brand-guidelines (Anthropic)
brand-guidelines：对照组 4.42、一句话提示 5.0、装 skill 5.0（0–5 分，Codex 实测，n=2/任务/组）。结论：视情况而定，相对不装 skill +0.58。
26.6 / 30
相对不装 skill 的提升：+0.58
视情况而定：提升 +0.58 低于 +1.0。推荐要求总分 22/30、产出质量 3.5、提升 +1.0。
前沿
通过使用 Codex 测试。
覆盖 Codex, Claude Code
Codex CLI 0.166（SOTA 档）：18 次评分运行。按我们的分档规则，这档通过同时覆盖 Claude Code；它不代表第二档的结果。
分数
每一维 0 到 5 分，六维相加是满分 30 的总分。每一维都是 5 更好。成本 5 表示又便宜又快。安装 5 表示容易。
- 触发可靠性
- 5.0
- 相对不装的提升
- 2.6
- 产出质量
- 5.0
- 令牌与时间成本
- 5.0
- 安装与可移植性
- 4.0
- 安全
- 5.0
安全审查
安全静态扫描：0 CRITICAL / 0 HIGH / 0 MEDIUM。人工审查：可在断网沙箱中运行。扫描没有命中不等于绝对安全。
安装
npx skills@latest add anthropics/skills --skill brand-guidelines
固定提交: ca45fc496a3436251f191354091d557da31c15b5
测试日期: 2026-11-02
我们测了什么
- Restyle an HTML deck — Style deck.html with Anthropic's official brand colors and typography. Edit the file in place.
- Write a branded stylesheet — Write brand.css for our internal documents following Anthropic's official brand guidelines (colors and typography). Save it as brand.css.
- Branded status card — Create status.html: a small self-contained status card (title, three status rows) styled in Anthropic's official brand look and feel.
优点
- 平均分从不装时的 4.42 提到 5.0（+0.58）。
- 不点名也会被触发：Skill file read in 6/6 treatment runs.
- 不增加 token 开销：约为不装 skill 时的 0.54 倍。
- 装 skill 后绝对质量高：5.0 / 5。
缺点
- 一句话提示得 5.0，装 skill 得 5.0（差 +0.00）。
- 每个任务每组 n=2，差距在 1 分以内属于噪声。
评测
在 Codex CLI（SOTA 档）上跑 3 个任务、对照、一句话提示、装 skill 三组，共 18 次运行，由规则脚本打分（没有 LLM 评委），断网沙箱、每次运行独立临时目录。具体做法见下方英文评测原文。
三组对比
| 组别 | 平均分（0–5） | 每次 token |
|---|---|---|
| 不装 skill | 4.42 | 104k |
| 一句话提示 | 5.0 | 52k |
| 装了 skill | 5.0 | 56k |
Codex CLI 实测，18 次运行，规则脚本打分，没有 LLM 评委。总分 26.6 / 30，结论 视情况而定。
下面是评测原文，英文。
Verdict: Situational (26.6 / 30). Source: anthropics/skills, skills/brand-guidelines, pinned at commit ca45fc4. Install: npx skills@latest add anthropics/skills --skill brand-guidelines. Licence: Apache-2.0 / Anthropic terms (see LICENSE.txt in skill).
What it is
The brand-guidelines skill from anthropics/skills: Anthropic's official brand colours (dark #141413, light #faf9f5, mid gray #b0aea5, light gray #e8e6dc, accents orange #d97757, blue #6a9bcc, green #788c5d) and typography (Poppins for headings with Arial fallback, Lora for body with Georgia fallback), plus how to apply them. One SKILL.md of about 330 words; no scripts.
How we tested
Codex CLI 0.166 (gpt-6-astra, low reasoning) on a Mac test machine, a fresh temporary project and temporary HOME/TMPDIR/caches per run, skill installed (treatment) or absent (control) or absent with the skill's core requirement squeezed into one sentence appended to the prompt (one-liner group), 2 runs per group per task, network off, /tmp writes blocked. The prompts never mention the skill (except the wording noted below).
Three tasks that name Anthropic's official brand without giving any value: restyle deck.html in place, write brand.css for internal documents, and build a small self-contained status card (status.html). Scored by rules: at least 5 of the 7 brand hex codes, Poppins headings, Lora body, Arial/Georgia fallbacks.
