self-reflect
Reflects on the current session to identify failures, inefficiencies, and improvement opportunities. Use at session end to extract learnings.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-02 00:09
Agents & models
25,480 results
agents-md
AGENTS.md: create, shrink, or tend the current project's always-loaded file and docs/agents/ after a task when a non-discoverable fact is new, a line is stale…
agent-browser
Browser automation tool for web navigation, interaction, screenshots, recording, etc. Use when browser operations need to be automated, web pages tested, web content scraped, forms filled, screenshots taken, videos recorded, or when "browser automation", "web testing", "agent-browser", or "browser operations" are mentioned.
implement-batch
Work a queue of agent-ready tracker tickets unattended — wherever the repo's issue-tracker doc says they live. A pre-flight asks everything up front, then per…
qt-dialogs
Qt dialog patterns — QDialog, QMessageBox, QFileDialog, QInputDialog, and custom modal/modeless dialogs. Use when creating confirmation prompts, file pickers,…
create-skill-file
Guides Claude in creating well-structured SKILL.md files following best practices. Provides clear guidelines for naming, structure, and content organization to…
jira
Use jira CLI and MCP tools (mcp__jira__*) for Jira Cloud operations — issue management, project queries, JQL search, transitions, worklogs, plans, and more.…
project-skill-writer
Use this skill when the user needs to create, update, or design project-level skills (.trae/skills/*/SKILL.md). Analyze the user's problem and project context, and design a reusable skill solution. Trigger words: 'create skill', 'write skill', 'build skill', 'add skill', 'update skill', 'project skill', 'new skill', 'design skill', or when the user describes a need to capture as a reusable AI...
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
course-skill-update-checker
Mengecek ketersediaan pembaruan (update) resmi paket Course-Agent-Skills dari repositori GitHub, membandingkan versi lokal vs remote, melindungi kredensial,…
alera-agent-profiles
Maintain Alera Agent Profiles or research and validate a launch catalog.
authoring-skills
Guide for authoring effective Agent Skills using principle-based approach (Progressive Disclosure, Respect Intelligence, Enable Discovery). Covers creating,…
prompt-lab
Test, validate, and improve agent instructions (CLAUDE.md, system prompts) using sub-agents as experiment subjects. Measures instruction compliance, context…
agent-worker
Create and manage AI agent sessions with multiple backends (SDK, Claude CLI, Codex, Cursor). Also supports multi-agent workflows with shared context, @mention…
orientation
Orients agents in new projects by scanning entry documents and discovering capabilities. Use at session start, when entering unfamiliar territory, or when…
agent-worker
Create and manage AI agent sessions with multiple backends (SDK, Claude CLI, Codex, Cursor). Also supports multi-agent workflows with shared context, @mention…
orientation
Orients agents in new projects by scanning entry documents and discovering capabilities. Use at session start, when entering unfamiliar territory, or when…
light-figure-planning
Based on the paper content, plan which figures and tables should be made, where they should be inserted, and what role each plays. Use when the user needs paper figure and table planning. Figures and tables are not limited to statistical charts; they also include real effect figures of datasets, model output examples, case displays, interpretability visualizations, etc. Plan framework diagrams, technical roadmap diagrams, dataset schematic diagrams, model architecture diagrams, algorithm flowcharts, result comparison/ablation/sensitivity figures, real effect figures, statistical tables/comparison tables, etc., and judge by reviewer standards which are must-do, ...
lobehub-cli
Command-line tool for managing LobeHub services. Use this skill when you need to manage AI agents, knowledge bases, conversations, files, models, providers,…
dsh-plugin-creator
Create a @deepseek-ai/dsh-* plugin package end-to-end — choose the extension point or capability seam, scaffold the package, implement the tool/hook/service,…
agentsmd-optimize
Audit and organize AI coding-agent instructions, including AGENTS.md, CLAUDE.md, skills, and agent definitions. Use when the user asks to diagnose conflicting…
skill-forge
Create new skills or review and improve existing ones. Use when user says create skill, new skill, improve skill, review skill, audit skills, or skill quality.
prompt-section-design
Design composable prompt sections for building agentic prompts. Use when creating reusable prompt components, designing LEGO-block prompt sections, or…
subagent-development
Central authority for Claude Code subagents (sub-agents). Covers agent file format, YAML frontmatter, tool access configuration, model selection (inherit,…