wiki-research-loop

Solid

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.

AI & Automation 2,862 stars 286 forks Updated 1 weeks ago

Install

View on GitHub

Quality Score: 84/100

Stars 20%
100
Recency 20%
90
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
0
Description 5%
100

Skill Content

# Wiki Research Loop Driver that turns a wiki into an auto-grown knowledge base. Layers on top of `wiki-builder` and `wiki-query`. ## Loop semantics ``` seed-queue (pending) → next-seed → fetch sources via plugins (web | arxiv | github) → extract claims → dedupe vs index (FTS5; later vector via 3.3.2) → compile new page or amend existing → upsert page (auto-FTS-index) → enqueue follow-up seeds (max-depth gate) → mark seed done → if budget OR convergence OR kill-switch → halt ``` ## Halt conditions (any one trips) - `budget_usd` exceeded (loop tracks per-fetcher cost estimate) - `max_pages_per_run` written - `max_depth` reached on every active branch - 3 consecutive pages add < 5 % new claims (convergence) - File `~/.pro-workflow/STOP` exists (operator kill-switch) - `wiki.config.md` `auto_research.enabled: false` - Wiki `private: true` AND any non-local fetcher selected ## Commands ``` node $SKILL_ROOT/scripts/research-loop.js run <slug> [--max-pages N] [--max-depth N] [--budget-usd 0.50] [--fetchers web,arxiv,github] node $SKILL_ROOT/scripts/research-loop.js seed <slug> "<query>" [--depth 0] [--parent-id N] node $SKILL_ROOT/scripts/research-loop.js seeds <slug> [--status pending|active|done|failed] node $SKILL_ROOT/scripts/research-loop.js cancel <slug> node $SKILL_ROOT/scripts/research-loop.js status ``` CLI flags override `wiki.config.md` for one run only. ## Source fetchers Pluggable. Each lives at `scripts/source-fetchers/<name>.js`. Interface: ...

Details

Author
rohitg00
Repository
rohitg00/pro-workflow
Created
7 months ago
Last Updated
1 weeks ago
Language
JavaScript
License
None

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

wiki-builder

Start, structure, and grow a persistent research wiki indexed in pro-workflow's SQLite knowledge base. Each wiki is a folder of markdown pages with provenance, plus a shadow FTS5 index so any session can recall it. Use when the user says "start a wiki", "add to wiki", "compile a page", "wiki on X", or wants a long-lived knowledge base on a topic, paper, product, person, project, or codebase.

2,862 Updated 1 weeks ago
rohitg00
AI & Automation Listed

autoresearch

Run an autonomous WEB-fed research loop on a topic. Iterates web-search → fetch → synthesize → file as wiki pages until depth is reached. Each iteration narrows the gap between what's known (in the wiki) and what's still missing. Use when the user explicitly says "research X on the web", "go research X", "deep dive online into X", "find new info about X", "build a wiki on X", "/autoresearch", or any phrasing that implies fetching NEW information from the internet. Do NOT use when the user wants answers from the existing wiki only — that's `wiki-query`. If "research X" is ambiguous, ask which is intended before kicking off the loop (it costs real tokens).

1 Updated today
tboome33
AI & Automation Listed

wiki-query

Query pro-workflow wikis via SQLite FTS5 BM25 retrieval. Returns top-K passages with citations. Use when answering a question that any of the user's wikis already covers, when the user says "what does the wiki say about X", "ask wiki", "search wikis", or before drafting a new wiki page (to avoid duplication).

2,862 Updated 1 weeks ago
rohitg00