Loading...
Loading...
Found 11,836 Skills
Browser automation CLI for AI agents. Use for website interaction, form automation, screenshots, scraping, and web app verification. Prefer snapshot refs (@e1, @e2) for deterministic actions.
Developer machine tool for replicating plugin source code between local project repositories. Use when you want to push plugin updates from agent-plugins-skills to a consumer project, or pull the latest plugins into a consumer project from this central repo. Works with explicit --source and --dest paths; supports additive-update (default), --clean (also removes deleted files), --link (symlink), and --dry-run modes.
Bridge plugin capabilities (commands, skills, agents, hooks, MCP) to specific agent environments (Claude Code, GitHub Copilot, Gemini, Antigravity). Use this skill when converting or installing a plugin to a target runtime.
CRITICAL: Use for writing and editing agent-spec .spec files. Triggers on: write spec, create spec, edit spec, new spec, spec authoring, task contract, .spec file, BDD scenario, acceptance criteria, completion criteria, test selector, boundary, constraint, intent, decision, out of scope, "how to write a spec", "spec format", "spec syntax", "contract quality", 写 spec, 创建规格, 编辑合约, 任务合约, 验收标准, 完成条件, BDD 场景, 测试选择器, 约束, 意图, 决策, 边界, 排除范围, "怎么写 spec", "spec 格式", "spec 语法", "合约质量"
Structured session analysis and project instruction refinement using a five-type intervention taxonomy (Correction, Repetition, Role Redirect, Frustration Escalation, Workaround) with severity scoring to categorize process gaps. Refines project instructions (CLAUDE.md, AGENTS.md, .team/coordinator-instructions.md) with structural (not advisory) language, maintains WORKING_STATE.md for crash recovery (read-first-after-any- interruption protocol), and implements a self-reminder protocol (re-read constraints every 5-10 messages to prevent role drift). Includes advisory- to-structural promotion pattern for recurring gaps. Activate after milestones, repeated user corrections, session restarts, crash recovery, every 5 completed tasks, or on user request. Triggers on: "reflect on this session", "why do I keep correcting you", "update project instructions", "update working state", "session retrospective", "crash recovery", "context compaction", "role drift", "I keep telling you the same thing", "analyze my corrections". Also relevant when the agent notices repeated corrections, needs to resume after compaction, or wants to prevent known failure modes from recurring.
Active knowledge intelligence. Runs Mine → Grow → Defrag cycle. Mine extracts signal from git/.agents/code. Grow validates existing learnings against current reality, synthesizes cross-domain insights, traces provenance chains, and identifies knowledge gaps. Defrag cleans up. Triggers: "athena", "knowledge cycle", "mine and grow", "knowledge defrag", "clean flywheel", "grow knowledge".
Configure and orchestrate Claude Code agent teams (TeamCreate, SendMessage, TaskUpdate workflow). Use when you need multiple agents working in parallel on a complex task, want to coordinate background agents with messaging, or are setting up a lead/teammate architecture with a shared task list. Teams are experimental — enable with --enable-teams flag.
Skill to create custom agents for VS Code Copilot or OpenCode, helping users configure and generate agent files with proper formatting and configurations. Use when users want to create specialized AI assistants for VS Code Copilot (.agent.md files) or OpenCode (JSON/markdown agent configs) with specific tools, prompts, models, and behaviors. If the user is not specific about the target platform, ask them to specify Copilot or OpenCode.
Provides active execution protocols to rigorously audit how code, directory structures, and agent actions comply with the authoritative ecosystem specs. Trigger when validating new skills, plugins, or workflows.
Use when the user wants to reuse one model result, read text/data/meta without re-requesting, or stream partial updates, including `get_response()`, async getters, `delta`, `instant`, and `specific`.
Execute a GRACE development plan in controller-managed parallel waves with selectable safety profiles, batched graph sync, and scoped reviews.
Starts a voice conversation with the user via the agent-voice CLI. Use when the user invokes /voice. The user is not looking at the screen — they are listening and speaking. All agent output and input goes through voice until the conversation ends.