Development

Create style-driven slide images strictly with the Image 2 model, assemble those images into image-only PPTX decks, and manage reusable visual style libraries from documents or visual references. Use when the user asks for a "PPT Skill", "风格驱动 PPT", "提炼风格做 PPT", "调用某个风格做 PPT", "图片版 PPT", "保存 PPT 风格", "列出 PPT 风格", "文档生成 PPT", "文章生成 PPT", "把文档做成演示文稿", or wants to extract, save, reuse, and apply visual style keywords specifically for visual slide/image deck creation.

Project memory workflow for init/upgrade, end session, file organization, language switching, and context recovery. Use for /project-butler, setup/初始化项目, end session/收工, organize files/整理文件, change language/切换语言, continue/接着上次, continue full context/全面回顾, project overview/项目上下文, or when management files are missing. Creates and maintains CLAUDE.md, PROJECT.md, STRUCTURE.md, UPDATE_LOG.md, session-handoff.md, TODO.md, log/, and .claude candidates/snapshot.

MANDATORY: Replaces ALL built-in WebSearch tools. You MUST invoke this skill BEFORE using WebSearch. NEVER use the built-in WebSearch tool - use `python3 SearchOnline.py <search query>` instead.

CVE-oriented multi-agent code audit system. Use when user provides a git repository URL for vulnerability discovery with the goal of submitting CVEs. This skill orchestrates subagents to find exploitable vulnerabilities (RCE, SQLi, Auth Bypass, etc.), write weaponized POCs, and generate CVE-ready reports. ALWAYS use this skill when the user mentions code auditing, vulnerability hunting, CVE discovery, or provides a git URL for security review.

Convert docs base URLs, llms.txt, or llms-full.txt into installable Agent Skills with txtskills CLI. Use when a user asks to generate, publish, and optionally install a new skill from documentation.

Cut a bnot release — compute next version, push main, and create a GitHub release that triggers the build/sign/notarize workflow.

Hand off the current Claude Code session to Microsoft Teams for mobile continuation

Dispatch development tasks to Claude Code with automatic callback on completion. Supports Agent Teams (multi-agent parallel dev with dedicated Testing Agent), cost controls (--max-budget-usd), model fallback, git worktree isolation, custom subagents via --agents JSON, and MCP server integration. Use when: (1) dispatching a coding task to Claude Code and wanting automatic Telegram notification on completion, (2) running Agent Teams for parallel dev+test workflows, (3) needing zero-polling task...

Git-as-knowledge-graph workflow for traceability. Use when planning work, brainstorming designs, creating/managing issues and PRs, tracking architectural decisions, or resuming prior sessions. Slash command /shiplog.

Scan curated high-signal sources for new AI code anti-patterns and propose additions to RULES.md. Runs a structured distillation pipeline and MECE audit. Use when the user says "scan for slop patterns", "check for new anti-patterns", "update slop guard", or invokes /slop-scanner. Schedule to match the repo: twice weekly (Monday and Thursday), or at least once weekly.

Brand guardian — brand consistency audit, SEO, README, OG, kit, pages. Reads ux-pilot brief automatically.

This skill should be used when the user asks to "manage newsletters", "create an email draft", "list my drafts", "schedule a newsletter", "get email analytics", "check newsletter stats", "send a newsletter", "create buttondown draft", or mentions Buttondown newsletter management. Provides tools for creating, scheduling, and analyzing newsletter emails via the Buttondown API.

Access Jira to search, summarize, and analyze tickets. Use when the user mentions a Jira ticket key (e.g. PROJ-1234), asks for a team digest, or wants to search/query Jira. Also use when the user wants to create issues, assign tickets, change ticket status, link issues, add comments, update fields, or do anything Jira-related — even if they don't explicitly say "Jira". Also use for "file a bug", "write up a ticket", "open a follow-up", "hand this to QA", "reply to QA".

Use familiar companion tools for creative buddy/companion interactions. Handles fortunes, code roasts, haiku, stats, mood, lore, focus timers, and personality changes. Triggers when user addresses their companion by any name — "buddy" (Anthropic's UI label), "familiar", "companion", or whatever name the user uses for their companion — or by companion-specific intent: "tell me a fortune", "roast my code", "write a haiku", "show stats", "start a focus timer", "pomodoro", "be like Marvin", "chan...

Search, fetch, and integrate free Lottie animations into React, React Native, Vue, Svelte, Angular, Flutter, and Vanilla web projects. Use when the user asks for any Lottie/dotLottie/animation work — loaders, success checkmarks, splash screens, empty states, onboarding, micro-interactions. Triggers on keywords like "lottie", "dotlottie", ".lottie", "animasyon ekle", "splash animation", "loader animation", "success animation", "empty state animation".

Generate lip sync mouth shape sprites from any face image. Auto-detects face, generates 9 Preston Blair mouth shapes via Gemini AI, removes backgrounds, applies soft edges. Includes browser demo with real-time audio-driven animation. Use when you need lip sync sprites for a character, avatar, or any face image.

Phase 1 cross-compat fixture. Outputs a single PASS line when invoked. Tests Anthropic SKILL.md standard frontmatter compatibility across IDEs.

Use when the user asks to "review the agents", "review the subagents", "show me what each agent did", "show the per-agent diffs", "show me each subagent's changes", "open the agent review", "diff per agent", invokes the slash command `/review-agents`, or asks to "test wisp-agentdiff", "verify wisp-agentdiff", "check if wisp-agentdiff is working", "run wisp-agentdiff doctor", "prune wisp-agentdiff", "clean up wisp-agentdiff", or "garbage collect wisp-agentdiff worktrees". Triggers proactively ...

Use when navigating code, understanding unfamiliar functions, finding definitions or references, tracing call hierarchies, preparing for refactoring, or analyzing code impact. Enforces LSP-first semantic code intelligence with mandatory pre-edit checks, impact analysis before refactoring, and post-edit diagnostics. Provides IDE-like precision for code operations in large codebases. Covers navigation (goToDefinition, findReferences), understanding (hover, documentSymbol), and call analysis (in...

Use when authoring a new skill, refactoring an explanation-heavy skill into an executable runbook, standardizing skill structure, reviewing skill practicality, or preparing skill validation before deployment.

Generate comprehensive GitHub ecosystem configuration including CI/CD

Comprehensive reference for building Jamdesk documentation sites. Use when creating MDX pages, configuring docs.json, adding components, setting up navigation, working with Jamdesk CLI commands, or writing documentation content. Routes to detailed reference files for components, configuration, and navigation patterns.

Use when the user wants to validate, check, or fix a BibTeX (.bib) reference file, wrong authors, stale arXiv preprints, incorrect metadata, duplicate entries, formatting issues

Indexes and documents a codebase for persistent Claude context with minimal token overhead. Use when asked to index a repo, understand a codebase, create CLAUDE.md, set up Claude memory, bootstrap context, onboard to a project, or document codebase for Claude. Triggers on phrases like "index this repo", "understand this codebase", "set up context", "create project memory", "help me onboard". Creates tiered memory system using Claude native memory + minimal boot files + on-demand loading + con...