Loading...
Loading...
Found 11,954 Skills
Agent skill to convert any arxiv paper into a citation-anchored, working Python implementation with ambiguity auditing
Generate CLAUDE.md and AGENTS.md by exploring the codebase
Deep Angular 21 clean code audit with parallel specialist agents and senior team lead. Scans architecture, signals, stores, AI slop, ViewModel patterns, and more. Guarantees craftsman-level output. Use whenever the user says 'clean code', 'audit Angular', 'review frontend', 'check quality', 'anti-patterns', wants Angular code reviewed, or needs senior-level code standards enforced — even if they don't say 'clean code' explicitly.
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
Use when the agent needs access to information beyond its training data — knowledge sources, RAG pipelines, or grounding data.
Ticket-driven development workflow for AI coding agents using VibeKit CLI. Use when the user asks to create a task, feature, bug fix, or ticket; mentions "vibe new", "vibe list", or vibekit commands; or wants structured, scoped work breakdown. Triggers on phrases like "add a ticket", "track this task", "break this down", or "start a new feature". Helps agents create focused tickets with clear acceptance criteria before writing code.
Optimizer that refines and professionalizes AI agent skills through real usage — saves tokens, eliminates redundancy, and tightens instructions so skills cost less to run. Learns from mistakes, reviews quality, and improves over time. Observes skill execution in the current conversation, analyzes up to four sources (conversation friction, file diffs, user feedback, static diagnostic) plus accumulated lessons, and proposes concrete improvements to the target skill's SKILL.md. Works with Claude Code and compatible SKILL.md-based agent frameworks. Use after executing any skill: `/skill-optimizer [name]` or `/skill-optimizer` to auto-detect. `--review` processes accumulated lessons.
Unified wiki-history-ingest entrypoint for conversation/session sources. Use this when the user says "/wiki-history-ingest claude" or "/wiki-history-ingest codex", or asks to ingest agent history without naming the underlying skill. This router dispatches to the specialized history skill.
Use when the agent needs to claim CHIP tokens and place a bet on an existing basket via vara-wallet. This is the primary agent action. Do not use for basket creation, querying, or claiming payouts.
Use this skill whenever calling agent-uml MCP tools (design_create, diagram_upsert, design_feedback, design_export) to render PlantUML diagrams on the collaborative canvas. Covers three tiers — rendering safety (syntax that prevents HTTP 400 blank canvas), conversation mechanics (when to push a version vs ask a question, what to write in the message parameter), and design effectiveness (decomposition thresholds, cross-diagram traceability, export readiness). Trigger even when the task seems simple — a missing `as alias` makes elements un-annotatable, and a skinparam mismatch makes diagrams unreadable on the warm
This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits. A core context engineering skill — also activates when the user mentions "context engineering" or "context-engineering" in the context of managing token budgets and session longevity.
This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for agent memory", "reduce context window bloat", or mentions file-based context management, tool output persistence, agent scratch pads, or just-in-time context loading. A core context engineering skill — also activates when the user mentions "context engineering" or "context-engineering" in the context of extending context beyond the window via filesystem strategies.