- Restyle an HTML deck — Style deck.html with Anthropic's official brand colors and typography. Edit the file in place.
- Write a branded stylesheet — Write brand.css for our internal documents following Anthropic's official brand guidelines (colors and typography). Save it as brand.css.
- Branded status card — Create status.html: a small self-contained status card (title, three status rows) styled in Anthropic's official brand look and feel.
Scoring is programmatic (hidden tests / planted-issue recall / constraint checks / render+OCR where relevant), 0–5 per run. No LLM judge decided any score.
Results
The one-liner given to the third group: "Use Anthropic's palette (dark #141413, light #faf9f5, mid gray #b0aea5, light gray #e8e6dc; accents orange #d97757, blue #6a9bcc, green #788c5d) with Poppins for headings (Arial fallback) and Lora for body text (Georgia fallback)."
| Task | Control score | One-liner | With skill | Control tokens | One-liner tokens | With-skill tokens | Skill read |
|---|---|---|---|---|---|---|---|
| t1-deck | 5.0 | 5.0 | 5.0 | 160k | 62k | 64k | 2/2 |
| t2-css | 5.0 | 5.0 | 5.0 | 76k | 47k | 56k | 2/2 |
| t3-card | 3.27 | 5.0 | 5.0 | 75k | 47k | 47k | 2/2 |
Mean score: 4.42 without vs 5.0 with the skill (delta +0.58). Tokens per run: 104k vs 56k (0.54x); time 64s vs 39s. One-liner group: 5.0 (the skill's gain over the one-liner: +0.0; one-liner's own gain over no skill: +0.58); one-liner tokens 52k per run, so the skill costs 1.08x the one-liner.
What happened
- Mean score 4.42 without the skill, 5.0 with the skill, 5.0 with a one-sentence version that lists the colours and fonts. The control group's misses came from the status-card task: in one of its two runs (1.9/5) the agent did not use the brand palette and fonts, in the other it did (4.64); on the deck and the stylesheet task control scored 5.0 in both runs.
- So plain Codex often knows the palette from training, but not reliably; with the skill every one of 6 runs hit the full palette and fonts.
- The skill was read in 6/6 runs and was cheaper than the control: 56k tokens per run against 104k (0.54x), and about the same as the one-liner (52k). On the deck task control used 155-166k tokens against 64k with the skill; we did not investigate why control spent more (it made 8 commands against 6 in the first run of each).
- The one-sentence version, which contains the same hex codes and fonts, scored the same as the skill (5.0) at the same cost, so the skill's value is the stored facts, not an elaborate method.
Dimension scores
| Dimension | Score | Why |
|---|---|---|
| 1_output_quality | 5.0 | Mean score 5.00/5 with the skill (programmatic checks, see per-task table). |
| 2_lift_vs_no_skill | 2.58 | +0.58 points vs 4.42 without the skill (n=2 per task; under ~1 point is noise). |
| 3_trigger | 5.0 | Skill file read in 6/6 treatment runs. |
| 4_instructions_portability | 4 | Plain Markdown facts; works in any agent that loads skills. Specific to Anthropic's brand. |
| 5_efficiency | 5 | 0.54x tokens (56k vs 104k per run) and 0.60x time (39s vs 64s). |
| 6_safety_hygiene | 5 | Markdown only; no scripts. |
Limits of this test
- A rule check of hex codes and font names, not a visual judgement of how brand-like the page looks.
- Three small tasks, two runs each; the control miss is a single run.
- The skill only has facts for one brand (Anthropic's); the test shows nothing about how well a skill like this works for another company's guidelines.
- n = 2 per group per task: differences under about 1 point are noise.
- Rule-based scoring measures what the checks can see; it cannot judge taste or whether a result is the best possible.
Security
See security.md. Scan: 0 CRITICAL / 0 HIGH / 0 MEDIUM. Verdict: safe to run (no-network sandbox). A clean scan does not prove a skill safe.
Bottom line
The skill reliably supplies the exact palette and fonts and in these runs it cost half the tokens of a bare request. A one-sentence prompt with the same values matches it, so the skill is worth using only if you want the facts stored once instead of repeated in each prompt.
