Loading...
Loading...
Found 789 Skills
Stop your AI from making things up. Use when your AI hallucinates, fabricates facts, isn't grounded in real data, doesn't cite sources, makes unsupported claims, or you need to verify AI responses against source material. Covers citation enforcement, faithfulness verification, grounding via retrieval, and confidence thresholds.
Systematic debugging methodology with root cause analysis. Phases: investigate, hypothesize, validate, verify. Capabilities: backward call stack tracing, multi-layer validation, verification protocols, symptom analysis, regression prevention. Actions: debug, investigate, trace, analyze, validate, verify bugs. Keywords: debugging, root cause, bug fix, stack trace, error investigation, test failure, exception handling, breakpoint, logging, reproduce, isolate, regression, call stack, symptom vs cause, hypothesis testing, validation, verification protocol. Use when: encountering bugs, analyzing test failures, tracing unexpected behavior, investigating performance issues, preventing regressions, validating fixes before completion claims.
Expert web research with advanced search techniques. Use for deep research, information gathering, or fact verification.
Conduct web research and material downloading for each node. Read node-list.txt, launch multiple sub-agents to perform parallel web research on node content, deeply retrieve relevant webpages/articles/blogs/literature, download and save them locally, and output a download.txt file to record the material sources for each node. Suitable for document writing scenarios that require extensive background information, data verification, and reference sources.
Testing Inertia Rails responses with RSpec and Minitest: component assertions, prop matching, flash verification, deferred props, and partial reload helpers. Use when writing controller specs, request specs, or integration tests for Inertia pages. ALWAYS use matchers (render_component, have_props, have_flash), NOT direct access (inertia.component, inertia.props). CRITICAL: after POST/PATCH/DELETE with redirect, MUST call follow_redirect! before asserting flash or props — without it you're asserting against the 302, not the Inertia page. Setup: require 'inertia_rails/rspec'.
Visual testing, UI verification, and design comparison using screenshots and Figma integration. Use when the user wants to verify UI appearance, compare with Figma designs, test responsive layouts, check for visual regressions, or validate design implementation.
Create and validate solution design documents (SDD). Use when designing architecture, defining interfaces, documenting technical decisions, analyzing system components, or working on solution-design.md files in docs/specs/. Includes validation checklist, consistency verification, and overlap detection.
End-to-end npm release workflow with verification gates and hardcoded-version protection
Phase-level implementation workflow for builder agents. Handles reading phase files, finding references, invoking domain skills, implementing all steps, and running verification (tests + typecheck). Preloaded into builder agents via skills: field — not user-invocable.
Mandatory incident fix verification with observables. Invoke after: applying production fixes, before declaring incidents resolved, when someone says 'I think that fixed it'. Requires log entries, metric changes, and database state confirmation.
Writes precise, autonomous-execution-ready tasks using the SMART+ framework (Specific, Measurable, Actionable, Referenced, Testable, +Context). Transforms vague task descriptions into detailed specifications with file paths, verification commands, and clear success criteria. Use when writing tasks for any agent, creating todos, planning features, decomposing work, or when tasks lack precision. Triggers on "write task", "create todo", "break down feature", "make task precise", "task is vague", or when task descriptions are missing file paths, verification steps, or clear success criteria. Works with todo.md, task lists, project planning documents, and agent instructions.
Use when Claude Code needs a second opinion, verification, or deeper research on technical matters. This includes researching how a library or API works, confirming implementation approaches, verifying technical assumptions, understanding complex code patterns, or getting alternative perspectives on architectural decisions. The agent leverages the Codex CLI to provide independent analysis and validation.