- Skills
- 36
- 仓库
- 1
- 职业覆盖
- 0
- 场景覆盖
- 0
- Stars
- ★ 10
Alpha Chen 的 Skills 36
zoekt
Use when searching code across repositories — prefer zoekt over grep/ripgrep for indexed code search. Covers indexing repos, search syntax, and query patterns.
writing-for-accessibility
Use when writing documentation, alt text, diagrams, or any content that should be accessible to people with disabilities. Covers alt text, color contrast, inclusive language, and accessible visuals. Also use when reviewing documents for accessibility.
writing-error-messages
Use when writing, reviewing, or improving error messages in code, CLI tools, APIs, or UIs. Covers identifying the cause, explaining the fix, and setting the right tone. Also use when error messages are vague, unactionable, or confusing.
working-in-the-open
Use when making design decisions during implementation — routes rationale to the right venue (commits, task comments, code comments, or documentation) based on how durable the context needs to be
web-standards
Use when writing or reviewing HTML, CSS, or browser JavaScript — covers semantic markup, native platform features over libraries, Baseline browser support, accessibility and APCA contrast, and optional validation with vnu, axe, and Lighthouse
web-design
Use when designing or building web UI, frontends, or styling — covers personal web design preferences, fluid layout, and Alpine.js
warm-handoff
Use when the user asks to "warm handoff", "/warm-handoff", "hand off this thread", or "redirect this to". Reads a Slack thread and proposes a warm handoff message for the target channel.
tighten-docs
Make docs, specs, prompts, and skills clearer and shorter while preserving required meaning, examples, rationale, constraints, and trigger behavior. Use to rewrite documentation for concision, trim verbose specs or design notes, reduce repeated guidance, or make a SKILL.md leaner.
threat-modeling
Use when writing or reviewing a threat model, designing a system with security implications, or evaluating security claims and trade-offs — covers the seven questions, layered decomposition, risk status categories, and spotting weak security reasoning
testing
Use when designing, writing, or reviewing tests — deciding what to test, structuring a suite, adding randomized or exhaustive tests, making failures reproducible, or dealing with slow or flaky tests
technical-writing
Use when writing or reviewing technical documentation, API docs, tutorials, READMEs, or developer guides. Covers terminology, audience analysis, document structure, lists, paragraphs, illustrations, and sample code. Complements diataxis (document classification).
speed-run
Fan out bug reports to parallel subagents on their own jj tracks, review each fix, and hand it back.
skill-notes
Use when creating a new SKILL.md file, reviewing an existing skill for quality, or when the user asks about skill authoring conventions
self-improving-skills
Use right after finishing a task where a skill you relied on fell short — you had to run `--help` or read docs it should have covered, you tried a command or flag that turned out not to exist, you hit an error and worked out the fix, or the skill was sparse, outdated, or missing a workflow. Load it and follow it to fold what you learned back into that skill before wrapping up, rather than moving on. Applies during normal work, not only when asked.
rust
Use when writing, reviewing, scaffolding, releasing, or measuring coverage on Rust code — routes to references for style, project layout, testing, Dockerfile, and release
ruby-style
Use when writing, reviewing, or refactoring Ruby code — covers personal style preferences and conventions
resolve-conflicts
Use when resolving jj conflicts after rebase, squash, or merge — handles conflict markers, mergiraf automation, and file-by-file manual resolution, in place with `jj resolve -r` or in an isolated workspace
pr
Use when opening a pull request for a jj revision, including pushing it first (/pr)