From meridian
Use after completing features, resolving complex bugs, or when hard-won knowledge would otherwise be lost
How this skill is triggered — by the user, by Claude, or both
Slash command
/meridian:documentThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Capture knowledge for humans. Not for AI, not for ceremony — for the person who maintains this code in six months.
Capture knowledge for humans. Not for AI, not for ceremony — for the person who maintains this code in six months.
If the project has a docs/ folder, use it. The spec file from brainstorm is a starting point, but it needs rewriting — specs are instructions for an agent, docs are explanations for a person.
Write for someone who will use or maintain this feature. What does it do, how does it work, what should they know.
When a complex issue is resolved, especially one that took significant investigation:
Place this close to the relevant code: inline comments for small gotchas, a dedicated doc for complex ones.
For complex ongoing work — like replicating engine-specific rendering in WebGL, or fighting a particularly tricky integration — maintain a living doc of approaches tried:
## Approaches Tried
- **Gamma correction swap (sRGB -> linear)** — didn't work because [reason]. See [source].
- **Manual tone mapping curve** — partially worked but [limitation].
- **[What actually worked]** — works because [explanation]. Key insight: [the non-obvious thing].
This prevents future sessions from re-treading the same ground. If the agent's first instinct is "maybe it's the gamma correction" but that was already tried and documented — the doc catches it.
When a non-obvious choice is made, document why. Not a formal ADR — just a brief note:
Lives in docs/ or as a comment near the relevant code, depending on scope.
execute, or direct invocation after completed worknpx claudepluginhub kodingdev/meridian --plugin meridianCreates bite-sized, testable implementation plans from specs or requirements, with file structure and task decomposition. Activates before coding multi-step tasks.