Skills

wiki-research-loop

wiki-research-loop is a skill in rohitg00/pro-workflow, last changed 29 Sept 2026. It can run shell commands, reach the network, name web addresses and bundle scripts — read the findings before installing. Our pattern check flagged nothing at commit 86d5f27 on 27 Oct 2026.

Pattern check: nothing flagged · commit 86d5f27 · 27 Oct 2026

Install
From the author
Auto-grow a pro-workflow wiki by running a budget-capped BFS research loop over pluggable source fetchers (web, arXiv, GitHub). Each iteration pops a seed from the queue, fetches sources, drafts a wiki page, dedupes claims against existing pages, enqueues follow-up seeds. Halts on budget cap, depth cap, or convergence. Use when the user says "research <topic>", "grow the <slug> wiki", "auto-research", or wants a knowledge base that builds itself overnight.
Licence
No licence
Repo stars
2.9k
Folder last changed
29 Sept 2026 (opens in a new tab)
Publisher
rohitg00
Files
5 files
Checked
86d5f27 (opens in a new tab) · 27 Oct 2026

Install

Each tab says whether it installs commit 86d5f27, the one we checked, or the latest version.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity, and Claude Code for Cline. Kiro needs the folder copied by hand.

Pinned to commit 86d5f27, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/rohitg00/pro-workflow.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 86d5f2770bd8e1695e40888e4242841eb7cbad4f &&
  git -C "$tmp" sparse-checkout set -- skills/wiki-research-loop &&
  git -C "$tmp" checkout -q 86d5f2770bd8e1695e40888e4242841eb7cbad4f &&
  mkdir -p .claude/skills &&
  mkdir .claude/skills/wiki-research-loop &&
  cp -R "$tmp"/skills/wiki-research-loop/. .claude/skills/wiki-research-loop/ &&
  rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Or install the pro-workflow plugin it ships in. Installs the latest version, not the one we checked. Installs everything in the plugin, including any hooks, MCP servers and scripts our check doesn't cover.

claude plugin marketplace add rohitg00/pro-workflow --scope project &&
  claude plugin install pro-workflow@pro-workflow --scope project
Claude Code docs (opens in a new tab)

What it can touch

From the files and frontmatter at commit 86d5f27. This is how much a skill can do, not whether it is risky.

What it can touch: Shell, network or credentials

  • Runs shell commands

    Its instructions or files give the agent commands to run on your computer.

  • Reaches the network

    It sends or fetches data over the internet, for example with curl, an HTTP library or a package install.

  • Names web addresses

    It mentions outside web addresses the agent may visit. We list them but don't follow them.

  • Bundles scripts

    The folder holds code files the agent may run.

Pattern check

Pattern check: nothing flagged · commit 86d5f27 · 27 Oct 2026

We checked every text file in this skill, at commit 86d5f27 on 27 Oct 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

Outside links we did not follow

  • https://export.arxiv.org/api/query
  • https://api.github.com/search/repositories
  • https://export.arxiv.org/api/query?search_query=all:$
  • https://api.github.com/search/repositories?q=$
  • https://lite.duckduckgo.com/lite/?q=$

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

  • Agent Skills specPasses with warnings

    The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.

    • Warning

      The description contains < or >. Uploads to the Claude apps and API reject it. D3

      Fix: Remove < and >, or reword (for example "less than").

    • Warning

      Fields outside the spec: user-invocable (read by Claude Code and VS Code). Uploads to the Claude apps and API, and the spec's validator, reject the file; most agents ignore these fields. O1

      Fix: Delete them for a portable skill, or keep them if you only target the agents that read them.

    • Note

      There is no license field, so readers can't tell whether they may reuse the skill. O2

      Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.

  • Claude CodePasses
  • Claude apps & API uploadFails

    Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

    • Error

      The description contains < or >. Anthropic's validator rejects any angle bracket there. D3

      Fix: Remove < and >, or reword (for example "less than").

    • Error

      Upload and packaging fail on fields outside the spec: user-invocable. O1

      Fix: Delete them, and keep your own data under metadata as text values.

    • Note

      The description is 460 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4

      Fix: If the claude.ai upload refuses it, trim the description to 200 characters.

  • OpenAI (Codex & API)Passes with warnings

    Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.

    • Warning

      Fields outside the spec: user-invocable. Codex ignores them; OpenAI doesn't say whether its upload accepts them. O1

      Fix: Delete them, or move your own data under metadata as text values.

  • VS Code & CopilotPasses with warnings

    VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.

    • Warning

      VS Code deletes text between < and > in a description, so "<topic>" would vanish. D3

      Fix: Remove the angle brackets or reword.

SKILL.md

We only show SKILL.md text here when its licence clearly allows it.

Read SKILL.md on GitHub (opens in a new tab)

Files

5 files

PathSize
SKILL.md (opens in a new tab)5.8 KB
scripts/research-loop.js (opens in a new tab)12.9 KB
scripts/source-fetchers/arxiv.js (opens in a new tab)2 KB
scripts/source-fetchers/github.js (opens in a new tab)2.2 KB
scripts/source-fetchers/web.js (opens in a new tab)3.1 KB

More from rohitg00/pro-workflow

  • agent-teams

    rohitg00/pro-workflow

    Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.

    • Runs shell commands
    • Names web addresses
    Pattern check: Nothing flagged

    No licence · 2.9k repo stars · Updated 18 Jul 2026

  • auto-setup

    rohitg00/pro-workflow

    Auto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use when onboarding a new codebase.

    • Runs shell commands
    Pattern check: Nothing flagged

    No licence · 2.9k repo stars · Updated 18 Jul 2026

  • batch-orchestration

    rohitg00/pro-workflow

    Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations, refactors, codemods, and any change touching 10+ files with the same pattern.

    • Runs shell commands
    Pattern check: Nothing flagged

    No licence · 2.9k repo stars · Updated 18 Jul 2026

  • bug-capture

    rohitg00/pro-workflow

    Capture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in parallel for context but never leaks file paths or line numbers into the issue. Use when the user reports a bug conversationally, runs a QA pass, or says "file an issue", "log this as a bug", "capture this".

    • Runs shell commands
    Pattern check: Nothing flagged

    No licence · 2.9k repo stars · Updated 17 Apr 2026

  • compact-guard

    rohitg00/pro-workflow

    Smart context compaction with state preservation. Saves critical files, task progress, and working state before compaction, restores after. Use before manual compact or when auto-compact triggers.

    • Instructions only
    Pattern check: Nothing flagged

    No licence · 2.9k repo stars · Updated 18 Jul 2026

  • context-engineering

    rohitg00/pro-workflow

    Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partitioning to keep AI sessions sharp and efficient.

    • Changes agent settings
    Pattern check: Nothing flagged

    No licence · 2.9k repo stars · Updated 26 Sept 2026

All skills in rohitg00/pro-workflow