analyze-code
Deep code analysis using consultant agent. Identifies technical debt, risks, and improvement opportunities.
Découvrez les skills DevOps, comparez leurs dépôts et consultez leurs instructions.
Deep code analysis using consultant agent. Identifies technical debt, risks, and improvement opportunities.
Create implementation plans from spec via iterative codebase research and strategic questions. Produces mini-PR plans optimized for iterative development.
Research external topics via web search with structured hypothesis tracking and source evaluation.
Requirements discovery through structured interview. Use when WHAT is unclear—scope needs definition, requirements need gathering, or starting from scratch. Outputs spec document, not executable manifest.
Single-model consultation using consultant agent. Defaults to gpt-5.2-pro.
Compresses prompts/skills into minimal goal-focused instructions. Trusts the model, drops what it already knows, maximizes action space. Use when asked to compress, condense, or minimize a prompt.
Verify code changes comply with CLAUDE.md instructions and project standards.
Audit documentation accuracy against code changes. Reports discrepancies without modifying files.
Executes implementation plans via subagents with automated verification and fix loops. Use after /plan for complex features. Each chunk gets dedicated Implementor + Verifier agents with up to 5 fix attempts.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven...
This skill should be used when the user asks to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", "SKILL.md format", "skill frontmatter", "sk...
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command w...
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomou...
This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plu...
This skill should be used when the user asks to "create a marketplace", "set up marketplace.json", "organize multiple plugins", "distribute plugins", "host plugins", "marketplace schema", "plugin marketplace st...
This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLU...
This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add comma...
Formats and lints code with ruff using a sub-agent. Use after tests pass to ensure code style compliance.
"Generates step instruction files and syncs slash commands from the job.yml specification. Use after job spec review passes."user-invocable: false---
Analyzes conversation history to improve job instructions and capture learnings. Use after running a job to refine it.
Creates file-change rules that enforce guidelines during AI sessions. Use when automating documentation sync or code review triggers.
Adds a new AI platform to DeepWork with adapter, templates, and tests. Use when integrating Cursor, Windsurf, or other AI coding tools.
Edits standard job source files in src/ and runs deepwork install to sync changes. Use when updating job.yml or step instructions.
Updates job schema and adapters with any new hook events the platform supports. Use after research to extend DeepWork's hook system.
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.