New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Benchmark Protocol

by inkline in inkline/inkline

How Inkline measures itself — compile performance, output size and quality vs hand-written components and Mitosis, fairness rules, and reporting format.

No licenceAuto-check passed

Install Benchmark Protocol

skills CLI
$ npx skills add inkline/inkline --skill benchmark-protocol -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install inkline/inkline benchmark-protocol --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/inkline/inkline.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/benchmark-protocol .claude/skills/benchmark-protocol && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
benchmark-protocol
GitHub stars
1.5k
Token cost
~955 tokens
SKILL.md length
368 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
None found

At a glance

How Inkline measures itself — compile performance, output size and quality vs hand-written components and Mitosis, fairness rules, and reporting format.

  • Works in 6 steps: Same reference component set per… → Pinned versions, stated hardware, median… → Measure the path users actually run (CLI… → …
  • Regression gates
  • SKILL.md covers Metrics that matter (for a…, Existing surface (extend,…, Fairness rules (non-negotiable… and Regression gating, plus 1 more section
  • Calls pnpm

What it does

Benchmark Protocol is an agent skill from inkline/inkline. How Inkline measures itself — compile performance, output size and quality vs hand-written components and Mitosis, fairness rules, and reporting format. Use for perf work, regression gates, and published comparisons.

Its SKILL.md is about 960 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Inkline is the intuitive UI Components library that gives you a developer-friendly foundation for building high-quality, accessible, and customizable Vue.js 3 Design Systems.

When your agent uses it

  • Regression gates
  • Published comparisons

Example prompts

  • “/benchmark-protocol”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Same reference component set per contender, idiomatic for each (no strawmen) — equivalent props, states, slots, styling.
  2. Pinned versions, stated hardware, median of ≥5 runs after warmup; report variance.
  3. Measure the path users actually run (CLI compile for libraries, plugin transform for apps) and say which.
  4. Contenders: Mitosis (the direct write-once-compile-everywhere neighbor) and hand-written per-framework components (the honest baseline…
  5. Publish the harness with the numbers. Reproducibility is the argument.
  6. Report losses honestly. A benchmark Inkline never loses reads as marketing and converts nobody. "Hand-written is N% smaller on target X"…

What it can do on your machine

Read from SKILL.md and the folder at commit f4da55a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pnpm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Benchmark Protocol loads about 955 tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 368 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~955

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 368 words (~955 tokens).

“Benchmarks serve two purposes: regression gates (internal, every release) and published comparisons (external, credibility). Both die if the methodology is sloppy — a benchmark we can't defend in a hostile Hacker News thread must not be published.”

— opening of SKILL.md by inkline
name
benchmark-protocol

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/benchmark-protocol of inkline/inkline.

Open the folder on GitHubat commit f4da55a

Compare with similar skills

Benchmark Protocol next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Benchmark Protocol compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Benchmark Protocol this skillinkline/inkline1.5k—~955Automated safety check: PassNone
Benchmarkaffaan-m/ECC274k3 repos~654Automated safety check: PassMIT
Benchmarkaffaan-m/ECC274k—~412Automated safety check: PassMIT
Benchmarkaffaan-m/ECC274k—~330Automated safety check: PassMIT
Gstack Performance Benchmarkgarrytan/gstack136k—~7.2kAutomated safety check: NotesMIT
Benchmark Optimization Loopaffaan-m/ECC274k1 repos~664Automated safety check: PassMIT

Similar skills

  • Benchmark

    affaan-m/ECC

    Measure performance baselines and detect regressions across browser Core Web Vitals (LCP, INP, CLS, page weight), API endpoint latency percentiles, and build/test feedback times, with before/after…

    274k GitHub starsUsed in 3 repos~654 tokens
    Frontend & DesignAuto-check passed

  • Benchmark

    affaan-m/ECC

    このスキルを使用して、パフォーマンスベースラインを測定し、PR前後の回帰を検出し、スタック代替案を比較します. An agent skill from affaan-m/ECC.

    274k GitHub stars~412 tokensUpdated 2 days ago
    Auto-check passed

  • Benchmark

    affaan-m/ECC

    使用此技能测量性能基线，检测PR前后的回归，并比较堆栈替代方案。

    274k GitHub stars~330 tokensUpdated 2 days ago
    Auto-check passed

  • Gstack Performance Benchmark

    garrytan/gstack

    Establishes page load, Core Web Vitals and resource-size baselines, then compares before and after on every pull request to track performance trends over time.

