npx claudepluginhub levifig/loaf --plugin loafWant just this skill?
Then install: npx claudepluginhub u/[userId]/[slug]
Integrates learnings from shipped work into strategic documents. Use after completing significant work or when the user asks "what did we learn?"
This skill uses the workspace's default tool permissions.
templates/adr.mdtemplates/update-proposal.mdReflect
Update VISION, STRATEGY, and ARCHITECTURE based on proven implementation.
Contents
- Purpose
- When to Reflect
- Process
- Guardrails
- Related Skills
Input: $ARGUMENTS
Purpose
Strategy evolves through shipping, not theorizing.
After completing work, /loaf:reflect extracts learnings and proposes updates to strategic documents. Don't update strategy during planning or shaping. Update after implementation proves (or disproves) assumptions.
When to Reflect
- After completing a spec or shipping a significant feature
- After discovering something unexpected during implementation
- After a series of related sessions
- Periodically (monthly/quarterly) to consolidate learnings
Process
Step 1: Parse Input
$ARGUMENTS can be: a spec ID (SPEC-001), a topic ("authentication learnings"), or empty (general reflection on recent work).
Step 2: Gather Evidence
Sources:
- Completed specs (
docs/specs/SPEC-*.mdwith statuscomplete) -- look for "Lessons Learned" - Session files (
.agents/sessions/) -- insights, surprises, pivots - Recent commits (
git log --oneline -30) - Implementation reality -- what was harder/easier than expected? What assumptions were wrong?
Step 3: Interview for Insights
Ask: What surprised you? What would you do differently? Did any assumptions prove wrong? What did we learn about users or technical constraints? Strategic implications?
Step 4: Identify Implications
Map learnings to documents:
| Learning Type | Document |
|---|---|
| User behavior / market / problem understanding | STRATEGY.md |
| Direction changes | VISION.md |
| Technical constraints / patterns | ARCHITECTURE.md |
| Decision updates | ADR (new or supersede) |
Step 5: Draft Proposals
For each document needing updates, create proposals following update-proposal template.
Step 6: Present and Await Approval
Present all proposals grouped by document. Do NOT update strategic documents without explicit approval.
User may: approve all, approve some, modify proposals, defer updates, or request more evidence.
Step 7: Apply Updates
After approval:
- Update documents with approved changes
- Create ADRs if needed (see
/loaf:architecturefor format) - Archive completed specs if appropriate
- Announce what was updated
Guardrails
- Evidence-based -- proposals need supporting evidence from shipped work
- Post-implementation -- reflect after shipping, not before
- Get approval -- don't update strategic docs without confirmation
- Consolidate -- batch related learnings, don't create micro-updates
- Link back -- reference specs/sessions that informed the update
- Archive completed work -- move done specs to archive
Related Skills
- shape -- Notes strategic tensions for later reflection
- strategy -- Deep discovery (before reflection validates)
- architecture -- Technical decisions (creates ADRs)
- research -- Investigation that may inform reflection
Similar Skills
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.