Skip to main content
ClaudeWave
EN, English
Skill2.9k repo starsupdated 1mo ago

wiki-builder

Wiki-builder creates and maintains persistent markdown-based research wikis stored locally on disk and indexed in SQLite with full-text search capability. Use it when a user requests to start a wiki on a topic, add sources or notes to an existing wiki, compile concept pages, or query a long-lived knowledge base about papers, products, people, projects, codebases, or research domains that span multiple sessions.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/rohitg00/pro-workflow /tmp/wiki-builder && cp -r /tmp/wiki-builder/skills/wiki-builder ~/.claude/skills/wiki-builder
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# Wiki Builder

Persistent knowledge base for any topic. Markdown on disk + SQLite FTS5 shadow index.

## When to use

- "Start a wiki on <topic>"
- "Add this paper / link / note to the <slug> wiki"
- "Compile a concept page on X in <slug>"
- "What does the <slug> wiki say about Y?" (delegates to wiki-query)
- "List my wikis"

## Locations

- **Global**: `~/.pro-workflow/wikis/<slug>/` — default, never committed
- **Project**: `<project>/.claude/wikis/<slug>/` — pass `--scope project`, committable

Both register in the same `~/.pro-workflow/data.db`.

## Flavors

| Flavor | Use for |
|--------|---------|
| `research` | ongoing topic exploration |
| `paper` | one-paper deep dive |
| `domain` | broad subject area |
| `product` | product/tool KB |
| `person` | researcher/founder dossier |
| `organization` | company/lab profile |
| `project` | internal project KB |
| `codebase` | symbol/file-aware KB tied to a repo |
| `incident` | post-mortem KB |

## Layout

```
<slug>/
├── wiki.config.md         # purpose, audience, page types, style, auto_research block
├── raw/                   # untouched source material (PDFs, scrapes, transcripts)
├── wiki/
│   └── index.md           # entry point, hand-curated TOC
├── derived/               # generated artifacts (surveys, charts, summaries)
├── prompts/               # per-task prompts (compile-page, lint, query)
├── logs/maintenance-log.md
└── sources.md             # one row per source: id | url | title | hash | fetched_at
```

Flavor adds folders: `wiki/papers`, `wiki/concepts`, `wiki/people`, `wiki/products`, `wiki/timelines`, `wiki/questions`.

## CLI surface

```
node $SKILL_ROOT/scripts/wiki-cli.js init <slug> --title "X" --flavor research [--scope project] [--root <path>]
node $SKILL_ROOT/scripts/wiki-cli.js list
node $SKILL_ROOT/scripts/wiki-cli.js page <slug> <rel-path> --title "X" [--type concept|paper|person|...] [--from-file path]
node $SKILL_ROOT/scripts/wiki-cli.js reindex <slug>
node $SKILL_ROOT/scripts/wiki-cli.js info <slug>
```

`init` runs `init_wiki.sh` (mirrors dair layout) AND registers the wiki in SQLite. `page` writes markdown + upserts FTS row.

## Workflow when invoked

1. Resolve action (init / ingest / compile / list / reindex / info).
2. Read `wiki.config.md` of the target wiki before any compile.
3. Every claim that lands in `wiki/` must cite a row in `sources.md` (one citation = one source row).
4. After page write, call `wiki-cli.js page` so FTS index stays in sync.
5. Append a one-line entry to `logs/maintenance-log.md` per change.
6. Update `wiki/index.md` if new top-level page.

## Quality bar

- First page useful immediately, not stub.
- Stable slug filenames (`tool-use-benchmarks.md`, not `2026-05-08-notes.md`).
- Separate raw source from compiled interpretation.
- Cross-link related pages in same wiki via relative links.
- Mark speculation with `> SPECULATION:` block.
- No duplicate summaries — link existing page instead.
- Generated pages stay navigable for future agents.

## Privacy

Wikis with `private: true` in config never get fetched from web sources by `wiki-research-loop`. Local raw/ only.

## Auto-research opt-in

Phase 3.3.0 ships builder + query only. Loop arrives in 3.3.1. To prep, `wiki.config.md` may include:

```yaml
auto_research:
  enabled: false        # flip in 3.3.1
  max_pages_per_run: 5
  max_depth: 3
  budget_usd: 0.50
  fetchers: [web, arxiv, github]
```

## Templates

See `templates/` for `wiki.config.md`, `index.md`, prompt files. `init_wiki.sh` copies these into the new wiki root.
agent-teamsSkill

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.

auto-setupSkill

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.

batch-orchestrationSkill

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.

bug-captureSkill

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".

compact-guardSkill

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.

context-engineerSubagent

Analyzes and optimizes context window usage across sessions. Use when context feels bloated, sessions run slow, or approaching compaction limits.

context-engineeringSkill

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.

context-optimizerSkill

Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.