    136k GitHub stars~7.2k tokensUpdated yesterday
    Frontend & DesignAuto-check: notes

  • Benchmark Optimization Loop

    affaan-m/ECC

    Convert 'make it faster' requests into a bounded measured optimization loop — baseline first, generate one-hypothesis variants, benchmark each against a correctness gate, and promote the fastest…

    274k GitHub starsUsed in 1 repo~664 tokens
    Auto-check passed

  • Cost Benchmark

    ruvnet/ruflo

    Run the corpus benchmark — booster locally, optional Gemini/Sonnet/Opus baselines — and persist a verifiable measured-vs-claimed table

    74k GitHub stars~745 tokensUpdated today
    AI & LLM EngineeringAuto-check: notes

More from inkline/inkline

All 23 skills in this repo

  • Adversarial QA

    inkline/inkline

    Repro-first QA for Inkline — minimal .ink.tsx reproductions, the visual-parity and cross-target harnesses, fuzz targets, and how to audit teammates' claims.

    1.5k GitHub stars~1.2k tokensUpdated 26 days ago
    Auto-check passed

  • Compiler Pipeline Internals

    inkline/inkline

    The Inkline compiler's end-to-end pipeline — parse → IR → analyze → per-target codegen → print — including the IR contracts, reactivity tracking, target rewrite rules, plugin hooks, the two compile…

    1.5k GitHub stars~1.9k tokensUpdated 26 days ago
    Auto-check passed

  • Component Catalog

    inkline/inkline

    How Inkline components are built and kept consistent — the headless/styled split, family anatomy, prop/axis conventions, recipe consumption, the current 5-family catalog and its gap list.

    1.5k GitHub stars~1.4k tokensUpdated 26 days ago
    Auto-check passed

  • Create PR

    inkline/inkline

    Author a pull request in the Guild's standard shape — a fixed Summary / Changes / Verification / Notes skeleton that mirrors the review-gate, plus the hard anti-leak rule that no agent @mention or…

    1.5k GitHub stars~1.7k tokensUpdated 26 days ago
    Auto-check passed

  • Design Token Architecture

    inkline/inkline

    How design tokens and recipes flow from styleframe into Inkline — the presets, the two faces of virtual:styleframe, recipe class contracts, theming, and the rules for custom CSS in components.

    1.5k GitHub stars~1.2k tokensUpdated 26 days ago
    Auto-check passed

  • Implement Component

    inkline/inkline

    Phase 2 of building an Inkline component — write the .ink.tsx source.

    1.5k GitHub stars~1.7k tokensUpdated 26 days ago
    Auto-check: notes

Questions about Benchmark Protocol

What does Benchmark Protocol do?

How Inkline measures itself — compile performance, output size and quality vs hand-written components and Mitosis, fairness rules, and reporting format. Benchmark Protocol is an agent skill from inkline/inkline. How Inkline measures itself — compile performance, output size and quality vs hand-written components and Mitosis, fairness rules, and reporting format.

When should I use Benchmark Protocol?

Benchmark Protocol fits situations like: regression gates; published comparisons.

How do I install Benchmark Protocol in Claude Code?

Run `npx skills add inkline/inkline --skill benchmark-protocol -a claude-code`. Or copy the skill folder (.claude/skills/benchmark-protocol in inkline/inkline) into .claude/skills/benchmark-protocol in your project. Claude Code loads it when a task matches its description.

How do I install Benchmark Protocol in Codex?

Run `npx skills add inkline/inkline --skill benchmark-protocol -a codex`. Or copy the skill folder (.claude/skills/benchmark-protocol in inkline/inkline) into .agents/skills/benchmark-protocol in your project. Codex loads it when a task matches its description.

Can I use Benchmark Protocol in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add inkline/inkline --skill benchmark-protocol -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/benchmark-protocol, .gemini/skills/benchmark-protocol, .github/skills/benchmark-protocol and .opencode/skills/benchmark-protocol in your project.

What does Benchmark Protocol need to run?

Going by SKILL.md and its folder, Benchmark Protocol needs the command-line tools its instructions call (pnpm).

Does Benchmark Protocol access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Benchmark Protocol safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Benchmark Protocol use?

No licence was found for Benchmark Protocol or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Benchmark Protocol use?

About 955 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Benchmark Protocol?

Skills that share tags, products or a category with Benchmark Protocol: Benchmark (affaan-m/ECC, 274k stars), Benchmark (affaan-m/ECC, 274k stars), Benchmark (affaan-m/ECC, 274k stars) and Gstack Performance Benchmark (garrytan/gstack, 136k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Benchmark Protocol?

inkline (a GitHub organization) maintains it in inkline/inkline, which has 1,469 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on September 11, 2026.

Source: inkline/inkline on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.