--- name: editing-content description: Edits a draft in two passes and returns the edited text plus a change log. The prose pass removes documented AI writing patterns using reference/ai-tells.md, working from the costliest pattern down. The fact pass verifies every number, percentage, date, and named claim against the organization it is credited to at that organization's own publication, using reference/stat-verification.md. Use when asked to edit, polish, humanize, de-AI, fact-check, or verify a draft or a published article. Do not use to write new sections (use drafting-content). --- # Editing Content Prose first, then facts. A fabricated figure inside a badly written paragraph is easy to miss and obvious once the paragraph reads clean. ## Workflow Copy this checklist and track progress: ``` Edit progress: - [ ] Step 1: Prose pass, top down through ai-tells.md - [ ] Step 2: Fact pass, every figure to its primary source - [ ] Step 3: Write the change log - [ ] Step 4: Manual passes (read aloud, cadence, repetition) - [ ] Step 5: Second full pass ``` ### Step 1: Prose pass Work down `reference/ai-tells.md` in order. It runs from the costliest pattern to the cheapest, so a partial pass still removes the worst. Two rules about how to make each edit: - **Rewrite the sentence, never swap the word.** Substituting a synonym keeps the sentence that needed the banned word. A line that only worked with "seamless" in it was doing nothing. - **Read three sentences back before changing one.** A sentence edited in isolation stops connecting to its neighbours, and disconnected sentences are the thing being removed. ### Step 2: Fact pass For every number, percentage, currency figure, date, and named claim, follow the four steps in `reference/stat-verification.md` and assign one of five verdicts. A figure that cannot be sourced comes out. It does not soften into "many companies report". ### Step 3: Write the change log ```markdown | # | Original | Change | Reason | Source | |---|---|---|---|---| ``` Include the verified figures alongside the corrections. A log showing 14 checks and 2 corrections tells the next reader the work happened; a log showing 2 corrections reads as a list of mistakes. ### Step 4: Manual passes Nothing above catches these. | Check | What to listen for | |---|---| | Read the whole piece aloud | Any sentence you would not say to a colleague | | Cadence | A run of short declaratives, or a run of long ones. Both are metronomes | | Paragraph shape | Two consecutive paragraphs that look identical on screen | | Repetition of point | The same idea made twice in different words, usually two sections apart | | Value per sentence | Every line carries information or rhythm. Cut the rest | | Side of the desk | A paragraph describing the article's own contents belongs to the writer | ### Step 5: Second full pass Run Steps 1 to 4 again. The second pass finds what the first was too close to see. ## Verification loop When a mechanical checker is available, run it between Step 1 and Step 2, fix every failure, and re-run until it exits clean. `drafting-content/scripts/quality_gate.py` covers vocabulary, reframes, anaphora, headings, cadence, and scaffolding. A clean checker is the floor. Steps 4 and 5 are the ceiling and they have no script. ## Test it 1. A draft containing "This isn't a tool, it's a process." The prose pass should delete everything before the positive claim. 2. A draft citing a percentage to an aggregator. The fact pass should trace it to the primary source or remove it. 3. A draft where every paragraph runs two sentences. The manual pass should break the pattern. ## What still needs a person Cadence. The writer who produced the draft is the worst judge of how it sounds, which is why the read-aloud step exists and why it is the step people skip. --- ## FILE: `editing-content/reference/ai-tells.md` Save this block at `~/.claude/skills/editing-content/reference/ai-tells.md` ```markdown # AI Tells ## Contents - 1. Reframe constructions - 2. Performed punch-sentences - 3. Anaphora and negation runs - 4. Writer-side scaffolding - 5. Metronome rhythm - 6. Significance inflation - 7. Participle padding - 8. Dead vocabulary - 9. Copula avoidance - 10. Rule of three - 11. False ranges - 12. Elegant variation - 13. Inline-header lists - 14. Dead phrases and transitions - 15. Meta commentary - 16. Hollow frames - 17. Em dashes - What this list cannot do Ordered by cost. Work top down. Most of these are catalogued in [Wikipedia's Signs of AI Writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), which cites the research. Below are the ones that show up in marketing prose specifically. ## 1. Reframe constructions Any sentence that negates a framing, then asserts the corrected one. The most reliable single tell. - ✗ This isn't a productivity tool. It's a thinking partner. - ✓ It's a thinking