Loading...
Loading...
Found 2,206 Skills
Generate professional Agent Skills for Claude Code and other AI agents. Creates complete skill packages with SKILL.md, references, scripts, and templates. Use when creating new skills, generating custom slash commands, or building reusable AI capabilities. Validates against Agent Skills specification.
Cursor PMでアイデアを検証し、Plans.mdを更新してバトンタッチ。2-Agentワークフロー対応。
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
Generate and prioritize US equity long-side edge research tickets from EOD observations, then export pipeline-ready candidate specs for trade-strategy-pipeline Phase I. Use when users ask to turn hypotheses/anomalies into reproducible research tickets, convert validated ideas into `strategy.yaml` + `metadata.json`, or preflight-check interface compatibility (`edge-finder-candidate/v1`) before running pipeline backtests.
Gate 2: Feature relationship map - visualizes feature landscape, groupings, and interactions at business level before technical architecture.
Structure complex questions into testable hypotheses. Use when validating product ideas, debugging problems, planning experiments, or breaking down ambiguous challenges into actionable research.
Verify logic diagrams against source code. Check line-number accuracy, Mermaid syntax, node completeness, and side effect documentation. Runs as independent Critic in fork context. Use when: verify logic, check logic diagram, validate phase 2, re-verify-logic.
Verify structure analysis output against source code. Check file:line references, component completeness, and Mermaid diagram validity. Runs as independent Critic in fork context. Use when: verify structure, check structure map, validate phase 1, re-verify-structure.
Review code changes against a plan using the plan location and implementing git commit(s).
Use when you need to locate the current spec pack (FEATURE_DIR) in the Spec process of sdlc-dev, avoid reading or writing requirements/*.md in the wrong directory, or encounter issues such as "misreading context/writing to the wrong file/non-compliant branch".
Complete guide for building accessible, high-UX forms in modern stacks (React/Next.js, Tailwind, Zod). Includes specific patterns for clickable areas, range sliders, output-inspired design, and WCAG compliance.
This skill should be used when the user asks to "validate a finding", "check if a vulnerability is real", "triage a security finding", "confirm a vulnerability", "determine if a finding is a true positive or false positive", or provides a security finding for review. It validates security vulnerability findings by tracing data flows, verifying exploit conditions, analyzing security controls, and optionally testing attack vectors against a live application.