记录
Run log for brand-guidelines: Codex CLI, network off, per-run temp HOME/TMPDIR, one row per graded run. Columns: task, arm-run, score (0-5), tokens, seconds, checks passed, skill files the agent opened. t1-deck control-1: score 5.0, tokens 155456, secs 85.7, checks 4/4, opened nothing t1-deck control-2: score 5.0, tokens 165533, secs 105.4, checks 4/4, opened nothing t1-deck oneliner-1: score 5.0, tokens 62478, secs 39.6, checks 4/4, opened nothing t1-deck oneliner-2: score 5.0, tokens 62290, secs 34.7, checks 4/4, opened nothing t1-deck treatment-1: score 5.0, tokens 64207, secs 41.4, checks 4/4, opened brand-guidelines t1-deck treatment-2: score 5.0, tokens 64192, secs 37.5, checks 4/4, opened brand-guidelines t2-css control-1: score 5.0, tokens 75329, secs 57.0, checks 4/4, opened nothing t2-css control-2: score 5.0, tokens 76695, secs 51.6, checks 4/4, opened nothing t2-css oneliner-1: score 5.0, tokens 47066, secs 34.8, checks 4/4, opened nothing
18 次运行、3 个产物
样例产物
前沿 · 装了 skill：deck.html（t1-deck，第 1 次，Codex）
<!DOCTYPE html> <html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1"><title>Q3 Update</title> <style> :root { color-scheme: light; --dark: #141413; --light: #faf9f5; --mid-gray: #b0aea5; --light-gray: #e8e6dc; --orange: #d97757; --blue: #6a9bcc; --green: #788c5d; } * { box-sizing: border-box; } body { margin: 0; padding: clamp(16px, 4vw, 56px); background: var(--light-gray); color: var(--dark); font-family: 'Lora', Georgia, serif; font-size: clamp(18px, 2vw, 24px); line-height: 1.6; } section { max-width: 1120px; min-height: 560px; margin: 0 auto 32px; padding: clamp(28px, 6vw, 80px); background: var(--light); border-top: 8px solid var(--orange); } section:first-child { display: flex; flex-direction: column; justify-content: center; background: var(--dark); color: var(--light); } section:nth-child(2) { border-color: var(--blue); } section:nth-child(3) { border-color: var(--green); } section:last-child { margin-bottom: 0; } h1, h2 { margin: 0 0 24px; font-family: 'Poppins', Arial, sans-serif; font-weight: 600; line-height: 1.15; letter-spacing: -0.035em; } h1 { font-size: clamp(48px, 7vw, 88px); } h2 { font-size: clamp(32px, 4.5vw, 52px); } p { margin: 0 0 28px; max-width: 48ch; } section:first-child p { color: var(--mid-gray); margin-bottom: 0; } ul { padding-left: 1.3em; margin: 32px 0 0; } li { padding-left: 0.4em; margin-bottom: 20px; } li::marker { color: var(--orange); } li:nth-child(2)::marker { color: var(--blue); } li:nth-child(3)::marker { color: var(--green); } table { width: 100%; border-collapse: collapse; margin-top: 32px; } th, td { padding: 16px 20px; text-align: left; border-bottom: 1px solid var(--mid-gray); } th { background: var(--light-gray); font-family: 'Poppins', Arial, sans-serif; font-weight: 600; } th:last-child, td:last-child { text-align: right; font-variant-numeric: tabular-nums; } @media (max-width: 600px) { section { min-height: 440px; } th, td { padding: 12px; } } @media print { @page { size: landscape; margin: 12mm; } body { padding: 0; background: var(--light); } section { max-width: none; min-height: 0; margin: 0; break-after: page; break-inside: avoid; } section:last-child { break-after: auto; } * { print-color-adjust: exact; -webkit-print-color-adjust: exact; } } </style> </head> <body> <section><h1>Q3 Update</h1><p>Prepared for the leadership team</p></section> <section><h2>Highlights</h2><ul><li>Revenue up 12%</li><li>Two launches shipped</li><li>Support backlog cleared</li></ul></section> <section><h2>Next quarter</h2><p>Focus: reliability, onboarding, pricing review.</p><table><tr><th scope="col">Metric</th><th scope="col">Q3</th></tr><tr><td>Revenue</td><td>$1.2M</td></tr><tr><td>Churn</td><td>2.1%</td></tr></table></section> </body></html>