team-wiki
Skill1 starsChanged 23 days agoMITView on GitHub
The team's shared cross-project Obsidian knowledge base: where it lives, when to consult it, and how to contribute back. Preloaded into every team agent.
In this repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- context7-cliSkill
- decision-protocolSkill
- frontend-designSkill
- gitlab-accessSkill
- hallmarkSkill
- harness-cleanerSkill
- image-genSkill
- k8s-debugSkill
- retroSkill
- sdd-workflowSkill
- ste100Skill
- teammate-protocolSkill
- technical-seoSkill
- ux-copySkill
- vector-genSkill
- web-design-guidelinesSkill
- writing-for-agentsSkill
The file
Files
Shared knowledge base — the wiki (consult per size; contribute back)
The team keeps one persistent, cross-project Obsidian vault as long-lived memory across every engagement — remote https://gitlab.com/<your-org>/wiki/<you>, local ~/Documents/Projects/obsidian/<you>/. When the task reads it, reuse what it already knows instead of re-researching or re-deciding, cite what you use as [[Page Title]], and file durable cross-project knowledge back into it.
The read is gated by size. XS and lane-S delivery work, a review, a /verify, and a UX or feed run do not read the vault at all; lane M/L work, research, and venture work read wiki/index.md and the pages it names for the task's domain; the vault's AGENTS.md is read only before a write (→ RP-46). Contribute back only when the task produced cross-project knowledge that no existing page holds.
At the start of a task that reads the vault, read ${CLAUDE_PLUGIN_ROOT}/.claude/process/wiki.md — it carries the read-first and contribute-back protocol, the vault's own behavioral rules (raw/ is immutable, read before write, prefer updating over duplicating, log every operation, surface contradictions rather than overwriting), and the scope boundary that keeps project execution artifacts out of the wiki.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

