New: 98,000+ 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

Astrea

by warpfront in warpfront/hipfire

A skill your agent uses for hipfire quant calibration, imatrix-driven experiments, KLD/PPL quality evaluation, k-map/format selection, MQ/HFQ/HFP/MFP tradeoff work, ParoQuant-style weight transform…

Custom licenceAuto-check passedAI & LLM Engineering

Install Astrea

skills CLI
$ npx skills add warpfront/hipfire --skill astrea -a claude-code

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

GitHub CLI
$ gh skill install warpfront/hipfire astrea --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/warpfront/hipfire.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/astrea .claude/skills/astrea && 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
astrea
GitHub stars
653
Token cost
~2.6k tokens
SKILL.md length
897 words
Files
2
Skills in repo
9
Repo updated
First seen
Licence
Custom licence

At a glance

A skill your agent uses for hipfire quant calibration, imatrix-driven experiments, KLD/PPL quality evaluation, k-map/format selection, MQ/HFQ/HFP/MFP tradeoff work, ParoQuant-style weight transform…

  • Works in 7 steps: No quality claim without measured… → No ship-ready claim without runtime… → bundle-plan is a package contract… → …
  • Hipfire quant calibration
  • SKILL.md covers Reach for this when, Canonical owners (read these;…, Core rules and CLI surface, plus 4 more sections
  • Calls python3

What it does

Astrea is an agent skill from warpfront/hipfire. Use for hipfire quant calibration, imatrix-driven experiments, KLD/PPL quality evaluation, k-map/format selection, MQ/HFQ/HFP/MFP tradeoff work, ParoQuant-style weight transform planning, and KV policy planning. Use when deciding whether a calibrated model candidate should be promoted, rejected, packaged, or sent through Atlas for AR/DFlash perf validation.

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in AI & LLM Engineering, covering Performance reviews and LLM inference and serving. The repository describes itself as: RDNA-native LLM inference engine in Rust.

When your agent uses it

  • Hipfire quant calibration
  • Imatrix-driven experiments
  • KLD/PPL quality evaluation
  • K-map/format selection

Example prompts

  • “/astrea”

Requirements

  • Python 3

Workflow steps

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

  1. No quality claim without measured KLD/PPL (or an explicit blocked eval
  2. No ship-ready claim without runtime compatibility + perf evidence on
  3. bundle-plan is a package contract artifact, not a model writer. Do
  4. Do not invent gates. Pick routes from docs/VALIDATION.md. There is
  5. **Do not compare KLD/PPL across different engine fingerprints or RoPE
  6. Non-finite logits fail the candidate. Reject KLD=0 rows unless the
  7. Admissions stay machine-recorded only in docs/admissions.yml. A green

What it can do on your machine

Read from SKILL.md and the folder at commit 0f999cb. 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:

    • python3

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

  • Network

    No URLs in SKILL.md.

    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

Astrea loads about 2.6k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 897 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~92
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 897 words (~2,602 tokens).

“Agent-native calibration harness for hipfire quant candidates. The executable is python3 scripts/astrea.py. It emits JSON plan/policy/metrics artifacts; you supply experiment judgment and promotion discipline.”

— opening of SKILL.md by warpfront, Custom licence
name
astrea

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in .agents/skills/astrea of warpfront/hipfire.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 0f999cb

Compare with similar skills

Astrea 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.

Astrea compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Astrea this skillwarpfront/hipfire653—~2.6kAutomated safety check: PassCustom licence
Quark Onnx Autosearch Proamd/Quark181—~3.4kAutomated safety check: PassMIT
Quark Onnx Quant Planamd/Quark181—~4.8kAutomated safety check: PassMIT
Add Vlm Modelintel/auto-round1.6k—~2.4kAutomated safety check: PassApache-2.0
Quark Onnx Skill Syncamd/Quark181—~3.3kAutomated safety check: PassMIT
Tensorrt Optimizationmajiayu000/claude-skill-registry6661 repos~2.4kAutomated safety check: NotesMIT

Similar skills

  • Quark Onnx Autosearch Pro

    amd/Quark

    L3 recipe that runs quark.onnx.AutoSearchPro end-to-end on a user .onnx model: intake → preset selection (or custom search space) → calibration / eval data reader → standalone autosearch script…

    181 GitHub stars~3.4k tokensUpdated 10 days ago
    AI & LLM EngineeringAuto-check passed

  • Quark Onnx Quant Plan

    amd/Quark

    Build a Quark ONNX PTQ quantization plan from modelanalysis.json and user intent.

