driven repository change after an authoritative verifier reports concrete gaps. Use when a workflow supplies an issue brief or assessment plus materialized gate-result and remaining-work evidence, and the existing candidate must be corrected without creating a MoonSpec feature packet.

Update Jira issues such as tasks, stories, bugs, or subtasks through MoonMind's trusted Jira tool surface. Use when a user asks to edit Jira fields, move workflow status, update descriptions, or publish completion/status summaries back to any Jira issue type.

Review an open GitHub issue for a selected repository against the current codebase, then either close it as already implemented with an evidence comment, label it needs clarification with an explanatory comment, or create a fleshed-out Jira story in the requested board/project when the remaining work is clear. Use when triaging GitHub issues into Jira backlog work or closing stale implemented GitHub issues.

Queue additional MoonMind workflows from inside an existing workflow by submitting explicit `/api/executions` requests, applying stable idempotency, verifying every returned `workflowId` with the execution API, and writing a durable queue summary. Use when a workflow needs to fan out follow-up MoonMind executions, create child implementation workflows, replace local task-list or manifest-only handoffs, or prove that downstream workflows were actually queued.

Lip-sync a face to a specific audio track on RunComfy via the `runcomfy` CLI. Routes across ByteDance OmniHuman (audio-driven full-body avatar from a portrait + audio), Sync Labs sync v2 / Pro (state-of-the-art mouth sync onto a video), Kling lipsync (audio-to- video and text-to-video with synced speech), and Creatify lipsync. The skill picks the right endpoint for the user's actual intent — portrait still + audio (avatar-style), source video + audio (mouth- swap on existing footage), or generate-and-sync from a script. Triggers on "lip sync", "lipsync", "make this video speak", "match audio to mouth", "dub video", "sync lips to voice", "Sync Labs", "voiceover sync", or any explicit ask to drive a face's mouth from an audio track.

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into `${CODEX_HOME:-$HOME/.codex}/pets/<name>/` and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as `runcomfy run openai/gpt-image-2/edit` to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no `$imagegen`, no OPENAI_API_KEY required, only RUNCOMFY_TOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

Generate and edit images with OpenAI GPT Image 2 (ChatGPT Images 2.0) on RunComfy. Documents GPT Image 2's strengths (embedded text, logos, multilingual typography, instruction precision), its 3 fixed sizes, edit-with-preservation language, and when to route to a sibling (Flux 2 / Nano Banana Pro / Seedream) instead. Calls `runcomfy run openai/gpt-image-2/text-to-image` or `/edit` through the local RunComfy CLI. Triggers on "gpt image 2", "gpt-image-2", "ChatGPT Images 2", "image 2", or any explicit ask to generate or edit with this model.

Create AI avatar, talking-head, and lip-sync videos on RunComfy via the `runcomfy` CLI. Routes across ByteDance OmniHuman (audio-driven full-body avatar), Wan-AI Wan 2-7 (audio-driven mouth sync via `audio_url` on a portrait), HappyHorse 1.0 (Arena #1 t2v / i2v with in-pass audio), and Seedance v2 Pro (multi-modal cinematic with reference audio + reference subject). Picks the right model for the user's actual intent — UGC voiceover, virtual presenter, dubbed product demo, lip-synced character, dialog scene — and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "talking head", "lip sync", "avatar video", "make X speak", "audio to video", "audio driven avatar", "virtual presenter", "AI spokesperson", "dubbed video", "UGC avatar", "HeyGen alternative", "Synthesia alternative", "digital human", "make this portrait talk", "video from voiceover", or any explicit ask to put words in a face.

Image outpainting on RunComfy via the `runcomfy` CLI — extend a still beyond its original canvas, fill in what the camera didn't capture, change aspect ratio (square → 16:9, portrait → landscape) while preserving the original content. Routes across Nano Banana 2 Edit (default, spatial-language driven), GPT Image 2 Edit (multi-ref with reference-style matching), FLUX Kontext Pro (single-shot maximum-preservation), and the brand edit endpoints (Seedream / Dreamina / Qwen / FLUX 2). Picks the right route based on whether the outpaint is prose-driven, reference-driven, or brand-locked. Triggers on "outpaint", "outpainting", "extend image canvas", "expand the image", "fill in around the photo", "uncrop", "change aspect ratio", "extend frame", "wide-screen from square", or any explicit ask to add canvas around an existing still.

Personal knowledge base powered by Ensue for capturing and retrieving understanding. Use when user wants to save knowledge, recall what they know, manage their toolbox, or build on past learnings. Triggers on "save this", "remember", "what do I know about", "add to toolbox", "my notes on", "store this concept".

Short slash command wrapper for Claude relay sessions. Use when the user wants concise /cc commands like /cc projects, /cc on <project>, /cc tail, /cc off, or /cc <message> to continue talking to Claude Code in the current project session.

Use the GitHub CLI (gh) to perform core GitHub operations: auth status, repo create/clone/fork, issues, pull requests, releases, and basic repo management. Trigger for requests to use gh, manage GitHub repos, PRs, or issues from the CLI.

Agents can sign plugins, rotate credentials without losing identity, and publicly attest to behavior.

根据「会议纪要」任务细化的操作流程与使用说明，支持步骤拆解与最佳实践。

Paid acquisition strategy, budget allocation, and avoiding common advertising mistakes across platforms

Guide art creation, technique development, and appreciation with practical, medium-specific advice.

Sell to AI agents with machine-readable products, agent-optimized APIs, structured pricing, and discovery strategies for the agentic economy.

Box API integration with managed OAuth. Manage files, folders, collaborations, and cloud storage. Use this skill when users want to upload, download, share, or organize files and folders in Box. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Requires network access and valid Maton API key.

Be the CFO with financial planning, cash management, fundraising, capital allocation, and strategic financial leadership.

