npx claudepluginhub caphtech/claude-marketplace --plugin disposable-pluginWant just this skill?
Then install: npx claudepluginhub u/[userId]/[slug]
Distill learnings from autopsy report into an improvement specification for the next cycle or production implementation. Extracts constraints, architecture decisions, interface contracts, and rejected options. Part of H-DGM cycle. Use after disposable-autopsy completes.
This skill uses the workspace's default tool permissions.
Disposable Distill — Phase 3: Synthesize
Transform autopsy findings into a structured improvement specification that guides the next iteration or production implementation.
Prerequisites
- Completed autopsy:
.disposable/cycles/cycle_{N}/autopsy-report.jsonmust exist - Template: references/distill-template.md in disposable-cycle skill
Procedure
Step 1: Load Autopsy Context
- Determine cycle: use
$ARGUMENTSif provided, otherwise read latest from.disposable/history.json - Load autopsy report from
.disposable/cycles/cycle_{N}/autopsy-report.json - Load spike metrics from
.disposable/cycles/cycle_{N}/spike-complete.json - If
parentCycleIdexists in metrics, load previous cycle's distill spec for delta analysis
Step 2: Extract Constraints
From autopsy findings, extract discovered constraints:
- Hard constraints (priority: must): From
criticalandmajorfindings- Security violations → security constraints
- Correctness failures → behavioral constraints
- Architecture issues → structural constraints
- Soft constraints (priority: should/could): From
minorandinfofindings- Performance patterns → optimization targets
- Readability issues → style guidelines
- Documentation gaps → documentation requirements
Format each constraint with:
- ID:
C-{NNN} - Description
- Source: axis name and finding ID
- Severity: must / should / could
Step 3: Identify Architecture Decisions
From autopsy architecture, maintainability, and dependency-hygiene axes:
- Extract decisions that emerged naturally in the prototype
- For each decision:
- Context: Why this decision was forced or emerged
- Decision: What the prototype chose
- Rationale: Evidence from autopsy scores and findings
- Trade-offs: What was sacrificed
- Compare with previous cycle's decisions (if any) to detect:
- Confirmed decisions (same choice, improved score)
- Reversed decisions (different choice this cycle)
- New decisions (not present in previous cycle)
Step 4: Extract Interface Contracts
From the spike code and autopsy correctness / testability axes:
- Extract type signatures, API shapes, protocol definitions
- Mark contracts as:
- Validated: Tests exist and pass
- Assumed: No test coverage, derived from code
- Disputed: Test failures or autopsy findings suggest issues
Step 5: Document Rejected Options
From autopsy findings and prototype exploration:
- List approaches that were tried or considered but rejected
- For each:
- What the option was
- Why it was rejected (evidence from findings)
- Under what conditions it might be reconsidered
Step 6: Compile Implementation Notes
Insights that must carry forward:
- Non-obvious behaviors discovered during spike
- Gotchas and edge cases
- Environment-specific requirements
- Performance characteristics observed
Step 7: Identify Open Questions
Unresolved items that need investigation:
- Assumptions that need validation
- Trade-offs that need user input
- Dependencies on external factors
Step 8: Generate Distill Specification
Using references/distill-template.md, produce the specification:
- Fill all template sections
- Include cycle metadata (ID, timestamp, parent cycle)
- Cross-reference finding IDs from autopsy report
- Ensure every constraint has an evidence trail
Step 9: Save & Report
- Write specification to
.disposable/cycles/cycle_{N}/distill-spec.md - Mask sensitive data:
node {plugin_root}/scripts/dist/mask-sensitive.mjs \ .disposable/cycles/cycle_{N}/distill-spec.md --in-place - Present to user:
- Constraint count by severity
- Architecture decisions (new / confirmed / reversed)
- Interface contracts status
- Open questions requiring input
- Recommendation: iterate (another spike) or graduate (to production)
Output
.disposable/cycles/cycle_{N}/distill-spec.md— improvement specification- Ready for next
/disposable-spikecycle or production implementation
Graduation Criteria
Recommend graduating to production when:
- Previous autopsy verdict was PASS
- No
mustconstraints remain unaddressed from prior cycles - Architecture decisions are stable (no reversals in last 2 cycles)
- Interface contracts are all
validated - Open questions are resolved or deferred by user decision
Otherwise recommend iterating with another disposable spike.
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.