Skip to content

Repository files navigation

awesome-skill-generate

Turn notebook knowledge into reusable agent work.

The manifesto for making agent-generated skills actually usable.

Turn notebooks, tutorials, and one-off workflows into reusable, source-grounded, reviewable agent skills.

GitHub stars GitHub last commit Python Tests Meta Skills Notebook to Skill Source Grounded Empirical Scoring README

Get Started · View Example · Read Score Report · Codex Tutorial · Claude Code Tutorial · 中文 README

Quick Start · Tutorials · At A Glance · Benchmark Snapshot · Repository Layout · Example · Contributing


Warning

Default agents can already generate skills. Most of those skills are not reusable. This repository exists to change that.

Why Builders Use This

If you are turning domain knowledge into AI products, internal automations, or reusable agent workflows, this repo gives you a path from:

  • notebook
  • prompt
  • transcript
  • one-off demo

to:

  • reusable skill
  • reviewable artifact
  • scored deliverable
  • standardizable unit of agent work

The Problem We Are Solving

Most agent-generated skills fail in predictable ways:

  • they summarize notebook prose instead of extracting a stable job
  • they document only the branch that happened to run once
  • they skip live checks against source code, signatures, help text, or CLI flags
  • they have weak validation and no reviewer-side execution evidence
  • they are hard to maintain because workflow, references, and evidence are all mixed together

awesome-skill-generate is designed to fix those failure modes.

What Makes This Repo Different

Source-Grounded

The generator pushes the agent to inspect real source code, inspect.signature(...), help(...), and -h/--help before documenting behavior.
Branch-Aware

It checks branch-heavy selectors such as method, recipe, backend, and mode so one notebook path is not mistaken for the whole interface.
Evidence-Backed

It does not stop at text quality. Skills are reviewed with validation rules, acceptance contracts, and reviewer-side empirical checks when the workflow is data-sensitive.
Structured Artifacts

The output is split into SKILL.md, references/, assets/, and optionally scripts/ instead of dumping everything into one bloated file.
Human-Visible Reports

The scorer produces a readable report with commands, evidence, weighted scores, residual risks, and a short reason under each dimension score.
Standard-Driven

This repo pushes capability-first naming, environment-agnostic skill content, and explicit split-vs-single-skill decisions instead of notebook-shaped output.

Quick Start

Tip

If you want the fastest path to value, start from one notebook with a clear stable task, generate one skill, score it, and inspect the report before scaling out.

  1. Open this repository in Codex or Claude Code.
  2. Pick a notebook you want to convert.
  3. Ask the agent to use skill-authoring and write to examples/generated-skills/<skill-name>/.
  4. Ask it to review the result with skill-quality-scorer.
  5. Run validation and acceptance.

Example request:

Use the skill-authoring skill in this repository to convert /absolute/path/to/notebook.ipynb into a reusable skill.

Requirements:
1. Write the output to examples/generated-skills/<skill-name>/
2. Do not just summarize the notebook
3. Check real source code, inspect.signature, help, or -h/--help
4. Inspect branch-heavy parameters such as method, recipe, backend, and mode
5. If the notebook mixes multiple independent jobs, split it into multiple skills or justify why one skill boundary is better
6. Do not put local absolute source paths, python interpreter paths, or local environment names into SKILL.md or references
7. For long-running or GPU-heavy steps, validate a representative smoke path unless a full run is explicitly required
8. Review the generated result with skill-quality-scorer
9. Write a score report in the current directory, with a short reason under each dimension score
10. Run validate and acceptance

Tutorials

English

中文

At A Glance

Notebook / Tutorial / Workflow
            |
            v
   skill-authoring
            |
            v
Generated Skill Directory
(SKILL.md + references + assets)
            |
            v
 skill-quality-scorer
            |
            v
Score Report + Validation + Acceptance

Default Agent Output vs. This Repo

Dimension Typical default agent output awesome-skill-generate
Goal Summarize the notebook Build a reusable skill
API handling Uses what the notebook happened to show Checks live source, signatures, help, and branches
Validation Light or missing Explicit validation and acceptance
Data workflows Often text-only review Reviewer-side empirical execution when needed
Artifact shape One big document SKILL.md + references/ + assets/ + optional scripts/
Human trust Implicit Report-backed
Maintenance Drift-prone Traceable and updateable

Benchmark Snapshot

Measured example in this repository:

Weighted Score Verdict Execution Clarity Empirical Executability

Source Grounded Branch Aware Report Backed

Note

The benchmark shown here is based on the repository's current dynamo-preprocess example skill and its linked score report.

