lyndonkl/skills/structural-review
skills/structural-review/SKILL.md
--- name: structural-review description: Performs pass-1 structural review of a substacker essay draft — argument flow, out-of-order moves, buried topic sentences, missing pivots, weak signposting, paragraph-logic issues. Emits the "Argument flow" and "Structural blockers" sections of the Editor artifact. Use when reviewing a draft's macro-structure before addressing voice, when a draft feels like it meanders, or when the user asks whether the argument lands. Trigger keywords: structure, argumen
$ install --global
skillsauthnpx skillsauth add lyndonkl/claude skills/structural-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 25, 2026, 10:22 AM138.7s1 file scanned
SKILL.md
- name:
- structural-review
- description:
- Performs pass-1 structural review of a substacker essay draft — argument flow, out-of-order moves, buried topic sentences, missing pivots, weak signposting, paragraph-logic issues. Emits the "Argument flow" and "Structural blockers" sections of the Editor artifact. Use when reviewing a draft's macro-structure before addressing voice, when a draft feels like it meanders, or when the user asks whether the argument lands. Trigger keywords: structure, argument flow, outline, signposting, meandering, pivot, macro edit, substantive edit.
Structural Review
Table of Contents
- Workflow
- Expected essay shape
- Worked example
- Guardrails
Related skills: Called by the Editor as the first structural skill. Runs before voice-check, hedge-detector, slop-detector. Pairs with paragraph-rhythm-check (paragraph logic) and opener-critique / closer-critique.
Workflow
Structural review of draft D:
- [ ] Step 1: Extract paragraphs as an array. For each: first-sentence topic + word count
- [ ] Step 2: Produce a 1-line-per-paragraph outline of the draft AS READ
- [ ] Step 3: Compare to expected essay shape (see below)
- [ ] Step 4: Flag out-of-order moves, buried topic sentences, walls, missing pivots, weak signposts
- [ ] Step 5: Per flag: tier (1 or 2), paragraph index, quote, reason, ≤2 suggested rewrites
Expected essay shape
Writer's signature shape (from voice-profile signature moves + opening/closing patterns):
1. Confession / concrete admission (opener)
2. Reframe / thesis
3. Exposition (mechanism, data, arithmetic)
4. Pivot (usually a one-sentence paragraph)
5. Applied case / example (often the IPL/Kalshi trade or a pathology slide)
6. Bolded maxim or forward-looking close
Not every essay hits every beat — short reflective posts skip steps 3 and 5. Series-log posts compress 2-3 and always include a scoreboard in 6.
Flag if:
- Hook is news-based or generic-opener (see
opener-critique). - Step 3 (mechanism) appears before step 1 (confession). "In this post we'll explore" structure = tier-1.
- Step 5 is missing in a full essay (not a series-log). Writer's voice has lived texture; its absence is a signal.
- Step 6 is absent entirely (no close). Tier-1.
- Buried topic sentence: the paragraph's point is in sentence 3 or later. Flag as tier-2.
- Wall: paragraph >120 words with no internal pivot. Flag as tier-2.
Worked example
Draft outline (as Editor reads it):
- Para 1 (42 w): "In today's AI landscape, teams often wonder whether RAG or fine-tuning…"
- Para 2 (81 w): Defines RAG.
- Para 3 (68 w): Defines fine-tuning.
- Para 4 (bullets): Comparison list.
- Para 5 (55 w): "I think RAG is the right choice for most teams."
- Para 6 (37 w): "To summarize, both have merit."
Flags (structural):
- (Tier-1) Hook is generic ("In today's AI landscape…"). Expected: confession. Rewrites: (a) "I spent four months moving a RAG pipeline to a fine-tune. I was wrong about which would win." (b) "I had never shipped a fine-tune until last quarter."
- (Tier-1) Mechanism before confession. Structural ordering violates the writer's shape. Rewrite: restructure so confession precedes exposition.
- (Tier-1) No pivot paragraph. Suggest: insert one-sentence paragraph at ~paragraph 3.5 marking the turn.
- (Tier-1) Argument runs through a bulleted list (para 4). Rewrite: convert to 3 short paragraphs, one mechanism each.
- (Tier-2) Closer is "To summarize" — prompt residue + no bolded maxim. Rewrite: replace with a mechanism close (e.g., "You're choosing where your domain knowledge lives — in weights, or in retrieval.").
Guardrails
- Never flag voice issues. This skill is structural only.
- Never propose more than 2 rewrite options per flag.
- Flags are located by paragraph index. If the writer paginates sections, cite section + paragraph.
- Do not rewrite the draft. Rewrites are ≤2 sentences each, bracketed.
- Series posts (frontmatter
series: {slug}) get a special-case: step 5 often IS the scoreboard+trade narration, not an extended applied case. Don't flag absence. - If the draft is a how-to / methodology post (H2 headers throughout, numbered steps), the expected shape is different (intro → sections → wrap). Detect and adapt.
Quick reference
- Input: draft markdown.
- Output: the "Structural pass → Argument flow" + "Structural blockers" sections.
- Runs first in the Editor pipeline.
Related Skills
lyndonkl/conf-theme-clustering
testing
VerifiedTrustedCommunity
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.
127SKILL.mdUpdated Jun 28, 2026
lyndonkl/conf-schedule-optimization
development
VerifiedTrustedCommunity
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.
127SKILL.mdUpdated Jun 28, 2026
lyndonkl/conf-program-extraction
development
VerifiedTrustedCommunity
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.
127SKILL.mdUpdated Jun 28, 2026
lyndonkl/conf-preference-elicitation
development
VerifiedTrustedCommunity
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.
127SKILL.mdUpdated Jun 28, 2026