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

Wikiskill Evolve

by ashutoshsinghpr7 in ashutoshsinghpr7/wikiskill

Run the WikiSkill self-evolution loop (arXiv 2608.27454) on a Hermes workspace — raw→maintainer→proposer→gate with strict Rval Rbest gating.

MITAuto-check passedResearch & Science

Install Wikiskill Evolve

skills CLI
$ npx skills add ashutoshsinghpr7/wikiskill --skill wikiskill-evolve -a claude-code

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

GitHub CLI
$ gh skill install ashutoshsinghpr7/wikiskill wikiskill-evolve --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/ashutoshsinghpr7/wikiskill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/wikiskill-evolve .claude/skills/wikiskill-evolve && 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
wikiskill-evolve
GitHub stars
267
Token cost
~655 tokens
SKILL.md length
218 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Run the WikiSkill self-evolution loop (arXiv 2608.27454) on a Hermes workspace — raw→maintainer→proposer→gate with strict Rval Rbest gating.

  • Tasks that involve Academic paper search
  • SKILL.md covers When to use, Install, Run the loop and Reading the output, plus 2 more sections
  • Calls pip

What it does

Wikiskill Evolve is an agent skill from ashutoshsinghpr7/wikiskill. Run the WikiSkill self-evolution loop (arXiv 2608.27454) on a Hermes workspace — raw→maintainer→proposer→gate with strict Rval Rbest gating.

Its SKILL.md is about 660 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Academic paper search. It works with arXiv. The repository describes itself as: WikiSkill (arXiv:2608.27454) for Hermes Agent — self-evolving agent skills via a persistent knowledge wiki. Faithful Algorithm 1 implementation with real agent runs, isolated… The licence is MIT.

When your agent uses it

  • Tasks that involve Academic paper search

Example prompts

  • “/wikiskill-evolve”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit cdc291c. 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:

    • pip

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

  • Network

    No URLs in SKILL.md. Its commands use pip, 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

Wikiskill Evolve loads about 655 tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 218 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~40
When it runs · the whole SKILL.md, loaded when a task matches
~655

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 ashutoshsinghpr7/wikiskill at commit cdc291c, republished under its MIT licence (© ashutoshsinghpr7). 218 words, ~655 tokens.

Download SKILL.mdSave it as .claude/skills/wikiskill-evolve/SKILL.md (or your agent's skills folder).
name
wikiskill-evolve
description
Run the WikiSkill self-evolution loop (arXiv 2608.27454) on a Hermes workspace — raw→maintainer→proposer→gate with strict R_val > R_best gating.
version
1.0.0
license
MIT
platforms
linux, macos, windows

WikiSkill Evolve

Run Google's WikiSkill evolution loop (arXiv:2608.27454) — a faithful implementation with Hermes as the reference backend. The agent evolves its own skills: raw sessions → a maintainer distills failure patterns into a persistent wiki → a proposer writes a candidate skill → a validation gate accepts it only if R_val > R_best (git rollback otherwise).

When to use

  • You want an agent's own experience (traces) turned into reusable skills
  • You want to test whether a candidate skill actually helps, with statistics instead of vibes
  • You're running the paper's protocol on your own tasks

Install

bash
pip install wikiskill          # Python ≥ 3.10; works with Hermes, Claude Code

Run the loop

bash
wikiskill init myws                        # workspace + auto-graded bench
wikiskill evolve myws --iters 3            # train → maintain → propose → gate
wikiskill status myws                      # baseline, r_best, skill state
wikiskill compare wsA wsB --iters 5        # paired exact-binomial comparison
wikiskill transfer src dst                 # copy accepted skills to another ws

Reading the output

  • runs/state.json — baseline (S₀ on val), r_best, next_iter
  • wiki/log.md — every maintenance/proposal/gate decision with evidence
  • wiki/patterns/ — distilled failure patterns (the raw material)
  • wiki/skill-impact.md — rejected proposals stay visible (paper requirement)
  • Gate verdicts: ACCEPTED (R_val > R_best, git commit), REJECTED (rolled back), no_action (proposer declined — a valid outcome)

Backends

bash
wikiskill init myws --backend claude       # Claude Code as the worker

Hermes is the reference backend; Claude Code ships in the box; codex/opencode are on the roadmap. All speak open SKILL.md, so evolved skills transfer.

Honest-expectation notes

  • Each iteration costs ~$0.09 on free-tier models (gemini-lite class) — turn budgets and --max-turns bound the spend
  • A weak model may produce no_action iterations — that's the gate working, not a failure; skill accumulation needs a reasonably strong proposer
  • The gate has rejected harmful skills in live runs — a rejection is a win

© ashutoshsinghpr7, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/wikiskill-evolve of ashutoshsinghpr7/wikiskill.

Open the folder on GitHubat commit cdc291c

Compare with similar skills

Wikiskill Evolve 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.

Wikiskill Evolve compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Wikiskill Evolve this skillashutoshsinghpr7/wikiskill267—~655Automated safety check: PassMIT
Read arXiv Paperkarpathy/nanochat59k1 repos~494Automated safety check: PassMIT
Literature Reviewneflibata-feng/MyArxiv-Agent12620 repos~5.9kAutomated safety check: NotesMIT
Openalex Databaseneflibata-feng/MyArxiv-Agent12612 repos~3kAutomated safety check: PassCustom licence
Citation ManagementK-Dense-AI/claude-scientific-writer2.4k2 repos~3.9kAutomated safety check: NotesMIT
Citation Managementneflibata-feng/MyArxiv-Agent12619 repos~8.1kAutomated safety check: NotesMIT

Similar skills

  • Read arXiv Paper

    karpathy/nanochat

    Fetches the TeX source of an arXiv paper from its URL, reads it and writes a markdown summary tied to the nanochat project.

