Loading...
Loading...
Found 3,083 Skills
Explains the mental model and architecture of the code under `packages/forms/signals`. You MUST use this skill any time you plan to work with code in `packages/forms/signals`
Self-evolving context protocol that captures insights, prevents repeated mistakes, and evolves project documentation through structured feedback loops.
Manage releases for this project. Validates changelog, installs git hooks, and cuts releases. Use when user says "/release", "release 1.0.5", "cut a release", or asks about the release process. NOT auto-invoked by the model.
Shatter compromised calibration and rebuild from ground truth.
Define, validate, and run lane-style multi-step automation sequences using `asc workflow` and a repo-local `.asc/workflow.json`. Use when migrating from lane-based automation, building enterprise CI flows, or orchestrating multi-command `asc` runs.
Review Vendure entities for missing VendureEntity inheritance, improper decorators, missing migrations, index violations, and TypeORM anti-patterns. Use when reviewing entity PRs or auditing data models.
Validate agent skills for correctness, readability, workflow clarity, and isolation, ensuring they can be installed independently without dependencies on other 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.
Agent definition conventions. Use when creating or modifying agents at any level (~/.claude/agents/, .claude/agents/, or project-local). Validate frontmatter, update README.md index. NOT for creating skills, MCP servers, or modifying CLAUDE.md.
Sub-agent powered code reviews spanning correctness, tests, consistency, and fit
Smoke test for alicloud-solution-content-article-illustrator. Validate solution-skill structure, compatibility-oriented documentation, prompt-before-image workflow, backend recommendation policy, and final Markdown output artifacts.
Validate Claude Code skills against the agentskills specification. Catches structural, semantic, and naming issues before users do.