Be the COO with process design, organizational scaling, cross-functional execution, and operational excellence.

Optimize conversion rates with funnel analysis, A/B testing, statistical significance, and compliance-safe experiments.

Be the CTO with technical strategy, architecture decisions, team scaling, hiring, tech debt management, and engineering leadership.

Task tracking for async/multi-step work. Use dex to create, track, and complete tasks that span multiple sessions or require coordination (e.g., coding agent dispatches, PR reviews, background jobs). Tasks stored as JSON files in .dex/tasks/.

Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.

Full version control coverage with essential commands, team workflows, branching strategies, and recovery techniques.

Windows GUI automation toolkit for global hotkeys and window management. Use when users need to register global hotkeys, find/control windows, automate GUI operations, or perform Windows desktop automation. Requires Windows OS with pywin32, pyuserinput, and pyautogui dependencies.

Execution discipline with agency, instinct detection, critical safety rules, trust layer, and error resilience. v2.7 adds timeout handling, checkpointing, and decision logging.

Lip-sync a face to a specific audio track on RunComfy via the `runcomfy` CLI. Routes across ByteDance OmniHuman (audio-driven full-body avatar from a portrait + audio), Sync Labs sync v2 / Pro (state-of-the-art mouth sync onto a video), Kling lipsync (audio-to- video and text-to-video with synced speech), and Creatify lipsync. The skill picks the right endpoint for the user's actual intent — portrait still + audio (avatar-style), source video + audio (mouth- swap on existing footage), or generate-and-sync from a script. Triggers on "lip sync", "lipsync", "make this video speak", "match audio to mouth", "dub video", "sync lips to voice", "Sync Labs", "voiceover sync", or any explicit ask to drive a face's mouth from an audio track.

Swap a face / character into video or images on RunComfy via the `runcomfy` CLI. Routes across community Wan 2-2 Animate (audio-driven character animation + identity swap), GPT Image 2 Edit (single-shot precise face swap on still images via reference composition), Nano Banana Edit (batch identity-preserving swap), Flux Kontext (single-ref high-fidelity local face edit), and Kling 2-6 Motion Control Pro (transfer motion from one performance onto a target character). Picks the right model for the user's actual intent — single still vs video, full character vs face only, dialog scene vs silent motion. Triggers on "face swap", "swap face", "deepfake", "face replacement", "character swap", "head swap", "put X's face on Y", "make this video star X", "replace the actor in this video", "swap the character in the photo", "deepfake video", "ReActor alternative", or any explicit ask to substitute one identity for another.

Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy. Documents Seedance 2.0 Pro's strengths (multi-modal references — up to 9 images, 3 videos, 3 audio — synchronized in-pass audio with natural lip-sync, cinematic motion refinement), the 4–15s duration schema, and when to route to HappyHorse 1.0 / Wan 2.7 / Kling instead. Calls `runcomfy run bytedance/seedance-v2/pro` through the local RunComfy CLI. Triggers on "seedance", "seedance 2", "seedance v2", "seedance pro", "bytedance video", or any explicit ask to generate video with this model.

Generate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Nano Banana 2's strengths (rapid iteration, in-image typography rendering, predictable framing, optional web-grounded context), the resolution-tier pricing, the safety-tolerance dial, and when to route to Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream instead. Calls `runcomfy run google/nano-banana-2/text-to-image` through the local RunComfy CLI. Triggers on "nano banana", "nano-banana-2", "nano banana 2", "google image gen", "gemini image", or any explicit ask to generate with this model.

Pose-conditioned generation on RunComfy via the `runcomfy` CLI. Routes across Kling 2-6 Motion Control Pro / Standard (transfer the motion / blocking of a reference video onto a target character), community Wan 2-2 Animate (audio-driven character animation with pose conditioning), and Z-Image Turbo ControlNet LoRA (pose-conditioned image generation from an OpenPose / DWPose / canny / depth control image). Picks the right route based on video vs still and stylized vs photoreal. Triggers on "controlnet", "control net", "pose control", "openpose", "DWPose", "transfer pose", "motion control", "pose driven", "character pose", "depth control", "canny edge", "use this pose", or any explicit ask to condition generation on a pose / skeleton / motion / depth / canny reference.

Video outpainting on RunComfy via the `runcomfy` CLI — extend the spatial canvas of a video, change aspect ratio (9:16 vertical to 16:9 horizontal or vice versa), add environment beyond the original frame while preserving the central action. Routes prompt-shaped spatial extension through Wan 2-7 edit-video and points the agent at dedicated ComfyUI outpaint workflows when seam quality matters for hero delivery. Triggers on "video outpaint", "video outpainting", "extend video canvas", "expand video frame", "uncrop video", "aspect ratio change", "vertical to horizontal video", "16:9 from 9:16", "TikTok to YouTube", or any explicit ask to extend a video spatially beyond its original frame.

WP-CLI-first principle — use WP-CLI instead of generating PHP code whenever possible, with command reference, ACF seeding patterns, and environment-aware execution

Analyze PyTorch profiler and vLLM trace files with Perfetto SQL evidence. Use when working with torch profiler traces, merged_trace files, vLLM profiling logs, Perfetto trace analysis, GPU kernel hotspots, synchronization waits, rank imbalance, prefill/decode bottlenecks, or optimization reports.

Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.

Expert UI designer specializing in component creation, layout systems, and visual design implementation. Masters modern design patterns, responsive layouts, and design-to-code workflows. Use PROACTIVELY when building UI components, designing layouts, creating mockups, or implementing visual designs.

Master API documentation with OpenAPI 3.1, AI-powered tools, and modern developer experience practices. Create interactive docs, generate SDKs, and build comprehensive developer portals. Use PROACTIVELY for API documentation or developer portal creation.