llm-wiki-research

LLM Wiki Research

Sub-skill of llm-wiki-pm. Handles research sprints, competitive deep dives, and auto-enrichment of stub entities. Delegates all URL fetching to worker-source-fetcher so privacy filtering and raw/ logging happen correctly.

WebFetch note: WebFetch is listed in allowed-tools for quick page previews (e.g., confirming a URL before delegation). For source capture (saving to raw/), always delegate to worker-source-fetcher. Never call WebFetch directly for source saving — privacy filtering and raw/ logging won't happen.

Orient First

Orient per AGENTS.md before any writes:

1. Read $WIKI/SCHEMA.md
2. Read $WIKI/index.md
3. Read last 20-30 lines of $WIKI/log.md
4. Read $WIKI/overview.md

Research sprints may create many pages. Get user confirmation before creating 5+ pages.

Wiki Path Resolution

WIKI=$(cat .wiki-path 2>/dev/null | tr -d '[:space:]')
WIKI=${WIKI:-${CLAUDE_PLUGIN_OPTION_wiki_path:-${WIKI_PATH:-$(pwd)}}}

Worker Delegation

This skill uses worker-source-fetcher for all URL fetching. Never call WebFetch directly for source capture — always invoke the worker:

"Use worker-source-fetcher to fetch [URL]"

This ensures privacy filtering and raw/ logging happen correctly. The worker returns: "OK: saved to raw/<subdir>/<slug>.md" — use that path for synthesis.

---

Operation 1: Research Sprint

Trigger: "research sprint on [topic]", "deep research on [topic]"

① Define scope

Confirm with user:

• What is the topic / question to answer?
• Target depth: surface / standard / deep
• Time budget (number of sources)

② Wiki-first

grep -r "<topic>" $WIKI --include="*.md" -l

Read all relevant pages. Surface: "Wiki has N relevant pages. Here's what we already know: [...]. Gaps: [...]."

③ Research plan

Present 3-5 specific sources to fetch — name each, why it's relevant, what question it answers. Typical: analyst reports, company pages, recent press, whitepapers, industry forums. Get user confirmation before fetching.