Agent skill

Compat Hunter

by layoutit in layoutit/polycss

A skill your agent uses when hunting for OBJ/GLB/glTF/VOX parser compatibility issues by streaming candidate models, parsing each immediately, deleting clean files, and retaining only actionable…

MITAuto-check passed

Install Compat Hunter

skills CLI
$ npx skills add layoutit/polycss --skill compat-hunter -a claude-code

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

GitHub CLI
$ gh skill install layoutit/polycss compat-hunter --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/layoutit/polycss.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/compat-hunter .claude/skills/compat-hunter && 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
compat-hunter
GitHub stars
757
Token cost
~999 tokens
SKILL.md length
308 words
Files
3 (incl. scripts)
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when hunting for OBJ/GLB/glTF/VOX parser compatibility issues by streaming candidate models, parsing each immediately, deleting clean files, and retaining only actionable…

  • Works in 5 steps: In the repo, prefer the reusable script → Let the script stream remote… → Treat these as known non-actionable… → …
  • Hunting for OBJ/GLB/glTF/VOX parser compatibility issues by streaming candidate models
  • SKILL.md covers Workflow, Useful Commands and Reporting
  • Runs JavaScript scripts from its folder; calls pnpm and node

What it does

Compat Hunter is an agent skill from layoutit/polycss. Use when hunting for OBJ/GLB/glTF/VOX parser compatibility issues by streaming candidate models, parsing each immediately, deleting clean files, and retaining only actionable failures, unknown warnings, or unexplained zero-polygon outputs. Especially useful in the polycss repo with scripts/compat-hunter.mjs.

Its SKILL.md is about 1000 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `agents/openai.yaml`).

It works with GitHub. The repository describes itself as: A CSS 3D engine for the DOM. Renders polygon meshes in HTML by leveraging matrix3d transforms. The licence is MIT.

When your agent uses it

  • Hunting for OBJ/GLB/glTF/VOX parser compatibility issues by streaming candidate models
  • Parsing each immediately
  • Deleting clean files
  • Retaining only actionable failures

Example prompts

  • “/compat-hunter”

Requirements

  • Node.js

Workflow steps

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

  1. In the repo, prefer the reusable script
  2. Let the script stream remote OBJ/GLB/glTF/VOX candidates, parse each model, and discard clean files. Reports are written under…
  3. Treat these as known non-actionable unless the user asks to support them
  4. Stop and inspect anything classified as
  5. If an actionable parser issue is found, keep the saved file under the report's interesting/ directory, add a focused parser test using…

What it can do on your machine

Read from SKILL.md and the folder at commit 04a1b66. 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

    Ships 1 file in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • pnpm
    • node

    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

Compat Hunter loads about 999 tokens when it runs. Until then it costs about 81 tokens; SKILL.md has 308 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~81
When it runs · the whole SKILL.md, loaded when a task matches
~999

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); the scripts in this folder are not scanned.

SKILL.md

The full file from layoutit/polycss at commit 04a1b66, republished under its MIT licence (© layoutit). 308 words, ~999 tokens.

Download SKILL.mdSave it as .claude/skills/compat-hunter/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
compat-hunter
description
Use when hunting for OBJ/GLB/glTF/VOX parser compatibility issues by streaming candidate models, parsing each immediately, deleting clean files, and retaining only actionable failures, unknown warnings, or unexplained zero-polygon outputs. Especially useful in the polycss repo with scripts/compat-hunter.mjs.

Compat Hunter

Use this skill when the user wants to keep digging for parser compatibility issues without building a fixed local corpus.

Workflow

  1. In the repo, prefer the reusable script:

    bash
    pnpm compat-hunter -- --max-models 2000

    Equivalent explicit form:

    bash
    pnpm --filter @layoutit/polycss-core build
    node .agents/skills/compat-hunter/scripts/compat-hunter.mjs --max-models 2000
  2. Let the script stream remote OBJ/GLB/glTF/VOX candidates, parse each model, and discard clean files. Reports are written under bench/results/, which is ignored by git.

  3. Treat these as known non-actionable unless the user asks to support them:

    • glTF POINTS/LINES/LINE_LOOP/LINE_STRIP primitives.
    • Required Draco or meshopt compressed primitives skipped with a warning.
    • STL source-quality diagnostics that the parser already handles: degenerate triangles, repaired winding, component orientation, non-manifold/shared-edge topology, supplied-normal mismatches, malformed normals/facets, overdeclared binary triangle counts, trailing binary bytes, and ignored non-Magics binary attribute bytes.
    • Empty/corrupt STL containers with no complete triangle records or no valid ASCII facets.
  4. Stop and inspect anything classified as:

    • throw
    • unknown-warning
    • obj-zero-no-warning
    • glb-zero-no-warning
  5. If an actionable parser issue is found, keep the saved file under the report's interesting/ directory, add a focused parser test using that behavior, implement the smallest fix, and rerun the focused parser tests plus the hunter on the saved file or source class.

Useful Commands

Fresh Objaverse and expanded GitHub stream:

bash
pnpm compat-hunter -- --max-models 5000 --max-bytes 10mb --timeout-ms 30000

Objaverse only, later shards:

bash
pnpm compat-hunter -- --sources objaverse --objaverse-shards 120:220 --max-models 5000

GitHub only:

bash
pnpm compat-hunter -- --sources github --max-models 500

Poly Haven only:

bash
pnpm compat-hunter -- --sources polyhaven --polyhaven-limit 250 --max-models 200

VOX-heavy GitHub sources:

bash
pnpm compat-hunter -- --sources github --github-repos ephtracy/voxel-model@master:vox/,mikelovesrobots/mmmm@master:vox/ --max-models 1000

Local directory:

bash
pnpm compat-hunter -- --sources local --local-root /tmp/models --max-models 1000

Keep known-warning files too:

bash
pnpm compat-hunter -- --keep-known --max-models 500

For STL hunts, --keep-known keeps warning-only models under known/ and the report includes warningCategoriesByKind plus stlDiagnostics on retained rows. Unknown STL warning text, throws, zero-polygon outputs, and suspicious DOM collapses remain interesting/.

