Wikipedia Human Style Writing

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

1. 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.
2. 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.
3. 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.
4. Descriptive, not prescriptive. These words and shapes are overused, not banned. Use judgment over find-and-replace.

Workflow

1. Read the whole draft first; note the core message, key facts, and the intended voice and audience.
2. Sweep the draft against the tell categories in references/ai-writing-tells.md, looking for clusters.
3. 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/has in 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.
4. 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.
5. 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.

Run this — do not improvise

This capability's deterministic implementation is a RAPP single-file agent, linked beside this file as wikipedia_human_style_writing_agent.py and embedded as the fenced Python below (sha256 0637639fc9756e8d…; a byte-exact copy is also vaulted in the capsule comment at the end of this file). On a host with sandbox execution, run the linked file directly — if it is missing, write the fence contents verbatim to wikipedia_human_style_writing_agent.py first:

python3 wikipedia_human_style_writing_agent.py '{"key": "value"}'      # arguments as one JSON object
echo '{"key": "value"}' | python3 wikipedia_human_style_writing_agent.py   # or on stdin
python3 wikipedia_human_style_writing_agent.py --tool                      # emit the JSON tool contract

Treat stdout as a tool result. If it reports missing or unresolved inputs, stop and collect them. If it returns steps, execute those steps in order exactly as returned; if it returns instructions, follow them with the supplied inputs. Otherwise use the result verbatim. Do not invent behavior beyond that output. On a host without code execution, treat the Parameters schema and the code below as the exact specification and never paraphrase a step. Never edit inside the generated markers; a converter-equipped host can instead restore the original file checksum-verified with the installed rapp-agent-converter/scripts/toast.py convert SKILL.md --to agent.

"""WikipediaHumanStyleWriting -- 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.

Generated by the rapp skill from wikipedia-human-style-writing. The RCI capsule at the bottom of this file carries the full original; `toast.py convert` restores it byte-exact."""

import json
import re
import sys

try:
    from agents.basic_agent import BasicAgent
except ImportError:  # running OUTSIDE a brainstem -- stay executable anyway.
    class BasicAgent:  # noqa: D101 - minimal stand-in, same contract
        def __init__(self, name=None, metadata=None):
            if name:
                self.name = name
            if metadata:
                self.metadata = metadata

        def perform(self, **kwargs):
            return "Not implemented."

        def system_context(self):
            return None

        def to_tool(self):
            return {"type": "function", "function": {
                "name": self.name,
                "description": self.metadata.get("description", ""),
                "parameters": self.metadata.get("parameters", {})}}

# The procedural layer, verbatim from the source capability.
INSTRUCTIONS = '# Wikipedia Human Style Writing\n\nWrite and revise prose so it does not carry the tell-tale signs of AI-generated\ntext, using the patterns catalogued in Wikipedia's\n[Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing).\nThe full pattern catalogue lives in `references/ai-writing-tells.md` — consult it\nwhenever you need the specific words-to-watch lists, examples, or the era-by-era\n"AI vocabulary" breakdown.\n\n## Operating principles\n\n1. **Signs, not sins.** Every pattern below can appear in good human writing. The\n   giveaway is **density and mechanical repetition**, not a single instance. Target\n   clusters, not isolated words.\n2. **Fix the cause, not the symptom.** Most tells are surface markers of a deeper\n   problem: vagueness, puffery, or unsupported claims. Restore the specific fact or\n   cut the empty claim — don't just swap the flagged word and leave hollow content.\n3. **Preserve the truth and the voice.** Never invent or drop facts, figures,\n   quotes, dates, or sources. Keep the author's meaning, stance, and legitimate\n   emphasis. Do not "de-AI" a draft into corporate blandness.\n4. **Descriptive, not prescriptive.** These words and shapes are overused, not\n   banned. Use judgment over find-and-replace.\n\n## Workflow\n\n1. Read the whole draft first; note the core message, key facts, and the intended\n   voice and audience.\n2. Sweep the draft against the tell categories in `references/ai-writing-tells.md`,\n   looking for **clusters**.\n3. Revise each cluster by fixing the underlying issue:\n   - Replace generic praise with the specific, concrete fact\n     (regression-to-the-mean: "a revolutionary titan of industry" → the actual\n     achievement).\n   - Cut empty significance/legacy flourishes and trailing "-ing" analysis clauses.\n   - Restore plain `is/are/has` in place of "serves as / stands as / boasts /\n     features".\n   - Name a real source or delete a vague attribution ("experts argue", "observers\n     have noted").\n   - Break up mechanical rule-of-three lists, "not just X but Y" parallelisms, and\n     templated "Challenges / Future prospects" wrap-ups.\n   - Remove promotional/travel-brochure tone ("vibrant", "nestled", "rich tapestry",\n     "seamless").\n   - Thin out an over-dense cluster of era-specific "AI vocabulary" words.\n4. Clean the formatting tells: sentence-case headings (not Title Case), sparing\n   boldface (not `**bold lead-in:**` on every list item), varied punctuation instead\n   of space-surrounded em-dash overuse, no emoji-as-bullets, no stray markdown or\n   copy-pasted smart-quote residue, and no "In conclusion / In summary" filler.\n5. Re-read against the original to confirm no meaning, fact, or nuance drifted.\n\n## Guardrails\n\n- Do not add, remove, or alter facts, numbers, quotes, or citations to make text\n  "sound less AI".\n- Do not strip emphasis or specificity that the source genuinely supports.\n- Do not flatten a distinctive human voice into neutral mush — the goal is natural,\n  specific, human prose, not blandness.\n- One or two flagged words are usually fine; don't over-correct isolated hits.\n\n## Output\n\nReturn the revised prose first, copy-ready. When a review was requested, or when\nuseful, follow it with a short bulleted list of the notable tells you found and how\nyou addressed them.\n\n## Reference\n\n- `references/ai-writing-tells.md` — the full field guide: every tell category with\n  words-to-watch, examples, the era-by-era AI-vocabulary breakdown, and formatting\n  tells. Read the relevant section whenever you need detail beyond the summary above.'

# Ordered commands lifted verbatim from the capability's own documentation.
STEPS = []


class WikipediaHumanStyleWritingAgent(BasicAgent):
    def __init__(self):
        self.name = 'WikipediaHumanStyleWriting'
        self.metadata = {
          "name": "WikipediaHumanStyleWriting",
          "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 \u2014 or to review a draft for signs of AI writing. Apply it before returning any substantial prose the user will publish.",
          "parameters": {
            "type": "object",
            "properties": {},
            "required": []
          }
        }
        super().__init__(name=self.name, metadata=self.metadata)

    def perform(self, **kwargs):  # toaster:generated-perform
        return json.dumps({"status": "ok", "instructions": INSTRUCTIONS,
                           "inputs": kwargs,
                           "note": "Prose-only capability: follow INSTRUCTIONS "
                                   "with the given inputs."}, indent=2)

if __name__ == "__main__":
    #     echo '{"arg": "value"}' | python3 wikipedia_human_style_writing_agent.py
    #     python3 wikipedia_human_style_writing_agent.py '{"arg": "value"}'
    #     python3 wikipedia_human_style_writing_agent.py --tool          # emit the JSON tool contract
    _a = sys.argv[1:]
    if _a and _a[0] == "--tool":
        print(json.dumps(WikipediaHumanStyleWritingAgent().to_tool(), indent=2))
    else:
        _raw = _a[0] if _a else (sys.stdin.read().strip() or "{}")
        print(WikipediaHumanStyleWritingAgent().perform(**json.loads(_raw)))

# rci-capsule:v1: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