# Second Brain Wiki > Queries the Second Brain wiki (~/second-brain/wiki/) for existing context on a topic, person, or project and returns the most relevant pages plus a short synthesis -- without the user pasting anything in. Use when the user says "what do I know about X", "check my second brain for X", "have I written about this before", "what's in my wiki about X", or when another skill needs background context on a topic/person/project before starting its own work (e.g. meeting prep, ticket breakdown, decision-making). Do NOT use this to add content to the wiki -- that's `second-brain-ingest`. This skill only reads. - Skill: `jaquevan/second-brain-wiki` (Agent Skill, multi-file: 10 files) - Install (CLI): `npx skillmds@latest add jaquevan/second-brain-wiki` - Raw SKILL.md: https://api.skillmd.com/api/skills/jaquevan/second-brain-wiki/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Productivity - Author: jaquevan (https://skillmd.com/u/jaquevan) - Updated: 2026-09-21 - Page: https://skillmd.com/skills/jaquevan/second-brain-wiki --- # Second Brain Wiki Reads `~/second-brain/wiki/` and answers "what do I already know about this?" so nobody has to manually open files or paste content into a prompt. This is the retrieval half of the second brain; `second-brain-ingest` is the write half. ## Step 1: Determine the query | Input | Query | |---|---| | "what do I know about prototype-creator" | topic = prototype-creator | | "check my second brain for " | person = | | Called by another skill with a topic/person/project string | Use that string directly | | Called by another skill with a topic/person **and a specific date range** (e.g. meeting prep's lookback window) | Use the string as the query, but see Step 4 -- the range changes how the cap applies | | Empty / vague ("check my wiki") | Ask what topic, person, or project to look up | ## Step 2: Search the tag index first (fast path) Read `~/second-brain/wiki/tags.md`. If the query matches a `project/*`, `person/*`, `type/*`, or `status/*` tag (exact or close match, e.g. "andy" matches `person/andy-braren`), collect every page listed under that tag. This is faster than scanning all pages and is the primary path once tagging (via `second-brain-ingest`) has been running for a while. If `tags.md` doesn't exist yet or the query doesn't match a tag cleanly, fall through to Step 3. ## Step 3: Fall back to index and content search 1. Read `~/second-brain/wiki/index.md` and look for title matches under any category. 2. If still nothing, grep page titles and first-10-lines across `~/second-brain/wiki/*.md` (excluding `index.md`, `log.md`, `tags.md`) for the query term. ## Step 4: Rank and read 1. Combine results from Steps 2-3, deduplicated. 2. Rank by: exact tag match > title match > content match. Within a tier, prefer more recent pages (check `log.md` for dates if needed). 3. Cap at the top 5 pages -- **but only for pages outside a stated date range.** If the caller gave a specific range (see Step 1), every page dated inside that range gets read regardless of how many that is; the cap-of-5 applies only to older background material beyond the range. A person with heavy tag volume (dozens of pages over months) can still have several matches in a one-week window -- a flat cap would silently drop same-day or same-week pages behind months of lower-relevance history, which is the opposite of what a time-bounded caller needs. With no stated range, the plain top-5-by-recency cap applies as usual. 4. Read each selected page in full. ## Step 5: Return the answer Return a short synthesis, not a dump of the raw pages: ``` **Second brain context: ** <1-3 sentence synthesis across the matched pages -- what's the state of this, what's already been decided or discussed> **Relevant pages:** - [Page Title](page-slug.md) -- one-line summary of what it covers - [Page Title](page-slug.md) -- one-line summary of what it covers **Coverage:** | or "Nothing found in the wiki for this yet." ``` If called by another skill (not directly by the user), skip the chat formatting and just return the structured data (page paths + one-line summaries + synthesis) for that skill to fold into its own output. ## Example: good vs bad response **Good** — specific, synthesized, sourced: > **Second brain context: ** > > Recent work with centers on the prototype-creator/evaluator-super-agent > merge (as of the 2026-07-09 meeting) and PatternFly 6 migration timing > (Q3 target, confirmed 2026-07-01). No open blockers from him currently. > > **Relevant pages:** > - [/Evan Meeting — 2026-07-09](andy-evan-2026-07-09.md) — Apollo canvas, prototype-creator merge plan > - [Weekly Design Sync — 2026-07-01](weekly-design-sync-2026-07-01.md) — PF6 migration, Nielsen's heuristics adopted > > **Coverage:** 4 pages found via `person/andy-braren` tag **Bad** — just lists files with no synthesis: > Here are some pages that mention : andy-evan-2026-07-09.md, > andy-evan-2026-06-29.md, weekly-design-sync-2026-07-01.md. The bad version makes the caller do the work the retrieval was supposed to save them. Synthesizing across pages, not just finding them, is the point. ## Common Mistakes | Problem | Fix | |---|---| | Reading every wiki page to answer a narrow query | Use the tag index (Step 2) first. Full content search (Step 3.2) is the fallback, not the default. | | Dumping raw page content back to the caller | Always synthesize (Step 5). A pile of file paths isn't an answer. | | Treating "nothing found" as an error | It's a valid, useful answer -- say so plainly rather than guessing or fabricating context. | | Writing to the wiki when asked to "check" it | This skill never modifies `~/second-brain/`. Any write request routes to `second-brain-ingest` instead. | | Applying the flat cap-of-5 to a caller-specified date range | A person tagged on dozens of pages over months can still have 6+ genuinely in-range matches for a one-week window. The cap only trims older background material -- every in-range page gets read, even past 5. Found via a real miss: a heavily-tagged person's same-day meeting got trimmed by the flat cap before this rule existed. | ## Read-Only Constraint This skill MUST NEVER create, edit, or delete anything under `~/second-brain/`. If the user's request is actually about adding content (not looking something up), say so and point to `second-brain-ingest`.