    59k GitHub starsUsed in 1 repo~494 tokens
    Research & ScienceAuto-check passed

  • Literature Review

    neflibata-feng/MyArxiv-Agent

    Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).

    126 GitHub starsUsed in 20 repos~5.9k tokens
    Research & ScienceAuto-check: notes

  • Openalex Database

    neflibata-feng/MyArxiv-Agent

    Query and analyze scholarly literature using the OpenAlex database.

    126 GitHub starsUsed in 12 repos~3k tokens
    Research & ScienceAuto-check passed

  • Citation Management

    K-Dense-AI/claude-scientific-writer

    Finds papers in OpenAlex, PubMed and Google Scholar, turns DOIs, PMIDs and arXiv IDs into clean BibTeX, and validates citations for a manuscript or thesis.

    2.4k GitHub starsUsed in 2 repos~3.9k tokens
    Research & ScienceAuto-check: notes

  • Citation Management

    neflibata-feng/MyArxiv-Agent

    Comprehensive citation management for academic research. An agent skill from neflibata-feng/MyArxiv-Agent.

    126 GitHub starsUsed in 19 repos~8.1k tokens
    Research & ScienceAuto-check: notes

  • Systematic Literature Review Builder

    bytedance/deer-flow

    Searches arXiv across many papers on one topic, extracts each paper's methodology and findings in parallel, and synthesizes a cited literature review.

    84k GitHub starsUsed in 2 repos~4.3k tokens
    Research & ScienceAuto-check passed

More from ashutoshsinghpr7/wikiskill

All 8 skills in this repo

  • Wikiskill Proposer

    ashutoshsinghpr7/wikiskill

    Propose skills from wiki patterns and traces (WikiSkill). An agent skill from ashutoshsinghpr7/wikiskill.

    267 GitHub stars~668 tokensUpdated 23 days ago
    Auto-check passed

  • Wikiskill Maintainer

    ashutoshsinghpr7/wikiskill

    Consolidate traces into the persistent wiki (WikiSkill). An agent skill from ashutoshsinghpr7/wikiskill.

    267 GitHub stars~476 tokensUpdated 23 days ago
    Auto-check passed

  • Script Exec Blocked

    ashutoshsinghpr7/wikiskill

    Sandbox approval policy blocks executecode and python3 -c; use readfile/writefile + manual transforms instead of retrying both runners.

    267 GitHub stars~281 tokensUpdated 23 days ago
    Auto-check passed

  • Search Miss Binary

    ashutoshsinghpr7/wikiskill

    ripgrep/searchfiles silently skips binary-detected files — verify empty search results with grep -a / file / xxd before concluding 'not found'.

    267 GitHub stars~327 tokensUpdated 23 days ago
    Auto-check passed

  • Spec Literal Execution

    ashutoshsinghpr7/wikiskill

    Apply ONLY the spec clauses literally — no aggregation, dedup, or cleanup transforms; each input record maps to its own output line.

    267 GitHub stars~385 tokensUpdated 23 days ago
    Auto-check passed

  • Trace Harness Launch Failure

    ashutoshsinghpr7/wikiskill

    Empty session traces mean launch failure, not agent behavior — verify apicallcount/toolcallcount and stdout.txt before analyzing.

    267 GitHub stars~443 tokensUpdated 23 days ago
    Auto-check passed

Works with

Categories

Questions about Wikiskill Evolve

What does Wikiskill Evolve do?

Run the WikiSkill self-evolution loop (arXiv 2608.27454) on a Hermes workspace — raw→maintainer→proposer→gate with strict Rval Rbest gating. Wikiskill Evolve is an agent skill from ashutoshsinghpr7/wikiskill.27454) on a Hermes workspace — raw→maintainer→proposer→gate with strict Rval Rbest gating.

When should I use Wikiskill Evolve?

Wikiskill Evolve fits situations like: tasks that involve Academic paper search.

How do I install Wikiskill Evolve in Claude Code?

Run `npx skills add ashutoshsinghpr7/wikiskill --skill wikiskill-evolve -a claude-code`. Or copy the skill folder (skills/wikiskill-evolve in ashutoshsinghpr7/wikiskill) into .claude/skills/wikiskill-evolve in your project. Claude Code loads it when a task matches its description.

How do I install Wikiskill Evolve in Codex?

Run `npx skills add ashutoshsinghpr7/wikiskill --skill wikiskill-evolve -a codex`. Or copy the skill folder (skills/wikiskill-evolve in ashutoshsinghpr7/wikiskill) into .agents/skills/wikiskill-evolve in your project. Codex loads it when a task matches its description.

Can I use Wikiskill Evolve 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 ashutoshsinghpr7/wikiskill --skill wikiskill-evolve -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wikiskill-evolve, .gemini/skills/wikiskill-evolve, .github/skills/wikiskill-evolve and .opencode/skills/wikiskill-evolve in your project.

What does Wikiskill Evolve need to run?

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

Does Wikiskill Evolve access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Wikiskill Evolve 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 Wikiskill Evolve use?

Wikiskill Evolve 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 Wikiskill Evolve use?

About 655 tokens (SKILL.md is roughly 2.6k 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 Wikiskill Evolve?

Skills that share tags, products or a category with Wikiskill Evolve: Read arXiv Paper (karpathy/nanochat, 59k stars), Literature Review (neflibata-feng/MyArxiv-Agent, 126 stars), Openalex Database (neflibata-feng/MyArxiv-Agent, 126 stars) and Citation Management (K-Dense-AI/claude-scientific-writer, 2.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Wikiskill Evolve?

ashutoshsinghpr7 (a GitHub user) maintains it in ashutoshsinghpr7/wikiskill, which has 267 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 15, 2026.

Source: ashutoshsinghpr7/wikiskill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.