bvandeusenandClaude Opus 5.5
f1fdc4a951
CI & Build / Python lint (push) Successful in 3s
CI & Build / Plugin hooks (push) Successful in 13s
CI & Build / TypeScript typecheck (push) Successful in 55s
CI & Build / integration (push) Successful in 1m3s
CI & Build / Python tests (push) Failing after 1m25s
CI & Build / Build & push image (push) Skipped
Loading a procedure now also reaches the moment it is for. Loading the reporting procedure is a report; loading the release procedure is a delivery. - Bundled skills: each SKILL.md declares `metadata: moments:`. The same declaration ships as Skill defaults (BUNDLED_SKILL_MOMENTS), because the server never sees the plugin's files. test_skill_moments holds the two together and pins the plugin name that qualifies the skill. - Stored processes: `moments` on create_process and update_process, stored in the note's data and returned by get_process. A `scribe-proc-<slug>` load resolves its process through the sync manifest at load time. The moments are not copied into the stub, which would go stale mid-session. - reachable_tools lists the skill loader whenever anything is mounted, since a process's moments are known only when it loads. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
1.5 KiB
1.5 KiB
name, description, metadata
| name | description | metadata | ||
|---|---|---|---|---|
| brainstorming | Use when exploring options or shaping a direction before committing — open up the solution space instead of jumping to the first idea. Triggers on "how should we approach X", "what are the options", weighing trade-offs, or any open-ended design question. Recall prior thinking first; capture the decision after. |
|
Brainstorming
Widen before you narrow. The first idea is rarely the best; the goal is a few real options and a reasoned choice — not a single path defended after the fact.
Recall first
search Scribe before generating from scratch — a prior decision, note, or
brainstorm on this often already exists. Build on it instead of repeating it.
Open up
- Generate a few genuinely different options, not variations of one. Include at least one you don't initially favor.
- For each: the core idea, what it's good at, and its main cost or risk — briefly.
- Resist converging until the space is actually explored.
Then choose
- Recommend one, and say why — the trade-off that decided it, not just the pick.
- Surface the 1–2 places you made an interpretive call, so the operator can redirect before it's baked in.
Capture the decision
When a direction is chosen, record it in Scribe (create_note, e.g. tag
decision): the choice, the alternatives weighed, and the reason. That's what
keeps the same question from being re-litigated later — and what a future
session reads to understand why, not just what.