writing-pre-publish-checklist
$
npx mdskill add lyndonkl/claude/writing-pre-publish-checklistExecutes final quality checks before publishing writing.
- Catches issues revision and stickiness enhancement miss.
- Depends on user intent to pre-publish or share.
- Uses binary pass/fail decisions for each check item.
- Flags problems to user instead of silently fixing.
SKILL.md
.github/skills/writing-pre-publish-checklistView on GitHub ↗
--- name: writing-pre-publish-checklist description: Runs a comprehensive six-section quality checklist (content, structure, clarity, style, polish, final tests) before writing is shared or published, catching issues that revision and stickiness enhancement might miss. Use when performing final quality checks before sharing, publishing, or submitting writing, or when user mentions pre-publish, final check, ready to publish, last review, quality check, or about to share. --- # Writing Pre-Publishing Checklist ## Table of Contents - [Core Principles](#core-principles) - [Workflow](#workflow) - [Check Details](#check-details) - [Guardrails](#guardrails) - [Quick Reference](#quick-reference) **Related skills:** Use `writing-structure-planner` for planning structure, `writing-revision` for deep prose revision, `writing-stickiness` for memorable messaging. ## Core Principles 1. **Systematic, not subjective**: Follow the checklist completely, don't skip sections 2. **Fresh eyes perspective**: Read as if seeing the piece for the first time 3. **Binary decisions**: Each check item is pass/fail, not "sort of" 4. **Flag, don't fix**: Identify issues and present to user rather than silently fixing 5. **Final gate, not revision**: This catches remaining issues, not does deep rewriting ## Workflow Copy this checklist and track your progress: ``` Pre-Publishing Checklist: - [ ] Section 1: Content check - [ ] Section 2: Structure check - [ ] Section 3: Clarity check - [ ] Section 4: Style check - [ ] Section 5: Polish check - [ ] Section 6: Final tests ``` **Before starting:** This is a systematic pass through the complete piece. Read the entire document first to understand context, then work through each section. ### Section 1: Content Check Step 1.1: Read the entire piece. Identify the core message. Verify core message is crystal clear - could a reader state it back in one sentence? Step 1.2: Check all facts for accuracy. Flag any claims that need verification. Note any statistics, dates, names, or specific details that should be double-checked with the user. Step 1.3: Evaluate examples and evidence. Are examples relevant and appropriate for the audience? Are arguments sound and complete? Is there any missing information that would leave readers with unanswered questions? Present Content Check results: ``` Content Check: - [ ] Core message crystal clear - [ ] All facts checked for accuracy - [ ] Examples relevant and appropriate - [ ] Arguments sound and complete - [ ] No missing information Issues found: [list any issues] ``` ### Section 2: Structure Check Step 2.1: Evaluate the opening. Does it hook readers? Would someone continue reading after the first paragraph? Step 2.2: Check flow and transitions. Is the logical flow smooth throughout? Do transitions between sections work? Are there any jarring jumps? Step 2.3: Examine the middle and ending. Does the middle section have gold-coin moments (rewards for the reader)? Does the conclusion satisfy - does it deliver on the promise of the opening? Present Structure Check results: ``` Structure Check: - [ ] Opening hooks readers - [ ] Flow is logical and smooth - [ ] Transitions work smoothly - [ ] Middle section has gold coins - [ ] Conclusion satisfies Issues found: [list any issues] ``` ### Section 3: Clarity Check Step 3.1: Scan for jargon. Is all jargon either removed or explained? Is it appropriate for the target audience? Step 3.2: Check for ambiguity. Are there ambiguous pronouns? Garden-path sentences that require re-reading? Any sentences where meaning is unclear? Step 3.3: Verify audience fit. Is technical accuracy maintained? Is the level of detail appropriate for the target audience? Present Clarity Check results: ``` Clarity Check: - [ ] No jargon (or all jargon explained) - [ ] No ambiguous pronouns - [ ] No garden-path sentences - [ ] Technical accuracy maintained - [ ] Appropriate for target audience Issues found: [list any issues] ``` ### Section 4: Style Check Step 4.1: Verify tone consistency. Is the tone consistent throughout? Does