agentleFS
matthewpmatthewp/tideway/skills/review/SKILL.md

review

Skill2 starsChanged 4 months agoBSD-3-ClauseView on GitHub

Review CSS against the Tideway conventions — off-scale values, inlined tokens, direct palette use instead of semantic roles, and BEM or selector violations. Use whenever the user wants to review, lint, audit, or check CSS for Tideway compliance, or asks whether some CSS follows Tideway / the tokens / BEM.

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use close-spec, design-with-images and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • dzhngSkill

    close-spec

    When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).

    Also in 5 projects that use this

  • dzhngSkill

    design-with-images

    Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.

    Also in 5 projects that use this

  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • +3 more from dzhng
  • +5 more from Lambenthan

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 157 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read each rule in the style skill and flag CSS that breaks it:

    line 31

“Common” is measured: kept by at least 6 in 10 of the 157 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Tideway: review

Review checks CSS against the Tideway conventions and reports where it drifts. It reads, it doesn't rewrite: findings go to the user, and fixes happen only on their go-ahead.

Before you start

Read the style skill. It defines the conventions you are reviewing against. Read ../style/SKILL.md and ../style/references/tokens.md so you know the exact token scales, the semantic role layer, and the BEM and selector rules. Everything below assumes you already know them.

Scope

By default, review only what changed — the staged and unstaged edits, not the whole codebase:

git diff HEAD

Review the CSS in that diff (and any new stylesheets in git status). Reviewing the whole codebase on every request buries the changes the user actually wants checked in a wall of pre-existing findings.

Widen to the whole codebase only when:

  • The user asks for a full audit, or names a scope ("review styles/").
  • There are no pending changes to review. In that case, say so and ask before scanning everything — a full review is a different, larger task the user may not want right now.

What to check

Read each rule in the style skill and flag CSS that breaks it:

  • Off-scale values — a margin, color, font-size, radius, or shadow that isn't one of the token scales. A hardcoded 13px, #4a7fd6, 0.85rem.
  • Inlined token values — a raw value that equals a token (padding: 1rem where --space-4 exists) instead of var(--space-4). The link to the token is severed.
  • Direct palette use — a component reading a --color-* primitive for color instead of a semantic role (--surface, --text, --accent, …). This is what breaks theming.
  • BEM violations — names that aren't block__element--modifier; nested elements (card__header__title); a modifier used without its base class; a block styling another block's internals.
  • Selector violations — more than one class per selector, IDs, bare element selectors outside a reset, chained classes to win specificity, descendant combinators, or !important.

Reporting

  1. Group findings by file, then by rule, so the scope is clear.
  2. For each, quote the offending line and name the rule it breaks and the fix (which token, which role, which BEM form).
  3. Report before changing anything. Apply fixes only on the user's go-ahead. A finding you're unsure about — a value that may be intentionally off-scale, a class that may be built dynamically — is worth raising as a question, not silently rewriting.

Out of scope

Writing new CSS is the style skill. Converting an existing project onto Tideway is the migrate skill. Removing classes that are defined but never used is the prune skill.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.