AI & ML

cdman28 Skill

Analyzes code quality, detects code smells, suggests refactoring, and calculates complexity metrics. Use before testing or deployment.

cdman28 Bundle

Ultra-fast codebase exploration for finding files, patterns, symbols, and dependencies. Use when you need to quickly search across large codebases.

cdman28 Skill

Automatically generates handoff documents for the next agent after completing a stage

cdman28 Bundle

Post-processing tool that removes excessive AI-generated comments. Use after code generation to make it look human-written.

cdman28 Skill

Implements server-side logic, APIs, database operations, and authentication. Use for backend code generation and API implementation.

cdman28 Skill

Creates comprehensive documentation including README, API docs, and user guides. Use after implementation for documentation tasks.

adamsilverstein Skill

Manages git worktrees using Worktrunk (wt CLI). Covers core commands (switch, list, merge, remove, step), configuration (user config at ~/.config/worktrunk/config.toml and project hooks at .config/wt.toml), hooks, LLM commit messages, parallel agents, and troubleshooting. Use for 'wt switch', 'wt list', 'wt merge', 'wt remove', 'worktree management', 'parallel agents', 'configuring hooks'.

metalagman Bundle

Use this skill to design, document, and structure AI agent skills for Gemini, Claude, and Codex. It provides architectural rules, directory standards, and writing best practices.

lylll9436 Skill

Search Google Scholar via Chrome DevTools MCP, let the user select a paper, and retrieve its BibTeX entry. 通过 Chrome DevTools MCP 在 Google Scholar 搜索论文并获取 BibTeX 引用。

dianel555 Bundle

Delegates coding/research tasks to the Google Antigravity CLI (`agy`) for external-model execution (Gemini 3.x, Claude Sonnet/Opus 4.6, GPT-OSS). Replaces the broken `collaborating-with-gemini` skill. Use when: (1) External-model delegation via Antigravity, (2) Multi-model prototyping (switch model per call), (3) Backend/logic implementation, (4) Algorithm design and optimization, (5) Bug analysis and debugging, (6) API/database code generation, (7) Code review. Triggers: "delegate to agy", "use Antigravity", "external model", "agy", "Gemini 3.5", "Claude Sonnet 4.6", "GPT-OSS". IMPORTANT: Always request unified diff patches only. Supports multi-turn sessions via SESSION_ID.

dianel555 Bundle

Deterministic Software Graph analysis via Ontoly CLI and MCP. Use when: (1) Codebase architecture, dependency, route, service, module, configuration, or impact questions need graph evidence, (2) A repository should be analyzed before source search, (3) You need a persistent SoftwareGraph.json for validation, MCP, or agent workflows. Triggers: "build software graph", "trace route", "impact analysis", "architecture summary", "dependency graph", "what uses this", "Ontoly".

dianel555 Bundle

Semantic codebase search, code indexing, and prompt enhancement via standalone CLI. Use when: (1) Semantic code search with natural language queries, (2) Code indexing for remote codebase retrieval, (3) Prompt enhancement with codebase context, (4) Before grep/find/glob operations for better accuracy, (5) Complex requirements clarification, (6) Large codebase navigation. Triggers: "search context", "enhance prompt", "find code that", "index project", "clarify requirements". IMPORTANT: Always use ace-tool BEFORE grep/find/glob for semantic-level code location.

peterkrueck Skill

Review uncommitted code changes using parallel Claude sub-agents (Bug Hunter, Rules Auditor, optional Architect). The invoking agent triages the diff by file path into impacted modules and risk surfaces, then spawns reviewers scaled to the change. Each reviewer self-primes via /prime, verifies any API/library claim via Context7 (mandatory — unverified claims are auto-discarded), and reports an intent verdict against progress.md before its findings. Catches bugs, security issues, CLAUDE.md compliance, and test-coverage gaps. Skip for trivial typos/formatting. Use after substantive implementation work, or when the Stop hook requests it. Also invocable manually with /review-work.

