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

Clawpathy Autoresearch

by ClawBio in ClawBio/ClawBio

Eval-driven skill tuning. An agent skill from ClawBio/ClawBio.

MITAuto-check passedAI & LLM Engineering

Install Clawpathy Autoresearch

skills CLI
$ npx skills add ClawBio/ClawBio --skill clawpathy-autoresearch -a claude-code

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

GitHub CLI
$ gh skill install ClawBio/ClawBio clawpathy-autoresearch --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/ClawBio/ClawBio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/clawpathy-autoresearch .claude/skills/clawpathy-autoresearch && 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
clawpathy-autoresearch
GitHub stars
1.2k
Token cost
~1.4k tokens
SKILL.md length
454 words
Files
27
Skills in repo
104
Repo updated
First seen
Licence
MIT

At a glance

Eval-driven skill tuning. An agent skill from ClawBio/ClawBio.

  • Works in 4 steps: Scout → Scope (you + user) → Build → …
  • Tasks that involve LLM evaluation
  • SKILL.md covers Core idea, You are the orchestrator, Workspace layout and Key principles, plus 2 more sections
  • Runs Python scripts from its folder; calls python

What it does

Clawpathy Autoresearch is an agent skill from ClawBio/ClawBio. Eval-driven skill tuning. Given a task and an LLM-judge rubric, iteratively rewrites a SKILL.md until a downstream executor agent performs well against the judge. Low-code: all evaluation is LLM-as-judge, not deterministic Python.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 30 other files (for example `__init__.py`, `__main__.py` and `dispatcher.py`).

It sits in AI & LLM Engineering, covering LLM evaluation, Autonomous loops and Quizzes and assessments. It works with Python. The repository describes itself as: 🦖 ClawBio - The first bioinformatics-native AI agent skill library. Local-first. Reproducible. Open. Free. The licence is MIT.

When your agent uses it

  • Tasks that involve LLM evaluation
  • Tasks that involve Autonomous loops
  • Tasks that involve Quizzes and assessments

Example prompts

  • “/clawpathy-autoresearch”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Scout
  2. Scope (you + user)
  3. Build
  4. Loop

What it can do on your machine

Read from SKILL.md and the folder at commit dece754. 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 script files (Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    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

Clawpathy Autoresearch loads about 1.4k tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 454 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~63
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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

The full file from ClawBio/ClawBio at commit dece754, republished under its MIT licence (© ClawBio). 454 words, ~1,364 tokens.

Download SKILL.mdSave it as .claude/skills/clawpathy-autoresearch/SKILL.md (or your agent's skills folder). This skill also uses 26 other files; get the full folder from GitHub.
name
clawpathy-autoresearch
description
Eval-driven skill tuning. Given a task and an LLM-judge rubric, iteratively rewrites a SKILL.md until a downstream executor agent performs well against the judge. Low-code: all evaluation is LLM-as-judge, not deterministic Python.
license
MIT
metadata.author
Jay Moore
metadata.tags
meta, autoresearch, skill-tuning, llm-judge, eval-driven
metadata.version
1.0.0

clawpathy-autoresearch

Eval-driven skill development. The system iteratively rewrites a SKILL.md so a downstream executor agent performs better at a task class, as judged by an LLM against a paper/task-specific rubric.

Core idea

  propose (sonnet)  →  execute (sonnet, shell)  →  judge (opus, rubric)
       ↑                                                       │
       └──────── feedback: verdict + recommended edits ────────┘
  • Proposer rewrites SKILL.md based on the last judge verdict.
  • Executor runs the new SKILL.md end-to-end inside a workspace.
  • Judge scores methodology (primary) and outputs (secondary) against a per-task rubric. Lower is better; 0 = perfect.
  • Keep the new SKILL.md only if it strictly beats the best score; else revert. Stop on target_score or on early_stop_n consecutive regressions.

You are the orchestrator

You (the agent reading this) don't run the loop yourself. You dispatch subagents to build the workspace, then hand off to the Python loop.

Phase 1 — Scout

Dispatch a subagent with prompts/scout.md to research the paper/task. Report key findings to the user in a few lines.

Phase 2 — Scope (you + user)

Have a conversation. Ask ONE question at a time, multiple-choice where helpful. Agree on:

  • what to reproduce / what success looks like
  • which data sources are in-bounds
  • what methodology expectations belong in the rubric
  • iteration budget and target_score (if any)

Present a summary and get approval.

