lyndonkl/writing-revision
skills/writing-revision/SKILL.md
Applies a systematic three-pass revision system (Zinsser, King, Pinker, Clark) to existing drafts — Pass 1 cuts clutter, Pass 2 reduces cognitive load, Pass 3 improves rhythm. Use when revising, editing, or polishing drafts, cutting word count, tightening prose, improving readability, or fixing flow, or when user mentions revision, editing, cut clutter, too wordy, improve readability, fix the flow, reduce word count.
$ install --global
skillsauthnpx skillsauth add lyndonkl/claude writing-revisionInstall 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, 10:27 AM132.4s3 files scanned
SKILL.md
- name:
- writing-revision
- description:
- Applies a systematic three-pass revision system (Zinsser, King, Pinker, Clark) to existing drafts — Pass 1 cuts clutter, Pass 2 reduces cognitive load, Pass 3 improves rhythm. Use when revising, editing, or polishing drafts, cutting word count, tightening prose, improving readability, or fixing flow, or when user mentions revision, editing, cut clutter, too wordy, improve readability, fix the flow, reduce word count.
Writing Revision (Three-Pass System)
Table of Contents
- Core Principles
- Workflow
- Pass Overview
- Guardrails
- Quick Reference
Related skills: Use writing-structure-planner for planning structure, writing-stickiness for memorable messaging, writing-pre-publish-checklist for final publishing checks.
Core Principles
- One focus per pass: Each pass targets one dimension rather than fixing everything at once
- Cut 10-25%: King's formula - second draft equals first draft minus 10-25%
- Every word earns its place: If a word doesn't contribute, remove it
- First reading is correct reading: Readers shouldn't need to re-read sentences (Pinker)
- Rhythm creates engagement: Varied sentence lengths and strong endings keep readers moving
Workflow
Copy this checklist and track your progress:
Three-Pass Revision:
- [ ] Pass 1: Cut clutter (analyze -> improve)
- [ ] Pass 2: Reduce cognitive load (analyze -> improve)
- [ ] Pass 3: Improve rhythm (analyze -> improve)
Before starting: Review resources/revision-guide.md for the complete three-pass system with examples and the full transformation demonstration.
For each pass, analyze the entire draft first and output findings to an analysis file in the current directory, then read that file to make improvements. This ensures complete coverage.
Pass 1: Cut Clutter (Zinsser/King)
Goal: Cut 10-25% of word count. Make every word earn its place.
Step 1.1 - Analysis: Read entire draft. Create analysis file writer-pass1-clutter-analysis.md identifying all instances of: adverbs (-ly words), qualifiers (very, really, quite, somewhat), passive voice, weak verbs (is, are, was, were, has/have/had), throat-clearing phrases, and cliches. Calculate word count and set target for 10-25% reduction.
Step 1.2 - Improvement: Read analysis file. Work through entire draft making improvements: remove 70% of adverbs, delete qualifiers, convert passive to active voice, replace weak verbs with action verbs, eliminate throat-clearing, remove cliches. Verify word count reduction meets 10-25% target. Ensure every remaining word earns its place.
See resources/revision-guide.md - Pass 1 for detailed examples.
Pass 2: Reduce Cognitive Load (Pinker)
Goal: Make reading effortless. First reading should be correct reading.
Step 2.1 - Analysis: Read entire draft. Create analysis file writer-pass2-cognitive-load-analysis.md identifying all issues: garden-path sentences (temporarily mislead readers), buried topics, subject-verb-object separated by more than 7 words, ambiguous pronouns, broken topic chains, sentences requiring re-reading.
Step 2.2 - Improvement: Read analysis file. Work through entire draft: fix garden-path sentences, signal topic at start of each sentence, keep subject-verb-object close, clarify pronouns, repair topic chains, break overly complex sentences. Read aloud to verify no stumbles.
See resources/revision-guide.md - Pass 2 for detailed examples.
Pass 3: Improve Rhythm (Clark)
Goal: Create engaging flow through sentence variety and strong endings.
Step 3.1 - Analysis: Read entire draft. Create analysis file writer-pass3-rhythm-analysis.md analyzing: sentence lengths for each paragraph (list actual lengths), monotonous patterns (5+ similar-length sentences in a row), last word of each sentence (mark weak endings), gold-coin placement (identify gaps), opportunities for ladder of abstraction (concrete -> general -> concrete), sections lacking variety.
Step 3.2 - Improvement: Read analysis file. Work through entire draft: add short sentences for emphasis after longer ones, replace weak sentence endings with strong words, distribute gold-coin moments throughout (especially middle), apply ladder of abstraction, vary sentence lengths deliberately. Read aloud to verify flow. Confirm good mix of short, medium, and long sentences.
See resources/revision-guide.md - Pass 3 for detailed examples.
Validate using resources/evaluators/rubric_revision.json. Minimum standard: Average score >= 3.5.
Pass Overview
| Pass | Focus | Method | Target | |------|-------|--------|--------| | Pass 1 | Clutter | Zinsser/King | Cut 10-25% word count | | Pass 2 | Cognitive Load | Pinker | No re-reading needed | | Pass 3 | Rhythm | Clark | Varied lengths, strong endings |
Guardrails
Requirements:
- Preserve meaning: Keep the author's intended meaning intact while cutting or restructuring
- Analyze before improving: Always create the analysis file first, then make improvements based on findings
- Complete coverage: Analyze the entire draft in each pass, not just the first few paragraphs
- Measure reduction: Track actual word count reduction in Pass 1 (target 10-25%)
- Read aloud: After Passes 2 and 3, verify by reading aloud for stumbles and rhythm
Common pitfalls:
- Trying to fix everything in one pass (stick to one focus per pass)
- Only revising the opening paragraphs and losing steam
- Cutting so aggressively that voice is lost
- Not tracking actual word count reduction
- Skipping the analysis phase and jumping straight to editing
Quick Reference
Key resources:
- resources/revision-guide.md: Complete three-pass system with before/after examples
- resources/evaluators/rubric_revision.json: Quality scoring criteria
Inputs required:
- Draft text to revise (any stage)
- User's intent or core message (if known)
- Any constraints (word count target, tone preferences)
Outputs produced:
- Analysis files for each pass (clutter, cognitive load, rhythm)
- Revised draft with tracked word count reduction
- Summary of changes made in each pass
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