it shift inappropriately between sections? Step 4.2: Check voice and sentence variety. Is the voice appropriate for the audience and purpose? Is there good sentence variety (mix of short, medium, long)? Rate sentence variety on a 1-10 scale (target 7+). Step 4.3: Scan for remaining clutter. Is there any clutter that should have been caught in revision? Does active voice predominate? Present Style Check results: ``` Style Check: - [ ] Tone is consistent - [ ] Voice is appropriate - [ ] Sentence variety is good (score: X/10) - [ ] No clutter remains - [ ] Active voice predominates Issues found: [list any issues] ``` ### Section 5: Polish Check Step 5.1: Check mechanics. Scan for spelling errors, grammar issues, and punctuation problems. Step 5.2: Verify formatting. Is formatting consistent throughout (headings, lists, emphasis, spacing)? Do links work (if applicable)? Present Polish Check results: ``` Polish Check: - [ ] Spelling checked - [ ] Grammar correct - [ ] Punctuation proper - [ ] Formatting consistent - [ ] Links work (if applicable) Issues found: [list any issues] ``` ### Section 6: Final Tests Step 6.1: Read-aloud test. Read the piece aloud (or simulate reading aloud). Flag any sections that sound awkward, trip over themselves, or lose momentum. Step 6.2: Intent test. Does the piece achieve its stated intent? Does it satisfy the target audience's needs? Step 6.3: Pride test. Present the overall assessment - is this piece ready for its intended audience? Note any remaining concerns. Present Final Tests results: ``` Final Tests: - [ ] Read aloud - sounds good - [ ] Achieves stated intent - [ ] Satisfies target audience needs - [ ] Ready for publication Overall assessment: [PASS / PASS WITH NOTES / NEEDS REVISION] ``` ### Final Summary Present the complete checklist results in a single summary: ``` Pre-Publishing Checklist Summary: ================================ Content: [PASS/FAIL] - [brief note] Structure: [PASS/FAIL] - [brief note] Clarity: [PASS/FAIL] - [brief note] Style: [PASS/FAIL] - [brief note] Polish: [PASS/FAIL] - [brief note] Final: [PASS/FAIL] - [brief note] Overall: [READY TO PUBLISH / NEEDS ATTENTION] Issues requiring action: 1. [issue] 2. [issue] ``` Validate using [resources/evaluators/rubric_pre_publish.json](resources/evaluators/rubric_pre_publish.json). **Minimum standard**: Average score >= 3.5. ## Check Details | Section | Focus | Key Questions | |---------|-------|---------------| | Content | Accuracy & completeness | Is the core message clear? Facts correct? | | Structure | Organization & flow | Does it hook, flow, and satisfy? | | Clarity | Readability | Can audience understand without re-reading? | | Style | Consistency & voice | Is tone consistent? Voice appropriate? | | Polish | Mechanics | Spelling, grammar, punctuation, formatting? | | Final | Overall quality | Read-aloud test? Achieves intent? | ## Guardrails **Requirements:** 1. **Complete all 6 sections**: Run every section even if the writing seems good 2. **Binary pass/fail**: Each checklist item gets a clear pass or fail, not "maybe" 3. **Flag to user**: Present issues for the user to address rather than silently fixing 4. **Context-aware**: Adjust standards to context (blog post vs. academic paper vs. email) 5. **Honest assessment**: Give genuine feedback even if it means more work is needed **Common pitfalls:** - Rubber-stamping everything as "pass" without careful review - Skipping the read-aloud test (it catches issues nothing else does) - Not adjusting standards for the specific publication context - Trying to do deep revision instead of flagging issues - Missing formatting inconsistencies in longer pieces ## Quick Reference **Key resources:** - **[resources/evaluators/rubric_pre_publish.json](resources/evaluators/rubric_pre_publish.json)**: Quality scoring criteria **Inputs required:** - Finished or near-finished piece of writing - Target audience and publication context - Stated intent or core message **Outputs produced:** - Complete 6-section checklist with pass/fail for each item - List of issues requiring attention - Overall publication readiness assessment
More from lyndonkl/claude
- abstraction-concrete-examplesBuilds structured abstraction ladders that translate high-level principles into concrete, actionable examples across 3-5 levels. Bridges communication gaps, reveals hidden assumptions, and tests whether abstract ideas work in practice. Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps.
