بنقرة واحدة
reflection-writing
// How and when to write a post-implementation reflection. Used by DEVELOPER after reviews are complete.
// How and when to write a post-implementation reflection. Used by DEVELOPER after reviews are complete.
Multi-agent team workflow for implementing tickets with peer-to-peer communication inside a single shared team. Used by chat-orchestrator for COMPLEX requests only (planner → wave → teardown). Single source of truth for cross-agent messaging.
Domain-by-domain interview to produce /app/docs/project-context.json. Invoked once by the orchestrator; the orchestrator then conducts all turns directly using Read/Write/Edit — no agent dispatching.
Shadcn/ui theming and component customization — CSS variables, OKLCH colors, dark mode, variants, wrappers. Load for any ticket involving colors, theme, UI layout, or component styling.
Playwright E2E testing patterns — web-first assertions, user-visible locators, network interception, fixtures, authentication, and parallel execution. Use when building or reviewing E2E tests with Playwright, when setting up browser testing for a web app, or when migrating from Cypress or Selenium.
When to write e2e tests, where to put them, and how to verify them. Apply to any task touching UI, filters, forms, or interactions.
How to find a Git worktree by task number without hardcoding paths. Use in hooks or scripts that need to locate a specific task's worktree.
| name | reflection-writing |
| description | How and when to write a post-implementation reflection. Used by DEVELOPER after reviews are complete. |
After all reviews are APPROVED, before SendMessaging the merger.
/app/docs/reflections/<SESSION_SHORT_ID>/<TASK_ID>.md
Absolute path, outside any worktree, on the shared volume (crm-docs).
SESSION_SHORT_ID is the first path segment of WORKTREE_PATH
(e.g. /app/worktrees/58c3f4c7/TASK-001 → 58c3f4c7).
One sub-folder per session avoids TASK-001 collisions across sessions.
Create the directory if it does not exist yet.
Hard cap: 1500 chars total. Shorter is better. Reflections are read by every future developer before implementing similar tasks; verbose ones are skipped or skimmed and waste tokens. Aim for the smallest set of load-bearing facts.
# TASK-XXX
## Gotchas
- 1-3 short bullets. Each must be a thing a future dev would NOT figure out
by reading the code (hidden constraint, surprising behavior, an axiom from
this ticket's context). NO obvious facts.
## Reusable
- 1-3 short bullets pointing to a function, file, or pattern that the next
similar ticket should reuse instead of re-inventing. Include the path.
That's it. NO sections like "what I learned", "what was tricky", "what I would do differently" — those produce blogposts. Only Gotchas + Reusable.
Knowledge transfer between tickets. Reading future devs read these BEFORE starting work in the same domain — keep the signal-to-noise ratio high.