write
Write blog posts from session insights with material recall and multi-perspective analysis.
What this skill does
# Write Skill
Transform session insights and conceptual explorations into structured, publishable content through multi-perspective analysis and iterative refinement.
Invoke directly with `/write` when the user wants blog drafting from session insights.
## When to Use
Invoke this skill when:
- Converting framework development or analytical sessions into blog posts
- Writing about conceptual topics requiring multi-perspective review
- Structured iterative refinement anticipated
Skip when:
- Technical tutorials with code (standard writing)
- Documentation updates (direct Edit)
- Single-pass content without review need
## Workflow Overview
```
RECOLLECT → PROTHESIS(Context→Perspective→Inquiry→Synthesis) → FORMAT → DRAFT → REFINE → VALIDATE → FINALIZE
```
| Phase | Tool | Decision Point |
|-------|------|----------------|
| Recollect | /recollect protocol | Prior session material recognition |
| Prothesis | /frame protocol | Context-derived perspectives, parallel inquiry |
| Format | AskUserQuestion | Output type, language |
| Draft | Write | — |
| Refine | Edit (loop) | User feedback |
| Validate | /gap | Gap detection |
| Finalize | Edit | — |
## Phase Execution
### 0. Material Recall (/recollect)
Invoke `/recollect` to surface prior session material relevant to the drafting topic — terminology coined in earlier sessions, prior decisions referenced, framings already established. The recalled context enriches the Phase 1-3 context acquisition (`G(U) → C`), improving perspective selection in the multi-perspective analysis.
This phase is conditional: skip silently when the drafting topic has no prior session footprint (e.g., entirely new domain). Anamnesis's internal Phase 0 scan determines applicability.
### 1-3. Prothesis Protocol (Multi-Perspective Analysis)
Apply the Prothesis protocol (/frame) for epistemic analysis:
```
Phase 0: G(U) → C -- Context acquisition from session/topic
Phase 1: C → {P₁...Pₙ}(C) → Pₛ -- Perspectives derived FROM context (not predefined)
Phase 2: Pₛ → ∥I(Pₛ) → R -- Parallel inquiry with Horizon Limits
Phase 3: R → Syn(R) → L -- Synthesis: convergence, divergence, assessment
```
**Key differences from standalone /frame**:
- Continues automatically to Format phase after Synthesis
- Lens L becomes input for content generation
Reference: `prothesis/skills/frame/SKILL.md`
### 4. Format Decision
Present output options:
- Blog Post (Korean/English)
- Essay
- Newsletter
- Thread
### 5. Draft Generation
Write initial draft to `~/.claude/.write/` directory:
- Filename: `YYYY-MM-DD-{topic-slug}.md`
- Structure: Hook → Context → Framework → Application → Implications
### 6. Iterative Refinement
Loop on user feedback:
- Incremental changes → Edit directly
- Structural changes → Generate option versions (A, B, C)
Exit conditions:
- User approval
- Explicit "finalize" command
### 7. Gap Detection
Invoke /gap for final validation:
- Procedural gaps
- Consideration gaps
- Duplicate content
**Composition note**: When /write output is downstream-reviewed by /comment-review, this Phase 7 internal /gap and /comment-review's Scan Step 2 /gap address distinct scopes (internal draft quality here vs. fixation-event decision quality downstream). Both invocations are intentional; the scope distinction preserves the /gap invariant.
### 8. Finalization
Apply final edits. Optionally clean intermediate versions.
## Quality Criteria
| Metric | Limit |
|--------|-------|
| Concepts per section | ≤3 |
| Framework components | ≤5 |
| Abstraction layers | ≤2 |
## Content Transformation
### What Becomes Content
| Session Element | Blog Element |
|-----------------|--------------|
| Problem context | Opening hook |
| Multi-perspective analysis | Framework structure |
| Convergence points | Core thesis |
| Divergence points | Discussion sections |
| Resolution approach | Actionable methodology |
### What Gets Filtered
- Tool invocations, command outputs
- Trial-and-error debugging steps
- Redundant restatements
- Context-specific details (paths, configs)
## Integration
This skill integrates with:
- **/recollect** — Material recall (Phase 0)
- **/frame** — Multi-perspective analysis (Phases 1-3)
- **/gap** — Gap detection (Phase 7)
## Additional Resources
For detailed workflow steps and content transformation rules:
- **`references/workflow.md`** — Complete phase descriptions
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.