    181 GitHub stars~4.8k tokensUpdated 10 days ago
    AI & LLM EngineeringAuto-check passed

  • Add Vlm Model

    intel/auto-round

    Official

    Add support for a new Vision-Language Model (VLM) to AutoRound, including multimodal block handler, calibration dataset template, and special model handling.

    1.6k GitHub stars~2.4k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Quark Onnx Skill Sync

    amd/Quark

    Detect upstream Quark ONNX changes that affect the ONNX skill family and classify required updates.

    181 GitHub stars~3.3k tokensUpdated 10 days ago
    AI & LLM EngineeringAuto-check passed

  • Tensorrt Optimization

    majiayu000/claude-skill-registry

    NVIDIA TensorRT model optimization and deployment. An agent skill from majiayu000/claude-skill-registry.

    666 GitHub starsUsed in 1 repo~2.4k tokens
    AI & LLM EngineeringAuto-check: notes

  • Quark Onnx Debug

    amd/Quark

    Diagnose failed Quark ONNX installation, calibration, quantization, custom-op compilation, or export attempts.

    181 GitHub stars~4.8k tokensUpdated 10 days ago
    AI & LLM EngineeringAuto-check passed

More from warpfront/hipfire

All 9 skills in this repo

  • Hipfire Autoheal

    warpfront/hipfire

    Triage and repair hipfire runtime failures such as daemon hangs, stale serve.pid, port 11435 conflicts, ROCm include-path problems, missing precompiled kernels, VRAM OOM, kernel JIT failures, and…

    653 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Hipfire Diag

    warpfront/hipfire

    Run and interpret hipfire GPU diagnostics for ROCm/HIP bring-up, missing kernels, testkernels failures, inference smoke failures, and install/runtime environment problems.

    653 GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Hipfire Kernel Atlas

    warpfront/hipfire

    Use Kernel Atlas to collect phase-aware hipfire measurements and render ISA Fit View visualizations for AMD GPU kernels, quant formats, and architectures.

    653 GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • Hipfire Tester

    warpfront/hipfire

    Guide a tester through hipfire bring-up, serve smoke, claim-scoped harnesses, and benchmark reporting on AMD RDNA/CDNA GPUs.

    653 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Rebase Onto Modular

    warpfront/hipfire

    A skill your agent uses when porting a hipfire feature/fix branch authored against pre-0.1.20 master onto post-modular master.

    653 GitHub stars~2.2k tokensUpdated today
    Auto-check passed

  • Hipfire Arch Port

    warpfront/hipfire

    Port hipfire compute kernels to a new RDNA / CDNA architecture (gfx1201/gfx1200/gfx94x/gfx1150/etc.).

    653 GitHub stars~1.6k tokensUpdated today
    Auto-check passed

Categories

Questions about Astrea

What does Astrea do?

A skill your agent uses for hipfire quant calibration, imatrix-driven experiments, KLD/PPL quality evaluation, k-map/format selection, MQ/HFQ/HFP/MFP tradeoff work, ParoQuant-style weight transform…. Astrea is an agent skill from warpfront/hipfire. Use for hipfire quant calibration, imatrix-driven experiments, KLD/PPL quality evaluation, k-map/format selection, MQ/HFQ/HFP/MFP tradeoff work, ParoQuant-style weight transform planning, and KV policy planning.

When should I use Astrea?

Astrea fits situations like: hipfire quant calibration; imatrix-driven experiments; KLD/PPL quality evaluation; K-map/format selection.

How do I install Astrea in Claude Code?

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

How do I install Astrea in Codex?

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

Can I use Astrea 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 warpfront/hipfire --skill astrea -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/astrea, .gemini/skills/astrea, .github/skills/astrea and .opencode/skills/astrea in your project.

What does Astrea need to run?

Going by SKILL.md and its folder, Astrea needs the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Astrea 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 Astrea 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 Astrea use?

Astrea has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Astrea use?

About 2.6k tokens (SKILL.md is roughly 10k 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 Astrea?

Skills that share tags, products or a category with Astrea: Quark Onnx Autosearch Pro (amd/Quark, 181 stars), Quark Onnx Quant Plan (amd/Quark, 181 stars), Add Vlm Model (intel/auto-round, 1.6k stars) and Quark Onnx Skill Sync (amd/Quark, 181 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Astrea?

warpfront (a GitHub organization) maintains it in warpfront/hipfire, which has 653 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 8, 2026.

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