wikipedia-human-style-writing
Use this skill whenever the user asks to write, rewrite, humanise, de-AI, or polish prose so it doesn't read as AI-generated — or to review a draft for signs of AI writing. Apply it before returning any substantial prose the user will publish.
- License 许可
- MIT
- 最近更新
- 2026-11-12
- Stars
- ★ 103
- Forks
- 119
01 前言 Front Matter
- name
- wikipedia-human-style-writing
- description
- Use this skill whenever the user asks to write, rewrite, humanise, de-AI, or polish prose so it doesn't read as AI-generated — or to review a draft for signs of AI writing. Apply it before returning any substantial prose the user will publish.
02 资源文件 3
- 参考文档metadata.json494 B
- 参考文档README.md1.3 KB
- 参考文档references/ai-writing-tells.md8.1 KB
03 SKILL.md 正文
Wikipedia Human Style Writing
Write and revise prose so it does not carry the tell-tale signs of AI-generated
text, using the patterns catalogued in Wikipedia's
Signs of AI writing.
The full pattern catalogue lives in references/ai-writing-tells.md — consult it
whenever you need the specific words-to-watch lists, examples, or the era-by-era
"AI vocabulary" breakdown.
Operating principles
- Signs, not sins. Every pattern below can appear in good human writing. The giveaway is density and mechanical repetition, not a single instance. Target clusters, not isolated words.
- Fix the cause, not the symptom. Most tells are surface markers of a deeper problem: vagueness, puffery, or unsupported claims. Restore the specific fact or cut the empty claim — don't just swap the flagged word and leave hollow content.
- Preserve the truth and the voice. Never invent or drop facts, figures, quotes, dates, or sources. Keep the author's meaning, stance, and legitimate emphasis. Do not "de-AI" a draft into corporate blandness.
- Descriptive, not prescriptive. These words and shapes are overused, not banned. Use judgment over find-and-replace.
Workflow
- Read the whole draft first; note the core message, key facts, and the intended voice and audience.
- Sweep the draft against the tell categories in
references/ai-writing-tells.md, looking for clusters. - Revise each cluster by fixing the underlying issue:
- Replace generic praise with the specific, concrete fact (regression-to-the-mean: "a revolutionary titan of industry" → the actual achievement).
- Cut empty significance/legacy flourishes and trailing "-ing" analysis clauses.
- Restore plain
is/are/hasin place of "serves as / stands as / boasts / features". - Name a real source or delete a vague attribution ("experts argue", "observers have noted").
- Break up mechanical rule-of-three lists, "not just X but Y" parallelisms, and templated "Challenges / Future prospects" wrap-ups.
- Remove promotional/travel-brochure tone ("vibrant", "nestled", "rich tapestry", "seamless").
- Thin out an over-dense cluster of era-specific "AI vocabulary" words.
- Clean the formatting tells: sentence-case headings (not Title Case), sparing
boldface (not
**bold lead-in:**on every list item), varied punctuation instead of space-surrounded em-dash overuse, no emoji-as-bullets, no stray markdown or copy-pasted smart-quote residue, and no "In conclusion / In summary" filler. - Re-read against the original to confirm no meaning, fact, or nuance drifted.
Guardrails
- Do not add, remove, or alter facts, numbers, quotes, or citations to make text "sound less AI".
- Do not strip emphasis or specificity that the source genuinely supports.
- Do not flatten a distinctive human voice into neutral mush — the goal is natural, specific, human prose, not blandness.
- One or two flagged words are usually fine; don't over-correct isolated hits.
Output
Return the revised prose first, copy-ready. When a review was requested, or when useful, follow it with a short bulleted list of the notable tells you found and how you addressed them.
Reference
references/ai-writing-tells.md— the full field guide: every tell category with words-to-watch, examples, the era-by-era AI-vocabulary breakdown, and formatting tells. Read the relevant section whenever you need detail beyond the summary above.
04 同仓库更多 Skills
stakeholder-and-decision-map
Mines customer interactions to identify stakeholders, infer their likely roles and engagement, map the decision process, and highlight who or what may be missing. Use when asked to "map a deal's buying group", identify influential or missing stakeholders, "assess who has gone quiet", or "explain how the customer will decide". Do not use for phased engagement plans, contact sequences, choosing or drafting outreach to the single next contact, seller or team performance reviews, or contacting, scheduling, or changing records.
sales-progress-update
Creates or refreshes a sales progress update for a manager or team about work done, deal movement, pending outcomes, supported forecast position, and help needed. Use when asked to "create my weekly sales update", "refresh my sales progress deck", "report my forecast position", "where do I stand against my quarter forecast", or "catch my manager up on committed deals". Do NOT use for non-sales project updates, a since-date deal change digest, momentum or blocker analysis, meeting prep, or outreach drafting.
submission-assemble
Put the checked CSR or 510(k) sections together in template order with a reviewer-facing open-items register, as a draft package for human sign-off. Use when the user asks "assemble the CSR draft", "put the module together for review", "build the review package with the open items on top", "compile the 510(k) sections in order" or "package this up for the submission lead". Do NOT use for assembling an unchecked draft - use consistency-check instead. Do NOT use for loading protocol, SAP or TLF sources - use source-ingest instead. Do NOT use for compiling general documents or slide decks - use the built-in docx or pptx skill instead. Do NOT use for filing or submitting to a regulator - use the sponsor's validated gateway, operated by a human, instead. Guardrail: draft for human approval only (L1); status is draft_clean or draft_open_items, never submitted.
source-ingest
Pull every number, date and population definition out of a study's protocol, SAP, TLF tables, investigator brochure and prior approved text into one cited fact map, keyed per config/field-dictionary.json, before any CSR or 510(k) section is written. Use when the user asks "here's the locked TLF set and SAP, set up the CSR", "load the protocol and tables before we start drafting", "what figures do we have from the database lock?", "pull the disposition counts out of Table 14.1.1" or "ingest the IB for the 510(k)". Do NOT use for drafting or assembling submission sections - use section-draft or submission-assemble instead. Do NOT use for reconciling a patient's medications - use the discharge-care-transition plugin instead. Guardrail: reads and cites sources only; never estimates, rounds or invents a fact.
section-plan
Work out which sections a CSR or 510(k) requires, from the templates in config, check each one against the cited fact map, and name what is missing before a word is drafted. Use when the user asks "what do we still need before we can draft the CSR?", "which sections are ready to start?", "what's blocking the performance data section?", "do we have everything for the synopsis?" or "map our tables to the E3 structure". Do NOT use for writing section language - use section-draft instead. Do NOT use for cross-checking a finished draft - use consistency-check instead. Do NOT use for outlining general Word documents or business reports - use the built-in docx skill instead. Only structures with a template in config are supported. Guardrail: plans only; never marks a section ready on a missing fact and never invents a structure.
section-draft
Write or revise the language for one planned CSR or 510(k) section - synopsis, efficacy, safety, discussion, device description - using only figures already in the cited fact map, each with its TLF or SAP citation. Use when the user asks "draft the Synopsis from our locked tables", "write up safety from Table 14.3.1", "give me a first pass at the discussion", "draft the device description for the 510(k)" or "tighten the wording of the Discussion section". Do NOT use for supplying a number not already in source_facts - use source-ingest instead. Do NOT use for verifying a draft's figures - use consistency-check instead. Do NOT use for appeal letters, clinical notes or discharge summaries - use the matching HLS plugin instead. Guardrail: drafts for human approval only (L1); never asserts an unsourced number or harmonises two figures.