/wiki
Use to run the second-brain loop — turn captures in raw/ into clean, cross-linked knowledge in wiki/, and to answer questions from past thinking. Trigger on "/wiki", "process my raw notes", "update the wiki", "add this to my brain/wiki", "what did I think about X", "what do my
$ npx -y skills add alirezarezvani/gaios --skill wiki --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/wiki
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use to run the second-brain loop — turn captures in raw/ into clean, cross-linked knowledge in wiki/, and to answer questions from past thinking. Trigger on "/wiki", "process my raw notes", "update the wiki", "add this to my brain/wiki", "what did I think about X", "what do my
SKILL.md
wiki.SKILL.mdname: wiki
description: Use to run the second-brain loop — turn captures in raw/ into clean, cross-linked knowledge in wiki/, and to answer questions from past thinking. Trigger on "/wiki", "process my raw notes", "update the wiki", "add this to my brain/wiki", "what did I think about X", "what do my notes say about X". Follows references/sops/wiki-translate.md. Enforces the admission policy: no PHI, no live financials, no secrets in the committed wiki.
Wiki — the user's second brain
The loop: **drop notes in `raw/` → `/wiki` translates them into `wiki/` → processed captures move to `raw/_archive/`.** `wiki/` is committed (durable knowledge); `raw/` is git-ignored (may hold sensitive material). Full procedure: `references/sops/wiki-translate.md`.
Two modes
1. Translate (ingest)
When there are files in `raw/`, or the user says "add this to the wiki": 1. Read `raw/` (skip `README.md`) and `wiki/_index.md`. 2. For each capture → pick topic(s), **read the existing entry, then merge** (never overwrite blindly). One topic per file, kebab-case. 3. **Apply the admission policy while writing** — strip PHI, replace live financial figures / named-deal specifics with a reference, drop secrets, cite sources, log uncertainty in-line. 4. Cross-link related entries; update `wiki/_index.md`. 5. **Move** processed files `raw/` → `raw/_archive/` (never delete). 6. Run `python tools/wiki_lint.py` — fix broken links/orphans; if it flags leakage, fix before committing. 7. Commit: `wiki: translate N captures (...)`. (Ask before committing if unsure.)
2. Answer (query)
When the user asks what he thought/decided about something: 1. Read `wiki/_index.md`, then the 3–10 relevant entries (+ `raw/_archive/` if needed). 2. Answer in his voice, with relative links to the entries used. 3. Offer to file the answer back as a new entry if it's worth keeping.
Guardrails (from CLAUDE.md)
- **Admission policy is non-negotiable:** no PHI, no live financials, no secrets in `wiki/`. Reference sensitive specifics, don't transcribe them.
- **Move, never delete** from `raw/` / `raw/_archive/`.
- **Read-then-merge**, never blind overwrite.
- **Lint is a gate** before commit, not a suggestion.
- When uncertain, log it in the entry rather than guessing.
Boundary (don't duplicate)
`wiki/` = evolving thinking & notes. Keep it distinct from `context/` (stable business facts), `decisions/log.md` (decisions), and the `memory/` store (cross-session facts). If something belongs in one of those, put it there and link, don't copy.
Read more
name: wiki description: Use to run the second-brain loop — turn captures in raw/ into clean, cross-linked knowledge in wiki/, and to answer questions from past thinking. Trigger on "/wiki", "process my raw notes", "update the wiki", "add this to my brain/wiki", "what did I think about X", "what do my notes say about X". Follows references/sops/wiki-translate.md. Enforces the admission policy: no PHI, no live financials, no secrets in the committed wiki.
Wiki — the user's second brain
The loop: **drop notes in `raw/` → `/wiki` translates them into `wiki/` → processed captures move to `raw/_archive/`.** `wiki/` is committed (durable knowledge); `raw/` is git-ignored (may hold sensitive material). Full procedure: `references/sops/wiki-translate.md`.
Two modes
1. Translate (ingest)
When there are files in `raw/`, or the user says "add this to the wiki": 1. Read `raw/` (skip `README.md`) and `wiki/_index.md`. 2. For each capture → pick topic(s), **read the existing entry, then merge** (never overwrite blindly). One topic per file, kebab-case. 3. **Apply the admission policy while writing** — strip PHI, replace live financial figures / named-deal specifics with a reference, drop secrets, cite sources, log uncertainty in-line. 4. Cross-link related entries; update `wiki/_index.md`. 5. **Move** processed files `raw/` → `raw/_archive/` (never delete). 6. Run `python tools/wiki_lint.py` — fix broken links/orphans; if it flags leakage, fix before committing. 7. Commit: `wiki: translate N captures (...)`. (Ask before committing if unsure.)
2. Answer (query)
When the user asks what he thought/decided about something: 1. Read `wiki/_index.md`, then the 3–10 relevant entries (+ `raw/_archive/` if needed). 2. Answer in his voice, with relative links to the entries used. 3. Offer to file the answer back as a new entry if it's worth keeping.
Guardrails (from CLAUDE.md)
- **Admission policy is non-negotiable:** no PHI, no live financials, no secrets in `wiki/`. Reference sensitive specifics, don't transcribe them.
- **Move, never delete** from `raw/` / `raw/_archive/`.
- **Read-then-merge**, never blind overwrite.
- **Lint is a gate** before commit, not a suggestion.
- When uncertain, log it in the entry rather than guessing.
Boundary (don't duplicate)
`wiki/` = evolving thinking & notes. Keep it distinct from `context/` (stable business facts), `decisions/log.md` (decisions), and the `memory/` store (cross-session facts). If something belongs in one of those, put it there and link, don't copy.
Clone it, run /setup, and it becomes yours in Claude Code or Codex — a second brain + Chief of Staff that holds your context, structures your work, drafts in your voice, and runs reliable workflows.
Other skills on gaios.
- /audit
Use when someone asks for an AIOS audit, asks to score their setup against the Four Cs, or says "is my AIOS working" / "audit my setup" / "find gaps in my AIOS". Produces a Four-Cs scoreboard with top-3 fixes ranked by leverage.
Open skill - /daily
Use at the start of a working day (or when the user asks "what should I focus on today / give me my brief / daily standup"). Produces a one-screen daily brief — today's top 3, open loops that need a nudge, what's slipping, and a suggested focus order. Trigger on "/daily", "daily
Open skill - /decide
Use when the user faces a real decision with stakes and wants it framed cleanly — options, ranked criteria, a recommendation, the falsifier, and reversibility — then logged to decisions/log.md. Trigger on "/decide", "help me decide", "should I X or Y", "frame this decision",
Open skill - /exec-cockpit
Template skill for a leadership-transition / executive cockpit — when someone steps into or covers a leadership role and needs to not drop anything. Produces a handoff doc + decision-rights map, an "open loops" tracker, a team-comms cadence, and a recurring report/update
Open skill - /experiment
Use to run an autoresearch-style experiment loop — improve a measurable artifact by trying changes, measuring against one objective metric, keeping if better and reverting if not, on an isolated git branch with a logged trail. Trigger on "/experiment", "run an experiment loop",
Open skill - /graph-ingest
Use when the user brings an external source worth keeping — a URL, a paper, a tweet/thread, a blog post, a docs page — and wants it pulled into the second brain. Fetches the source into the git-ignored capture inbox, admits it to the committed wiki through the admission policy,
Open skill