Phase 3 — Build

Dispatch a builder subagent with prompts/builder.md and the agreed scope. It writes:

  • task.json
  • rubric.md — the authoritative scoring rubric for the LLM judge
  • reference/ (optional; judge-only)
  • skill/SKILL.md — seed

Validate:

python
from skills.clawpathy_autoresearch import validate_workspace
print(validate_workspace(Path("WORKSPACE")))  # [] means valid
Phase 4 — Loop
bash
python -m skills.clawpathy_autoresearch WORKSPACE_DIR
# or with custom models:
python -m skills.clawpathy_autoresearch WORKSPACE_DIR \
  --proposer-model sonnet --executor-model sonnet --judge-model opus

The loop streams progress to WORKSPACE/history.jsonl, snapshots every iteration's skill to WORKSPACE/snapshots/iter-NNN.md, and writes the executor's full transcript to WORKSPACE/executor_runs/iter-NNN.log.

Workspace layout

workspace/
  task.json                  # task metadata + loop knobs
  rubric.md                  # LLM-judge rubric (the heart of the system)
  reference/                 # optional ground truth, judge-only
  skill/SKILL.md             # iterated by the loop
  output/                    # executor outputs (cleared each iter)
  executor_runs/iter-NNN.log # transcripts (judge reads these)
  snapshots/iter-NNN.md      # per-iter SKILL.md snapshots
  history.jsonl              # one row per iter: score, kept, verdict
Show full SKILL.md (210 more words)Show less

Key principles

  • LLM judge only. No deterministic Python scorers. All evaluation goes through judge.md + opus. This keeps the system low-code and lets the rubric carry paper-specific nuance without adding code.
  • Methodology is primary. The rubric weights "did the agent use sound methods?" above "did the numbers match?". Ground-truth match is a signal, not the objective — the goal is better SKILL.md files.
  • Never leak ground truth. reference/ is judge-only. The executor prompt says not to read it, and the judge penalises leakage.
  • No hardcoded answers in SKILL.md. The proposer prompt and the judge both enforce this. The executor must derive results by running methods.
  • Snapshots + strict-better revert. Score on the first iter becomes the floor. Later iters that tie or regress revert to the best.

Safety

  • All processing is local except scout web fetches for public resources.
  • ClawBio disclaimer: research/education tool, not a medical device.

Gotchas

  • Do not skip scoping. The rubric is paper-specific; a generic rubric tunes nothing. Get the user to agree on methodology expectations.
  • Do not write a Python scorer. Earlier versions of this project did. They rewarded API-fetching, not methodology. The judge is the scorer.
  • Do not hand-pick the "best" snapshot yourself. Trust the loop. If the judge is calibrated wrong, fix the rubric, not the history.

© ClawBio, 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 26 other files in skills/clawpathy-autoresearch of ClawBio/ClawBio.

  • SKILL.md
  • .gitignore
  • __init__.py
  • __main__.py
  • dispatcher.py
  • examples/champions/README.md
  • examples/champions/trubetskoy_scz_finemap_0.235.md
  • examples/champions/yengo_height_ldsc_h2.md
  • examples/demo_task/README.md
  • examples/demo_task/rubric.md
  • examples/demo_task/skill/SKILL.md
  • examples/demo_task/task.json
  • examples/presentation_intro.md
  • examples/skill_transfer_summary.png
  • executor.py
  • judge.py
  • loop.py
  • … and 10 more

Open the folder on GitHubat commit dece754

Compare with similar skills

Clawpathy Autoresearch 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.

Clawpathy Autoresearch compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Clawpathy Autoresearch this skillClawBio/ClawBio1.2k—~1.4kAutomated safety check: PassMIT
Promptfoo Evaluationdaymade/claude-code-skills1.4k—~3kAutomated safety check: PassMIT
Author Skillericrisco/rsc-harness180—~4.3kAutomated safety check: PassMIT
Advanced Evaluationguanyang/open-agent-hub9772 repos~4.2kAutomated safety check: PassMIT
A-Evolve Agent EvolutionOrchestra-Research/AI-Research-SKILLs13k—~3.6kAutomated safety check: PassMIT
Agentic Evalgithub/awesome-copilot40k3 repos~1.5kAutomated safety check: PassMIT

Similar skills

  • Promptfoo Evaluation

    daymade/claude-code-skills

    Configures and runs LLM evaluation using Promptfoo framework.

    1.4k GitHub stars~3k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Author Skill

    ericrisco/rsc-harness

    A skill your agent uses when authoring a NEW rsc skill or editing an existing one — scoping it to one job, writing the description that decides whether it ever loads, splitting the body into…

    180 GitHub stars~4.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Advanced Evaluation

    guanyang/open-agent-hub

    This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring, and automated…

    977 GitHub starsUsed in 2 repos~4.2k tokens
    AI & LLM EngineeringAuto-check passed

  • A-Evolve Agent Evolution

    Orchestra-Research/AI-Research-SKILLs

    Guidance for using A-Evolve to improve an AI agent automatically, evolving its prompts, skills and memory against a benchmark through solve, observe and evolve cycles.