Avoid repeating the same shuffled queue:

bash
pnpm compat-hunter -- --sources thingi10k --exts stl --max-models 5000 --seed "$(date +%s)" --queue-offset 5000

Skip models already attempted by prior reports:

bash
pnpm compat-hunter -- --sources thingi10k --exts stl --max-models 5000 --skip-report bench/results/<previous-run>/report.json

Continue after interesting cases:

bash
pnpm compat-hunter -- --no-stop-on-interesting --max-models 2000

Reporting

Summarize the final report.json with:

bash
pnpm compat-hunter -- --report bench/results/<run>/report.json

In the final response, state the attempted/parsed counts, whether any interesting files were retained, and whether the findings are actionable. Do not imply a clean stream proves full compatibility; it only means this pass found no new actionable parser issue.

© layoutit, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in .agents/skills/compat-hunter of layoutit/polycss.

  • SKILL.md
  • agents/openai.yaml
  • scripts/compat-hunter.mjs

Open the folder on GitHubat commit 04a1b66

Compare with similar skills

Compat Hunter 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.

Compat Hunter compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Compat Hunter this skilllayoutit/polycss757—~999Automated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Diagnosing Superpowers Sessionsobra/superpowers296k3 repos~1.7kAutomated safety check: PassMIT
GitHub Deep Researchbytedance/deer-flow83k5 repos~1.3kAutomated safety check: PassMIT
Greplooponyx-dot-app/onyx32k4 repos~3.3kAutomated safety check: PassMIT
Update V8 Versionopeninterpreter/openinterpreter69k2 repos~845Automated safety check: PassApache-2.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.

    296k GitHub starsUsed in 3 repos~1.7k tokens
    Agent WorkflowsAuto-check passed
  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    83k GitHub starsUsed in 5 repos~1.3k tokens
    Research & ScienceAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed
  • Update V8 Version

    openinterpreter/openinterpreter

    Bumps the pinned v8 and rusty_v8 versions in Codex, validates the release-candidate path with the v8-canary check, and traces failures to upstream build changes.

    69k GitHub starsUsed in 2 repos~845 tokens
    DevOps & CloudAuto-check passed
  • Check PR

    onyx-dot-app/onyx

    Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions.

    32k GitHub starsUsed in 2 repos~2.3k tokens
    DevelopmentAuto-check passed

More from layoutit/polycss

  • Chrome Trace

    layoutit/polycss

    Capture and analyze Chrome/Chromium performance traces with Playwright around a concrete browser interaction.

    757 GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check passed
  • Polycss

    layoutit/polycss

    Build PolyCSS scenes that render 3D meshes, primitive shapes, or custom polygons as DOM/CSS polygon elements.

    757 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about Compat Hunter

What does Compat Hunter do?

A skill your agent uses when hunting for OBJ/GLB/glTF/VOX parser compatibility issues by streaming candidate models, parsing each immediately, deleting clean files, and retaining only actionable…. Compat Hunter is an agent skill from layoutit/polycss. Use when hunting for OBJ/GLB/glTF/VOX parser compatibility issues by streaming candidate models, parsing each immediately, deleting clean files, and retaining only actionable failures, unknown warnings, or unexplained zero-polygon outputs.

When should I use Compat Hunter?

Compat Hunter fits situations like: hunting for OBJ/GLB/glTF/VOX parser compatibility issues by streaming candidate models; parsing each immediately; deleting clean files; retaining only actionable failures.

How do I install Compat Hunter in Claude Code?

Run `npx skills add layoutit/polycss --skill compat-hunter -a claude-code`. Or copy the skill folder (.agents/skills/compat-hunter in layoutit/polycss) into .claude/skills/compat-hunter in your project. Claude Code loads it when a task matches its description.

How do I install Compat Hunter in Codex?

Run `npx skills add layoutit/polycss --skill compat-hunter -a codex`. Or copy the skill folder (.agents/skills/compat-hunter in layoutit/polycss) into .agents/skills/compat-hunter in your project. Codex loads it when a task matches its description.

Can I use Compat Hunter 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 layoutit/polycss --skill compat-hunter -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/compat-hunter, .gemini/skills/compat-hunter, .github/skills/compat-hunter and .opencode/skills/compat-hunter in your project.

What does Compat Hunter need to run?

Going by SKILL.md and its folder, Compat Hunter needs JavaScript for the scripts in its folder and the command-line tools its instructions call (pnpm and node). Our summary lists: Node.js.

Does Compat Hunter 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 Compat Hunter 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Compat Hunter use?

Compat Hunter is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Compat Hunter use?

About 999 tokens (SKILL.md is roughly 4k 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 Compat Hunter?

Skills that share tags, products or a category with Compat Hunter: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Diagnosing Superpowers Sessions (obra/superpowers, 296k stars), GitHub Deep Research (bytedance/deer-flow, 83k stars) and Greploop (onyx-dot-app/onyx, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Compat Hunter?

layoutit (a GitHub organization) maintains it in layoutit/polycss, which has 757 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on August 25, 2026.

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