peterkrueck Skill

Get a second opinion from OpenAI's Codex CLI running locally. Use this skill when in Plan Mode for large or critical tasks, when stuck on a debugging dead end, when facing architecture trade-offs, for subtle edge cases in code review, or any situation where an independent perspective would add value. Also use when the user explicitly asks for a "second opinion", "another perspective", "cross-check this", "ask Codex", or "ask GPT". This is the DEFAULT second-opinion engine — Codex runs a completely different model architecture from Claude, so it catches blind spots Claude shares with itself. For a Gemini second opinion specifically, the user says "ask Gemini" (separate second-opinion-gemini skill); "ask both" runs this skill and that one, then synthesizes.

peterkrueck Bundle

Get a second opinion from Google's Gemini Pro via the locally installed Gemini CLI (defaults to gemini-3.1-pro-preview; override with the CLAUDE_SECOND_OPINION_MODEL env var). This is the explicit / fallback engine — invoke ONLY when the user explicitly says "ask Gemini", "Gemini's take", "what does Gemini think", or "ask both" (run alongside the default engine and synthesize). Do NOT trigger on a generic "second opinion", "another perspective", or "cross-check this" — those route to the default `second-opinion` skill. Reserve this for when the user specifically wants Gemini, or as a fallback when the default engine is unavailable. Reports unavailability rather than falling back to a weaker model.

sparkling Bundle

Design, implement, and manage knowledge organization systems with SKOS (Simple Knowledge Organization System). Covers concept schemes, taxonomies, thesauri, controlled vocabularies, semantic relations, mapping, SKOS-XL labels, AI/LLM integration patterns, and SHACL validation. Informed by Kurt Cagle's ontologist perspective and W3C specifications.

sparkling Bundle

Design, implement, and validate RDF data with SHACL (Shapes Constraint Language). Covers node shapes, property shapes, constraint components, validation reports, SHACL-SPARQL integration, AI/LLM patterns, UI generation, and taxonomy integration. Informed by Kurt Cagle's ontologist perspective and W3C specifications.

sparkling Bundle

Write, analyze, and optimize SPARQL 1.1 queries for knowledge graphs. Covers RDF, OWL, SHACL, Turtle serialization, and AI/LLM integration patterns. Informed by Kurt Cagle's ontologist perspective.

sparkling Bundle

Convene a dialectic expert-panel review (the Linked Data Council Hive) on an ontology/ADR/ODR proposition or a set of outstanding questions, then produce a session record. Use when a modelling decision has a credible split, a contested mapping or identity-criterion question needs adjudicating, or a precedent needs recording. Spawns a SCOPED panel via the Agent tool (Queen + Devil's Advocate + only the relevant experts), collects per-question verdicts, writes the synthesis, and routes dispositions to the ODRs/ADRs.

dianel555 Bundle

Delegates coding tasks from Codex to local Claude Code in print mode while preserving Claude's normal runtime customizations by default. Use when: (1) You want Codex to call Claude Code locally, (2) You need Claude-side skills, plugins, MCP servers, custom commands, CLAUDE.md rules, or workspace settings to stay active, (3) You want resumable Claude sessions from Codex via SESSION_ID, (4) You need thin `claude mcp` / `claude plugin` passthrough from the same bridge.

dianel555 Bundle

Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.

microsoft Skill

Agent for validating Aspire documentation against actual behavior. Use when auditing documentation accuracy, testing examples, or identifying discrepancies between documentation and implementation.

hanhuark Bundle

Iterative manuscript improvement workflow where a reviewer agent critiques, an author agent revises, a verifier checks the revision, and the loop repeats until acceptance or a human-pause condition is reached. Use for virtual peer review, reviewer-author revision loops, rebuttal preparation, resubmission polishing, journal paper improvement, response-to-reviewers drafting, and deciding when additional data, experiments, theory, modeling, or author judgment is required before further revision.