partner. The negated half carries no information. Nobody needs to be told what something is not before learning what it is. **Disguises that clear most greps:** ``` Sure, dashboards work. But the interesting part is... Attribution gets all the attention, but retention is where... While the first approach might seem right, the second is... We didn't build a tool. We built a process. X, not Y. (the two-word form, easiest to miss) which isn't X, it's Y (hidden in a relative clause) is usually not X, it's Y (no comma before "not") ``` Same skeleton every time: concession, pivot, corrected claim. Delete everything before the claim. ## 2. Performed punch-sentences Short standalone declaratives that announce a point instead of making it. - ✗ The goal was simple. Nobody wanted complexity. That was the idea. - ✓ The goal was a brief in under 10 minutes, so anything adding a step got cut. Three or more in a row reads machine-written even when every word is clean. Fold setup and point together with connective tissue: so, and, because, which, where, but. Ration genuine single-sentence-for-impact lines to three in a whole piece. ## 3. Anaphora and negation runs Three sentences opening on the same word. Or the negation list: "no outline, no brief, no draft." Both survive every vocabulary scan. Rewrite to one positive statement, or to a real list with distinct openers. ## 4. Writer-side scaffolding Sentences whose subject is the article rather than the work. - ✗ The top row is the one worth sitting with. - ✓ Between 53% and 86% of citations go to pages that never mention the brand. - ✗ Two coverage limits, since a range without them is a claim you can't check. - ✓ Don't carry those ranges into a category outside B2B SaaS. - ✗ Five things accumulated in there, and each is worth something to you. - ✓ Five rules ended up in mine. The test: does the sentence describe the article, rate its own material, or announce a list? Every paragraph should open on an action taken, a thing that happened, a fact, or an instruction to the reader. ## 5. Metronome rhythm Every sentence the same length, every paragraph the same number of lines. Both directions are equally bad. All-short reads as social filler, all-long as dense filler. Aim for a spread: the bulk at 10 to 18 words, a good number shorter, a solid chunk at 19 to 28, a few over 29 that earn it. ## 6. Significance inflation Claiming importance instead of demonstrating it. - ✗ marking a pivotal moment in the evolution of content operations - ✓ after that, briefs took under 10 minutes State the fact. The reader decides what it means. Related: the appended clause explaining why the previous fact mattered. "Which is the point." Cut it. A fact needing an explanation was not specific enough. ## 7. Participle padding Trailing "-ing" phrases that look like analysis and contain none. - ✗ ...cutting brief time in half, highlighting the value of templates. - ✓ ...cutting brief time in half. Analysis worth having gets its own sentence with a specific claim. ## 8. Dead vocabulary ``` actually, shift, significantly, fundamentally, leverage, robust, seamless, streamline, optimize (verb), delve, realm, harness, unlock, elevate, empower, holistic, comprehensive, innovative, game-changer, cutting-edge, transformative, revolutionize, testament, pivotal, crucial, meticulously, showcase, foster, underscore, tapestry, move the needle, real, really, fix, ship, shipped, rather than, compound ``` Rewrite the sentence, do not swap the word. Scan headings too: a heading is the most read line on the page. ## 9. Copula avoidance Bloated verbs standing in for "is" and "has": serves as, stands as, marks a, boasts a, represents a, features a, holds the distinction of. - ✗ The template serves as a mechanism that represents our approach. - ✓ The template is a fixed section order. ## 10. Rule of three Three parallel items used to make shallow coverage look complete. "Speed, efficiency, and scale." Use two, four, or name the one that matters. Genuine factual sets are fine. ## 11. False ranges "From ancient traditions to modern innovations." If no meaningful midpoint can be named, the range is decoration. ## 12. Elegant variation Cycling synonyms to avoid repeating a word: the tool becomes the platform, then the solution, then the offering. Repeat the clearest word. ## 13. Inline-header lists Bold labels acting as mini-headings inside a paragraph, each followed by a definition. Convert to flowing prose or a proper list. A paragraph of bolded stubs is a table that lost its formatting. ## 14. Dead phrases and transitions ``` It's important to note that / It's worth noting In today's [anything] At the end of the day Moving forward In order to (say "to") Furthermore / Moreover / Additionally That said / That being said In other words To put this in perspective Here's the thing Let that sink in / Read