    13k GitHub stars~3.6k tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed

  • Agentic Eval

    github/awesome-copilot

    Official

    Patterns and techniques for evaluating and improving AI agent outputs.

    40k GitHub starsUsed in 3 repos~1.5k tokens
    AI & LLM EngineeringAuto-check passed

  • Woo AI Smoke

    woocommerce/woocommerce-ios

    Evaluate WooAIAssistant against a structured scenario suite with hard invariants + LLM-as-judge rubric scoring.

    358 GitHub stars~7.4k tokensUpdated yesterday
    EducationAuto-check: notes

More from ClawBio/ClawBio

All 104 skills in this repo

  • Eqtl Catalogue Region Fetch

    ClawBio/ClawBio

    Fetch a region of cis-eQTL summary statistics from EBI eQTL Catalogue v7+ via tabix-on-FTP.

    1.2k GitHub starsUsed in 1 repo~4.7k tokens
    Auto-check passed

  • Xena Tcga Gene Query

    ClawBio/ClawBio

    Query TCGA tumor biology through the ucscxenatoolspy API. An agent skill from ClawBio/ClawBio.

    1.2k GitHub stars~4.7k tokensUpdated yesterday
    Auto-check passed

  • Gwas Catalog Region Fetch

    ClawBio/ClawBio

    Fetch a region of GWAS summary statistics from the NHGRI-EBI GWAS Catalog harmonised collection via tabix-on-FTP.

    1.2k GitHub starsUsed in 1 repo~3.5k tokens
    Auto-check passed

  • Dnasp

    ClawBio/ClawBio

    Population genetics of pre-aligned DNA sequences or multi-sample VCFs using selected DnaSP 6 methods.

    1.2k GitHub stars~5.1k tokensUpdated yesterday
    Auto-check passed

  • Ld 1000g Region Compute

    ClawBio/ClawBio

    Compute pairwise r² between a lead variant and every variant in a window using the 1000 Genomes Phase 3 GRCh38 reference panel, ancestry-stratified.

    1.2k GitHub stars~3.9k tokensUpdated yesterday
    Auto-check passed

  • Ncbi Datasets

    ClawBio/ClawBio

    Download genomes, genes, virus sequences, and taxonomy data from NCBI using the datasets and dataformat CLI tools.

    1.2k GitHub starsUsed in 1 repo~2.8k tokens
    Auto-check passed

Works with

Categories

Questions about Clawpathy Autoresearch

What does Clawpathy Autoresearch do?

Eval-driven skill tuning. An agent skill from ClawBio/ClawBio. Clawpathy Autoresearch is an agent skill from ClawBio/ClawBio. Eval-driven skill tuning.

When should I use Clawpathy Autoresearch?

Clawpathy Autoresearch fits situations like: tasks that involve LLM evaluation; tasks that involve Autonomous loops; tasks that involve Quizzes and assessments.

How do I install Clawpathy Autoresearch in Claude Code?

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

How do I install Clawpathy Autoresearch in Codex?

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

Can I use Clawpathy Autoresearch 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 ClawBio/ClawBio --skill clawpathy-autoresearch -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/clawpathy-autoresearch, .gemini/skills/clawpathy-autoresearch, .github/skills/clawpathy-autoresearch and .opencode/skills/clawpathy-autoresearch in your project.

What does Clawpathy Autoresearch need to run?

Going by SKILL.md and its folder, Clawpathy Autoresearch needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Clawpathy Autoresearch 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 Clawpathy Autoresearch 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 Clawpathy Autoresearch use?

Clawpathy Autoresearch is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Clawpathy Autoresearch use?

About 1.4k tokens (SKILL.md is roughly 5.5k 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 Clawpathy Autoresearch?

Skills that share tags, products or a category with Clawpathy Autoresearch: Promptfoo Evaluation (daymade/claude-code-skills, 1.4k stars), Author Skill (ericrisco/rsc-harness, 180 stars), Advanced Evaluation (guanyang/open-agent-hub, 977 stars) and A-Evolve Agent Evolution (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Clawpathy Autoresearch?

ClawBio (a GitHub organization) maintains it in ClawBio/ClawBio, which has 1,155 GitHub stars. The repository holds 104 skills in this directory. The repository was last updated on October 9, 2026.

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