一键导入
这个仓库中的 skills
Project code patterns and conventions. Auto-loads when implementing, designing, verifying, or reviewing code. Provides detailed pattern definitions with code examples. Consult this whenever writing new code, reviewing changes, or trying to understand how this project structures things.
Code review skill from tap plugin
A helper skill
Lints code
Research findings on Claude Code marketplace, plugin structure, and distribution. Auto-loads when working with marketplace.json, plugin.json, plugin distribution, Claude Code plugin format, SKILL.md frontmatter, tap.json integration, npm skill packages, agentskills.io standard, /plugin install, or designing how skilltap interacts with the Claude Code plugin ecosystem.
Biome v2 linter/formatter reference. Auto-loads when working with biome.json, biome config, linting rules, formatting, import organization, biome check.
Zod v4 validation library reference. Auto-loads when working with Zod schemas, validation, z.object, z.string, z.infer, safeParse, transforms, discriminatedUnion.
Reference for Bun runtime APIs used in this project. Use this skill whenever writing code that runs shell commands (Bun.$ or Bun.spawn), reading/writing files (Bun.file/Bun.write), running tests (bun test), or configuring the monorepo (workspaces, bunfig.toml). Prefer Bun APIs over Node.js equivalents — use Bun.$ instead of child_process, Bun.file() instead of fs.readFile, bun:test instead of jest.
Reference for the citty CLI framework (UnJS). Use this skill whenever writing CLI commands, defining arguments/options, creating subcommands, or working with any file in packages/cli/. This covers defineCommand, runMain, argument definitions, subcommands, lifecycle hooks, and all citty patterns used in this project.
Keep shell completion scripts in sync with the CLI after adding a command, removing a command, adding/removing flags, or adding subcommands. Use after any change to index.ts subCommands, any command's args definition, or config/agent/tap subcommands. Invoke proactively — do not wait for the user to ask.
Align all documentation layers to code after implementing a feature, adding a config key, new CLI command, new flag, or any other change. Use this skill whenever you've finished writing code and need to make sure docs are complete and consistent — including internal specs (docs/), public website (website/), LLM ingestion files (llms-full.txt), and the project memory file. Invoke proactively after any non-trivial code change, not just when the user asks.
Reference for @clack/prompts terminal UI library. Use this skill whenever building interactive CLI prompts, spinners, select menus, confirmation dialogs, or any terminal UI. Covers text, password, confirm, select, multiselect, spinner, group flows, tasks, logging, and cancel handling. Use this for any file in packages/cli/src/ui/ or any command that needs user interaction.
Reference for smol-toml TOML parser/serializer. Use this skill whenever reading, writing, or manipulating TOML files, especially config.toml. Covers parse, stringify, TomlDate, TomlError, and the TOML-to-JavaScript type mapping. Use this for packages/core/src/config.ts or any code touching config.toml.
A test fixture containing synthetic security patterns for scanner testing.