skills/writing-structure-planner/SKILL.md
Guides writing architecture planning using McPhee's structural diagramming method, helping select from 8 structure types (list, chronological, circular, dual/triple profile, pyramid, parallel, custom), create visual diagrams, and place gold-coin moments for engagement. Use when planning or organizing writing structure, outlining before drafting, restructuring disorganized drafts, or when user mentions outlining, organizing ideas, structure planning, article architecture, narrative flow.
npx skillsauth add lyndonkl/claude writing-structure-plannerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Related skills: Use writing-revision for revising existing prose, writing-stickiness for memorable messaging, writing-pre-publish-checklist for final quality checks.
Copy this checklist and track your progress:
Structure Planning:
- [ ] Step 1: Analyze material thoroughly
- [ ] Step 2: Explore structure options
- [ ] Step 3: Select and refine structure
Before starting: Review resources/structure-types.md for the 8 structure types, diagramming method, and selection criteria.
For analysis steps, output findings to analysis files in the current directory to ensure thorough coverage of all material. These analysis files remain in the project for your review.
Step 1: Analyze material thoroughly
Step 1.1: Gather and understand all material completely. Read everything the user has provided.
Step 1.2: Create analysis file writer-structure-material-analysis.md and output: all key points, anecdotes, data, quotes, and examples found in the material. Identify themes and patterns. Determine what's most important vs. supporting detail. Identify the natural organizing principle (time, space, importance, comparison). Note reader considerations (busy? engaged? unfamiliar? expert?).
Step 1.3: Present the material analysis to the user and confirm understanding is complete. Ask: "Did I miss any important material or themes?"
See resources/structure-types.md - Gather Your Material for detailed guidance.
Step 2: Explore structure options
Step 2.1: Read the analysis file. Review all 8 Structure Types with examples.
Step 2.2: Create analysis file writer-structure-options.md and sketch 3 different structure options. For each option include: structure type name, diagram sketch, how user's material maps to it, pros and cons.
Step 2.3: Test each option against Structure Selection Criteria. Present all 3 options to the user with your recommendation.
See resources/structure-types.md - Sketch 3 Options for detailed process.
Step 3: Select and refine structure
Step 3.1: Read the options file. Based on user's choice (or your recommendation if they defer), select the structure that best serves the material.
Step 3.2: Create the final annotated structure diagram. Map key moments and transitions. Identify where to place gold-coin moments throughout (especially middle sections). Annotate with pacing and transition notes.
Step 3.3: Verify structure supports the through-line (promise -> delivery -> resonance). Test: Does this feel inevitable or forced? Present final annotated structure diagram for user review before drafting.
See resources/structure-types.md - Select and Refine for detailed guidance.
How to know if structure is working:
If working: Readers won't notice it, they'll just experience flow and feel the piece is "well-organized."
If not working: Readers will feel lost, wonder "where is this going?", or abandon before the end.
Validate using resources/evaluators/rubric_structure.json. Minimum standard: Average score >= 3.5.
The 8 structure types available (see resources/structure-types.md for full details):
| Type | Best For | |------|----------| | List | Multiple independent points, how-to guides | | Chronological | Narratives, historical accounts, processes | | Circular/Cyclical | Hooking readers with drama, then providing context | | Dual Profile | Character profiles, examining topic from multiple angles | | Triple Profile | Complex characters in multiple contexts | | Pyramid (Inverted) | News, executive summaries, busy readers | | Parallel Narratives | Comparing/contrasting, multi-threaded stories | | Custom Diagrams | Unique material that doesn't fit standard types |
Requirements:
Common pitfalls:
Key resources:
Inputs required:
Outputs produced:
testing
Cluster a conference's event records into a small set of coarse themes with finer sub-clusters, an explicit outlier bucket, and soft (multi-membership) affinities — using the hybrid embed-then-label pipeline (embed abstracts, reduce, density-cluster, then LLM-label the clusters) when embedding libraries are available, and an LLM-reasoned hierarchical fallback when they are not. Embeddings do the grouping; the LLM only names the groups. Conference-agnostic. Use when turning structured event records into a navigable theme map for preference elicitation and scheduling, when you need 6-8 reasonable themes rather than 20 muddy ones, or when overlapping talks must belong to more than one theme. Trigger keywords - theme clustering, cluster talks, embed then label, soft membership, outlier talks, conference themes, topic map.
development
Build a personal conference schedule as a constraint-optimization problem — hard constraints (no time overlap, room-to-room travel time, capacity/registration, the attendee's own must-attends and blackouts) plus a user-owned weighted objective trading interest against breadth, pacing (maximize contiguous free time), and serendipity. Surfaces unbreakable conflicts (two high-value overlapping talks the model cannot rank) as decisions for the human rather than silently picking, and reports what each choice traded away. Conference-agnostic. Use to turn a preference profile plus a theme map into a day-by-day plan, to resolve overlapping sessions, or to balance a packed vs paced schedule. Trigger keywords - schedule optimization, conference schedule, constraint optimization, overlapping talks, contiguous free time, conflict surfacing, packed vs paced.
development
Parse a heterogeneous conference program (markdown, HTML, PDF-derived text, or JSON) into normalized event records with per-field confidence scores and independent classification axes (topic, depth, format, prerequisites, recorded, capacity). Detects the program's format before extracting, treats every inferred field as uncertain (present vs inferred vs missing), and flags thin or missing abstracts so downstream enrichment can target them. Conference-agnostic. Use when ingesting a conference or event schedule into a structured store, normalizing a talk/session list, or extracting per-session metadata with calibrated confidence. Trigger keywords - program ingestion, parse schedule, session extraction, event records, conference program, talk metadata, per-field confidence.
development
Build a personalized preference profile from a small number of well-chosen, cluster-grounded questions instead of a long survey. Represents the person's interests as an uncertainty region over the theme map, picks the single highest-information-gain choice-based question (contrasting real talks from different clusters), balances exploiting known interests against exploring uncertain ones, deliberately injects outlier probes to fight selection bias, and stops as soon as the schedule would be stable. Also elicits the user-owned objective weights and hard constraints. Interactive — runs where it can actually ask the person. Conference-agnostic. Use to turn a theme map into a preference profile, to decide what to ask a conference attendee, or to elicit scheduling priorities. Trigger keywords - preference elicitation, ask few questions, information gain, choice-based questions, selection bias probe, objective weights, attendee preferences.