DEDUPED Hot AI repos, turned into use cases Get 5 a day

What you can do with Wikiskill

WikiSkill is a Python framework that lets an AI agent turn its past runs into a persistent wiki and evolve its own skills, keeping only changes that score better on held-out tasks.

Trended earlier

ashutoshsinghpr7/wikiskill on GitHub

Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk.

What do you want to do?

5 use cases

  • Evolve an agent's skills from its own task traces

    Run the full WikiSkill loop so the agent distills failures into a wiki and gates skill changes.

    View prompt
    Use the ashutoshsinghpr7/wikiskill repo to create a demo workspace with `wikiskill init demo`, then run `wikiskill evolve --iters 3`. Report the baseline score from `wikiskill status` and whether each proposal was kept or rolled back. Verify that the wiki folder still contains its pattern pages after the run.

  • Test whether an evolved skill actually improved results

    Use paired per-task comparison with an exact binomial p-value to judge a skill change.

    View prompt
    In the ashutoshsinghpr7/wikiskill repo, run `wikiskill compare` on the demo workspace after an evolve run. Report the per-task wins, losses, ties and the two-sided exact-binomial p-value. Verify that the comparison used the same validation tasks for both the baseline and the evolved skills.

  • Run the WikiSkill loop with Claude Code as the agent

    Pin a workspace to the Claude backend and evolve skills using Claude Code runs.

    View prompt
    Using the ashutoshsinghpr7/wikiskill repo, run `wikiskill init demo --backend claude`, then `wikiskill evolve --iters 2`. Report the baseline and final validation scores and the backend in workspaces/demo/workspace.json. Verify that the workspace file names the claude backend before the evolve run starts.

  • Evolve skills on a custom task set you write

    Write tasks.json with auto-graded checks and run the loop on your own agent work.

    View prompt
    In the ashutoshsinghpr7/wikiskill repo, add my tasks.json with train and val splits and at least one task per grader type I use. Run `wikiskill evolve --iters 2` and report the baseline score and any rejected proposals. Verify that every task has a grader and that missing deliverables score 0 rather than crashing.

  • Install the distilled Hermes skills from the WikiSkill tap

    Add the WikiSkill skills tap to Hermes and install the patterns from live runs.

    View prompt
    Using the ashutoshsinghpr7/wikiskill repo as a Hermes skills tap, add the tap and install the skills search-miss-binary and script-exec-blocked. Report which skills were installed. Verify that each skill name appears in the Hermes skill list after the install.

How to use Wikiskill

  1. Check you have what it needs: Python 3.10 or newer; Hermes Agent installed as the reference backend, or another supported agent CLI (Claude Code, Codex or GitHub Copilot CLI); A configured default model for the agent, for example through OpenRouter using --model and --provider.
  2. Open ashutoshsinghpr7/wikiskill on GitHub and read the README and license.
  3. Run pip install wikiskill to install the package from PyPI.
  4. Run wikiskill init demo to create the workspace and the 22-task demo bench (13 train, 9 validation).
  5. Run wikiskill status to see the baseline scores, skills, wiki and history.
  6. Run wikiskill evolve --iters 3 to start the full Algorithm 1 loop with your default model.

These steps come from our top use case, Evolve an agent's skills from its own task traces, which also has a copy-paste agent prompt.

Wikiskill alternatives · Best AI repos for Software and DevOps

About this repo

Requirements

  • Python 3.10 or newer
  • Hermes Agent installed as the reference backend, or another supported agent CLI (Claude Code, Codex or GitHub Copilot CLI)
  • A configured default model for the agent, for example through OpenRouter using --model and --provider
  • Enough API budget for several iterations (the README cites about $0.09 per iteration on one free-tier run)
Maintain Wikiskill? Add the Featured on Deduped badge

Paste this into your README:

[![Featured on Deduped](https://dedupedai.com/badge/ashutoshsinghpr7-wikiskill.svg)](https://dedupedai.com/use-cases/ashutoshsinghpr7-wikiskill/?ref=badge)

More badge styles and HTML

Questions about Wikiskill

What is Wikiskill?

WikiSkill is a Python framework that lets an AI agent turn its past runs into a persistent wiki and evolve its own skills, keeping only changes that score better on held-out tasks. It is an open-source project on GitHub: https://github.com/ashutoshsinghpr7/wikiskill.

Who is Wikiskill for?

Developers and ML engineers who run coding agents on repeatable tasks and want the agent to improve its skills with measured gating instead of manual edits.

What can I do with Wikiskill?

5 use cases so far, for example: Evolve an agent's skills from its own task traces; Test whether an evolved skill actually improved results; Run the WikiSkill loop with Claude Code as the agent. Each has steps and a copy-paste agent prompt.

What do I need to run Wikiskill?

Python 3.10 or newer; Hermes Agent installed as the reference backend, or another supported agent CLI (Claude Code, Codex or GitHub Copilot CLI); A configured default model for the agent, for example through OpenRouter using --model and --provider; Enough API budget for several iterations (the README cites about $0.09 per iteration on one free-tier run).

What are alternatives to Wikiskill?

Other hot AI repos in Software and DevOps: Harness2, iFixAi, Orca, Diagram Design, AI Memory.

Is Wikiskill safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.