- academic-letter-architectGuides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.
- adr-architectureDocuments significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.
- adverse-selection-priorProduces a Bayesian prior probability that an offered transaction is +EV for the recipient, given that the counterparty chose to propose it. Applies Akerlof market-for-lemons logic -- if they offered it, they believe it is +EV for them, so the prior that it is +EV for us is materially below 50%. Reusable across trade evaluation, waiver drops (another team dropping a player is also adverse selection), job-offer analysis, M&A, and any "someone offered me this" situation. Use when you receive an unsolicited trade/offer/proposal, analyzing incoming trade prior, evaluating why a counterparty proposed a deal, or when user mentions adverse selection, market for lemons, why did they offer this, incoming trade prior, they proposed it, Bayesian adjustment on received offer.
- alignment-values-north-starCreates actionable alignment frameworks that give teams a shared North Star (direction), values (guardrails), and decision tenets (behavioral standards). Enables autonomous decision-making while maintaining organizational coherence. Use when starting new teams, scaling organizations, defining culture, establishing product vision, resolving misalignment, creating strategic clarity, or when user mentions North Star, team values, mission, principles, guardrails, decision framework, or cultural alignment.
- analogy-weight-checkFor every analogy in a substacker draft, verifies it carries mechanical weight — the analogy does real work explaining the mechanism, not merely decorates it. Cross-references analogy-catalog.md for novelty (is this analogy reused from a prior post?) and domain fit (biology > organizational > sports preferred; physics/military disfavored). Use whenever an analogy appears in the draft. Trigger keywords: analogy weight, decorative, mechanical weight, reused analogy, catalog check, metaphor check.
- answer-uncomfortable-questionTakes one strategic question about substacker ("should we launch paid?", "is this section dead?", "are we writing for the wrong audience?") and produces the mandatory evidence + reasoning + downside triad plus a recommendation. Used 3 times per Growth Strategist review. Trigger keywords: uncomfortable question, strategic question, evidence reasoning downside, triad.
- attribute-performanceFor each substacker post that materially over- or under-performs the rolling baseline (|z| ≥ 1.0), produces a plain-English attribution paragraph with calibrated confidence (high / medium / low / unexplained). Considers subject-line effect, topic zeitgeist, external share, day-of-week, length effect, and audience-notes signals. Labels unexplained outliers explicitly rather than fabricating a story. Use after compute-baseline when outlier posts exist. Trigger keywords: attribution, why did this post work, outlier explanation, performance analysis.
- auction-first-price-shadingComputes the optimal shaded bid for a first-price sealed-bid auction given a true private value, an estimate of the number of competing bidders N, and a value-distribution assumption. Implements the `(N-1)/N` equilibrium shading rule for uniform private values, adjusts for log-normal or empirical value distributions, layers a risk-aversion adjustment, and caps output against the bidder's remaining budget. Domain-neutral auction theory reusable across fantasy sports (baseball FAAB, NBA/NHL waiver auctions), prediction-market limit sizing, sealed procurement bids, and any blind-bid context. Use when user mentions "first-price auction bid", "sealed bid shading", "(N-1)/N", "FAAB bid amount", "auction shading", "optimal bid first-price", "bid for sealed-bid", "blind bid sizing", or when downstream logic needs a principled shade factor rather than an ad-hoc heuristic.
- auction-winners-curse-haircutApplies a Bayesian haircut to a bid valuation for common-value auctions where winning is itself evidence the bidder over-estimated. Takes a raw valuation, a value-type classification (common_value / private_value / mixed), the number of informed bidders N, and a signal-dispersion estimate, and returns an adjusted valuation. Domain-neutral and reusable across fantasy FAAB, prediction markets, M&A bids, ad-auction budgets, and any generic bidding context. Use when user mentions "winner's curse", "common value auction", "valuation haircut", "adverse valuation", "Bayesian bid adjustment", or "over-paying in auction".