dianel555 Bundle

Self-evolution workflow for the agent. Before substantive work, recall past outcomes from evolution memory; while editing, detect improvement signals; at task end, record the outcome; when reusable, distill or search the EvoMap network for proven genes/capsules. Use when the user starts non-trivial work (a feature, a fix, a refactor) or asks the agent to "evolve", "learn from this", or "remember how this went".

dianel555 Bundle

Crawl GitHub trending repositories, analyze with LLM for Chinese insights, categorize by themes, compute diffs against history, and generate Markdown reports. Default brief mode stops at trend analysis; optional detailed mode appends per-project analysis. Supports incremental gap-filling and selective re-analysis with caching.

data-wise Skill

This skill should be used when the user asks for "email help", "himalaya help", "email commands", "what can you do with email", "email features", "how do I use email", "what email tools are available", "show email capabilities", or wants to discover available email capabilities. Help hub for browsing all tools, prompts, skills, and workflows.

data-wise Skill

This skill should be used when the user asks to "check email", "inbox", "read email", "my emails", "any new messages", "what's in my email", "show me my mail", "unread emails", "check messages", "what emails do I have", "show my inbox", or wants to see what's new in their inbox. Lists envelopes from the default inbox via himalaya CLI.

data-wise Skill

This skill should be used when the user asks to "reply to email", "respond to email", "draft reply", "email reply", "answer that email", "get back to them", "write back", "respond to that", "reply to that message", or wants to respond to a specific message. Drafts replies with safety confirmation that never auto-sends.

data-wise Skill

This skill should be used when the user asks for "email config", "email setup", "configure email", "himalaya setup", "setup email", "set up email", "change email account", "which email account", "add email account", "switch email account", or needs help installing and configuring himalaya. Interactive setup wizard that checks installation, configures accounts, and tests connectivity.

data-wise Skill

This skill should be used when the user asks for "email digest", "daily digest", "email summary", "email roundup", "summarize my inbox", "what did I miss", "summary of recent emails", or wants a quick summary of recent messages. Generates a markdown digest grouped by priority. For a full morning briefing with calendar events and action items, use /himalaya:morning instead.

data-wise Skill

This skill should be used when the user asks to "export email", "save email", "export to markdown", "copy to clipboard", "save this email", "export as markdown", "save for later", "clip this email", "archive this to notes", or wants to preserve an email as structured markdown with YAML frontmatter and optionally copy to clipboard. Chains export_to_markdown and copy_to_clipboard.

data-wise Skill

This skill should be used when the user asks to "manage email", "bulk email", "move emails", "flag emails", "archive emails", "unflag emails", "move these emails", "flag this", "archive that", "mark as read", "star this email", "clean up my inbox", or wants to perform batch operations. Handles flag, unflag, move, and archive for multiple emails at once.

data-wise Skill

This skill should be used when the user asks to "search email", "find email", "look for email", "email from", "email about", "did I get an email about", "find message from", "look for that email from", "any emails about", "search my inbox for", or wants to locate specific messages. Searches by keyword, sender, flags, or date using himalaya filter syntax.

data-wise Skill

This skill should be used when the user asks to "triage email", "classify email", "sort email", "go through my inbox", "what needs attention", "prioritize my email", "sort my messages", "which emails are important", "what should I respond to", or wants to prioritize their inbox. Classifies emails as actionable, informational, or skip using MCP prompts.

data-wise Skill

This skill should be used when the user asks to "compose email", "write email", "send email to", "new email", "send a message to", "email someone", "write to", "new message", "draft an email", "message someone", or wants to draft and send a new message. Composes emails with a two-phase safety gate that never auto-sends.

transloadit Skill

One-off image generation (prompt -> image file) using Transloadit via the `transloadit` CLI. Prefer `image generate` for text-only and input-guided generation, and use `--output` when you need a deterministic path.