that again What nobody tells you / Most people don't realize In this article, I will Let's dive in / Let's explore / Let's unpack ``` ## 15. Meta commentary Announcing the writing instead of doing it. "In this section we'll look at..." Say the thing. ## 16. Hollow frames Sentences that sound structural and carry no new fact. - ✗ This is where the magic happens. - ✗ The edit stage is where good content becomes great content. Test: does this sentence add a fact, or add texture? Texture is allowed occasionally as a breather. Two in a row is padding. ## 17. Em dashes None. Commas, periods, colons, semicolons, parentheses, or "to" for ranges. ## What this list cannot do It cannot tell whether a paragraph is written from the reader's side of the desk, and it cannot hear rhythm. Both need the read-aloud pass. ``` --- ## FILE: `editing-content/reference/stat-verification.md` Save this block at `~/.claude/skills/editing-content/reference/stat-verification.md` ```markdown # Stat Verification ## Contents - The rule - The four steps - The five verdicts - Patterns that produce bad figures - Where the primary source lives - What cannot be verified here - Output ## The rule Every figure gets checked against the organization it is credited to, at that organization's own publication. An aggregator repeating a figure is not a source. Neither is a blog post citing the report, a roundup listing the number, or a deck quoting it. Those are where fabricated figures survive, because each cites the last and none cites the study. ## The four steps 1. **Write the claim exactly.** Number, unit, year, and who it is credited to. Vague attribution ("studies show", "research suggests") fails before the search starts, because there is nothing to check. 2. **Search the primary source directly.** Query the number in quotes plus the organization plus the year: `"73%" Gartner 2026 marketing`. Searching the claim in prose form finds the articles repeating it. 3. **Open the report.** Not the press release summarizing the report, and not the blog post summarizing the release, unless the release is the only published form. 4. **Assign a verdict.** ## The five verdicts | Verdict | Meaning | Action | |---|---|---| | Verified | At the source, as stated | Leave it. Add the link if missing | | Misquoted | The source says something adjacent | Correct to the source's figure | | Stale | Correct for an earlier year | Update, or state the year in the sentence | | Miscredited | Exists, from a different organization | Recredit and relink | | Not found | Not at the source credited | Remove, or replace with a verified figure from the same source | ## Patterns that produce bad figures **The orphan percentage.** A clean round number with no organization attached. "Studies show 60% of marketers..." There is no study. Most common fabrication, easiest to spot. **The citation chain.** A cites B cites C, and C cites nothing. Follow the chain to the end. If it terminates in a blog post, the figure is unsourced. **The plausible drift.** A source said 34%; it travels as "over a third", then 40%, then "nearly half". Each step is a small rounding and the end is wrong. Check the original number, not the characterization. **The wrong-year survival.** A genuine figure from three years ago, still circulating as current. Verified but stale, which needs the year stated rather than removal. ## Where the primary source lives Go to the organization's own research or newsroom index rather than searching the open web. Research firms, analysts, and large vendors publish an index of their own studies, and that index is the fastest route to the figure. Government statistics agencies and standards bodies publish theirs as datasets with a citation format attached, which is the easiest kind to verify and the kind least often cited correctly. For a figure from a survey, find the methodology: sample size, sampling frame, date collected. A figure from an n of 40 self-selected respondents exists and does not support a claim about an industry. ## What cannot be verified here Figures that exist only in rendered page output or behind an interactive element. Pricing pages are the usual case, since many serve their numbers by script, so a raw fetch returns nothing and looks identical to a fabricated claim. Write "check current pricing at the source" and carry no figure. Do not guess, and do not carry a figure from a months-old screenshot. **One caution learned expensively:** a fetch failure reads exactly like a fabricated claim. Before deleting a figure because it "was not on the page", confirm the page arrived. Redirects, timeouts, and bot filters each return an empty result that looks like proof of absence. ## Output ```markdown | # | Figure | Credited to | Verdict | Corrected to | Source | |---|---|---|---|---|---| ``` Log the verified figures alongside the corrections. ```