Agent skill

Wikiskill Maintainer

by ashutoshsinghpr7 in ashutoshsinghpr7/wikiskill

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

MITAuto-check passedDevelopment

Install Wikiskill Maintainer

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

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

GitHub CLI
$ gh skill install ashutoshsinghpr7/wikiskill wikiskill-maintainer --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-maintainer .claude/skills/wikiskill-maintainer && 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-maintainer
GitHub stars
267
Token cost
~476 tokens
SKILL.md length
243 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

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

  • Works in 4 steps: Read the trace manifest in the task… → Deep trace analysis: read each trace's… → Compare successful vs failed executions.… → …
  • Development work in your project
  • SKILL.md covers Your tools, Workflow and Rules
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Wikiskill Maintainer is an agent skill from ashutoshsinghpr7/wikiskill. Consolidate traces into the persistent wiki (WikiSkill).

Its SKILL.md is about 480 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 Development. 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

  • Development work in your project

Example prompts

  • “/wikiskill-maintainer”

Workflow steps

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

  1. Read the trace manifest in the task prompt: a list of trace paths
  2. Deep trace analysis: read each trace's JSONL (role + content lines
  3. Compare successful vs failed executions. Identify action patterns
  4. Update the wiki incrementally (never rewrite wholesale)

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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Wikiskill Maintainer loads about 476 tokens when it runs. Until then it costs about 19 tokens; SKILL.md has 243 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~19
When it runs · the whole SKILL.md, loaded when a task matches
~476

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). 243 words, ~476 tokens.

Download SKILL.mdSave it as .claude/skills/wikiskill-maintainer/SKILL.md (or your agent's skills folder).
name
wikiskill-maintainer
description
Consolidate traces into the persistent wiki (WikiSkill).

Wiki Maintainer (WikiSkill)

You are a Wiki Maintainer Agent for a WikiSkill evolution loop. Your job is to consolidate raw execution traces into the persistent wiki so that later skill updates can build on accumulated, organized knowledge.

Your tools

  • read_file(path) — read a wiki file or an execution trace (JSONL transcript). Paths are given in the task prompt and are absolute — use them as-is.
  • search_files(pattern, path) — find text inside traces or wiki files.
  • write_file(path, content) / patch(path, old, new) — edit wiki files.

Workflow

  1. Read the trace manifest in the task prompt: a list of trace paths (raw execution logs). Traces are immutable — never modify them.
  2. Deep trace analysis: read each trace's JSONL (role + content lines: reasoning, tool calls, tool outputs, final answer). Focus on failed tasks for root causes; also read passing traces to preserve effective behavior.
  3. Compare successful vs failed executions. Identify action patterns (concrete behaviors that cause failure or success), not just error messages.
  4. Update the wiki incrementally (never rewrite wholesale):
    • wiki/patterns/<name>.md — create or extend pattern pages: PROBLEM → ROOT CAUSE → FIX, 10–30 lines, concise, no duplicates.
    • wiki/index.md — rewrite completely, one line per pattern: [name](wiki/patterns/name.md): PROBLEM + ROOT CAUSE + FIX in 1–2 sentences.
    • wiki/log.md — append a dated entry summarizing this iteration's findings.

Rules

  • Focus on actionable, transferable patterns (they will drive skill proposals).
  • Do not invent patterns not supported by the traces.
  • Keep the wiki compact; merge overlapping patterns.
  • Do not touch the skills directory — that is the Skill Proposer's job.

© 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-maintainer of ashutoshsinghpr7/wikiskill.

Open the folder on GitHubat commit cdc291c

Compare with similar skills

Wikiskill Maintainer 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 Maintainer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Wikiskill Maintainer this skillashutoshsinghpr7/wikiskill267—~476Automated safety check: PassMIT
Workflow AuthoringQuintinShaw/pi-dynamic-workflows555—~671Automated safety check: PassMIT
Awesome Rebuttalxiongqi123123/awesome-rebuttal306—~3.3kAutomated safety check: PassMIT
Jj Flowseandavi/GEOquery118—~981Automated safety check: PassCustom licence
Light Project StructureLight0305/Light-skills640—~3kAutomated safety check: NotesMIT
Diagram312362115/claude107—~2.7kAutomated safety check: PassMIT

Similar skills

  • Workflow Authoring

    QuintinShaw/pi-dynamic-workflows

    Guidance for writing, editing, reviewing, and debugging JavaScript workflow code for pi-dynamic-workflows.

    555 GitHub stars~671 tokensUpdated 3 days ago
    DevelopmentAuto-check passed
  • Awesome Rebuttal

    xiongqi123123/awesome-rebuttal

    Global-installable, project-level academic rebuttal strategy skill for AI/ML/CV/NLP/Robotics papers.

    306 GitHub stars~3.3k tokensUpdated 3 mo ago
    DevelopmentAuto-check passed
  • Jj Flow

    seandavi/GEOquery

    jujutsu (jj) command cheatsheet for this colocated jj+git Bioconductor repo.

    118 GitHub stars~981 tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Light Project Structure

    Light0305/Light-skills

    Audits, scaffolds and safely migrates research project folder structures, keeping existing repositories read-only until you approve exact moves from a plan.

    640 GitHub stars~3k tokensUpdated 3 mo ago
    DevelopmentAuto-check: notes
  • Diagram

    312362115/claude

    专业图表生成技能:根据需求自动选择合适的图表类型,生成符合设计规范的 PNG 图表. An agent skill from 312362115/claude.

    107 GitHub stars~2.7k tokensUpdated 4 mo ago
    DevelopmentAuto-check passed
  • Tiger Release

    safreita1/TIGER

    Prepare and publish a TIGER release by keeping implementation, tests, source and hosted documentation, citations, version metadata, GitHub, and PyPI artifacts synchronized.

    164 GitHub stars~1.8k tokensUpdated 26 days ago
    DevelopmentAuto-check passed

More from ashutoshsinghpr7/wikiskill

All 8 skills in this repo
  • Wikiskill Evolve

    ashutoshsinghpr7/wikiskill

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

    267 GitHub stars~655 tokensUpdated 24 days ago
    Auto-check passed
  • Wikiskill Proposer

    ashutoshsinghpr7/wikiskill

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

    267 GitHub stars~668 tokensUpdated 24 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 24 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 24 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 24 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 24 days ago
    Auto-check passed

Questions about Wikiskill Maintainer

What does Wikiskill Maintainer do?

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

When should I use Wikiskill Maintainer?

Wikiskill Maintainer fits situations like: development work in your project.

How do I install Wikiskill Maintainer in Claude Code?

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

How do I install Wikiskill Maintainer in Codex?

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

Can I use Wikiskill Maintainer 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-maintainer -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-maintainer, .gemini/skills/wikiskill-maintainer, .github/skills/wikiskill-maintainer and .opencode/skills/wikiskill-maintainer in your project.

What does Wikiskill Maintainer need to run?

SKILL.md names no scripts, command-line tools or credentials: Wikiskill Maintainer is instructions for the agent only.

Does Wikiskill Maintainer 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 Wikiskill Maintainer 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 Maintainer use?

Wikiskill Maintainer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Wikiskill Maintainer use?

About 476 tokens (SKILL.md is roughly 1.9k 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 Maintainer?

Skills that share tags, products or a category with Wikiskill Maintainer: Workflow Authoring (QuintinShaw/pi-dynamic-workflows, 555 stars), Awesome Rebuttal (xiongqi123123/awesome-rebuttal, 306 stars), Jj Flow (seandavi/GEOquery, 118 stars) and Light Project Structure (Light0305/Light-skills, 640 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Wikiskill Maintainer?

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.