Important

The default-agent baseline below is an illustrative rubric-based profile, not a separately versioned benchmark artifact. It is meant to show the failure modes this repository is trying to eliminate.

Comparison baseline used below:

  • a typical default agent output that mostly summarizes a notebook
  • does not do full source-grounding or reviewer-side empirical validation
  • this baseline is an illustrative rubric-based profile, not a separately versioned benchmark artifact

Weighted Score Comparison

Typical default agent skill      38/100  [########------------]
awesome-skill-generate example   95/100  [###################-]

Dimension Breakdown

Dimension                  Default Agent   This Repo Example
Trigger Precision          3/5  ###--      5/5  #####
Execution Clarity          2/5  ##---      5/5  #####
Validation Strength        1/5  #----      4/5  ####-
Empirical Executability    1/5  #----      5/5  #####
Context Efficiency         3/5  ###--      4/5  ####-
Reusability                2/5  ##---      5/5  #####
Resource Partitioning      2/5  ##---      5/5  #####
Compatibility Robustness   1/5  #----      5/5  #####
Maintainability            2/5  ##---      5/5  #####

What Those Gains Actually Mean

The gains are not aesthetic. They come from four concrete upgrades:

  • source-grounding against live APIs instead of notebook memory
  • branch coverage for method / recipe / backend style selectors
  • reviewer-side empirical execution checks for data workflows
  • a structured artifact layout that remains maintainable as upstream code changes

The Standard We Want To Set

This repository is not just a prompt collection. It is trying to make skill generation auditable, comparable, and standardizable.

The standard is simple:

  1. A skill must define a stable capability, not mirror a tutorial title, sample dataset, or organism name.
  2. If a notebook mixes multiple independently triggerable jobs, the generator should split them into multiple skills unless one shared boundary is clearly better.
  3. A skill must include a trigger contract, execution spine, and validation contract.
  4. Concrete API or CLI claims should be grounded in live source, signatures, help text, or CLI help.
  5. Branch-heavy parameters must be checked for coverage, not inferred from a single notebook path.
  6. Reusable skill content should stay environment-agnostic; local review configuration does not belong in SKILL.md or references/.
  7. Generated documentation should use repo-relative paths or import paths instead of machine-specific absolute paths.
  8. Long-running or GPU-heavy workflows should usually be validated with a representative smoke path inside a bounded review budget, not by defaulting to a full expensive run.
  9. Data workflows should be reviewable with reviewer-side execution evidence when needed.
  10. The artifact layout should be explicit: SKILL.md, references/, assets/, and optionally scripts/.
  11. A score report should be visible to humans and should include commands, evidence, residual risks, and a short reason under each dimension score.
  12. Quality should be measured with a rubric, not with vibes.

If enough generated skills follow these rules, skill generation stops being ad hoc prompt craft and starts looking like an engineering discipline.

Core Meta-Skills

Repository Layout

awesome-skill-generate/
├── README.md
├── README.zh.md
├── codex-tutorial-en.md
├── codex-tutorial-zh.md
├── claude-code-tutorial-en.md
├── claude-code-tutorial-zh.md
├── skills/
│   ├── skill-authoring/
│   └── skill-quality-scorer/
├── examples/
│   └── generated-skills/
├── scripts/
└── tests/

Example

This repository includes a notebook-derived example skill:

Source notebook:

  • docs/tutorials/notebooks/100_tutorial_preprocess.ipynb

Example score report:

Common Commands

Validate skills:

python3 scripts/validate_skills.py --root all

Run acceptance:

python3 scripts/run_skill_acceptance.py --root all

Run tests:

python3 -m unittest discover -s tests -v

Inspect a Python interface:

python3 scripts/inspect_python_interface.py dynamo.preprocessing:Preprocessor --pretty

Principles

  • A skill is not a notebook summary
  • A skill should be capability-first, not dataset-first
  • Source code is more authoritative than tutorial memory
  • Branch-heavy parameters must be checked for coverage
  • Complex notebooks may need to be split into multiple skills
  • Reusable skill docs should stay environment-agnostic
  • Long-running workflows should use representative smoke validation by default
  • Scoring should not rely on text alone when empirical execution is needed

Contributing

Contributions of all types are more than welcome. Whether it is publishing skills, improving the generator, refining the scorer, tightening the benchmark story, or contributing code, feel free to check out our GitHub Issues and start building.

License

This project is BSD 2-Clause licensed.

Copyright

Copyright © 2026 Qiu Lab.

About

No description, website, or topics provided.

Resources

Stars

11 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages