petar-djukic
UserClaude Code skills for rewriting AI-drafted prose to pass AI detectors: a measured three-step pipeline (structural rewrite, tell removal, cross-model diction) scored against Pangram, plus reference management and citation auditing.
Categories
Indexed Skills (14)
filter-tells
Detect and fix AI writing patterns recursively. Use when: reviewing text for AI tells, cleaning AI-generated drafts, checking for CoT leakage, measuring text perplexity and burstiness, making text sound human, fixing opening diversity. Triggers: filter-tells, ai detection, ai writing, perplexity, burstiness, CoT leakage, humanize text, opening diversity, sentence starts.
tighten-style
Tighten prose against a rule catalog: cut needless words, restore buried verbs and the active voice, and give paragraphs a spine. Checks sentence-level rules (needless words, intensifiers, hedge stacks, negative form, nominalizations) and paragraph-level structure (topic sentence, one topic, consequent order), citing rule IDs. Tightens toward the author's measured density, never past it. Triggers: tighten, tighten style, omit needless words, wordy, too wordy, cut the fat, edit for concision, copyedit, style rules, paragraph structure, active voice.
review-chapter
Critique a book chapter draft through six critics, each testing something a checker cannot: whether concepts are defined precisely, whether the claims survive someone who has done the work, whether a working programmer can follow it, whether the logic holds for a skeptical outsider, whether the opening earns the next page, and whether the real-world grounding is told as a story. Produces per-critic verdicts quoting the passages they judge, then the top three fixes in priority order. Triggers: review chapter, critique my chapter, chapter review, six critics, is this chapter any good, book chapter feedback, clarity test, bullshit test, pedagogy test, does this chapter work.
write-article
Complete a Substack article from a brainstorm file or outline. Research supporting data, verify sources, and produce a publication-ready article follo
seo-pass
Run an SEO analysis on a published or draft article, identify the search queries it should rank for, and apply concrete edits — subtitle rewrites, n
update-references
Find, download, read, and summarize research papers related to the work in the current directory. Searches arXiv, OpenAlex, Semantic Scholar, and Google Scholar, with a hierarchical mode (hubs, surveys, citation snowball). Maintains a CSL-YAML reference database (references.yaml) compatible with pandoc's --bibliography flag, so the same file serves both the skill and document builds. Triggers: update references, refresh the bibliography, find papers, related work, literature review, what's been published on, recent papers, cite sources for, background reading, summarize this paper, search scholar.
match-voice
Rewrite paragraphs of a draft in the author's voice using a second model family served by Ollama, with a verification gate before any text is spliced back. Retrieves voice anchors from the repository's writing-voice/ exemplars, sends paragraph plus anchors to a local (or cloud) Ollama model, then gates the result on citation/number preservation, meaning entailment, anchor similarity, and register. Triggers: voice rewrite, rewrite in my voice, ollama rewrite, rewrite paragraphs, local model rewrite, sound like my earlier papers, rewrite against writing-voice.
humanize
Three-step pipeline to move AI-drafted prose to human-passing on Pangram: a configurable structural step (match-outline for section-level rewriting, tighten-style for paragraph-level tightening, or skip), filter-tells (semantic cleanup), then match-voice --no-anchors (paragraph diction). Parameterized blueprint and anchor-tag selection, inter-step Pangram measurement, consolidated five-category writing-quality report. Venue mode (--venue <name>) resolves every choice from a writing-voice/venues/ profile instead of asking. Carries the pipeline's ordering contract: locked spans respected by every stage, inject-vernacular terminal, and after the terminal stage models read but never write. Triggers: humanize, humanize article, make it human, full rewrite pipeline, rewrite for pangram, three-step rewrite, humanize for venue.
match-outline
Whole-document voice analysis: compare a draft against a corpus profile, extract voice persona blueprints from exemplar papers, and rewrite the entire draft in one pass to match a voice. Uses gpt-oss:120b-cloud via Ollama by default; match-voice cleans AI diction downstream. Triggers: compare my outline, section analysis, does my intro match the field, methodology conventions, results conventions, rewrite in the style of, apply the voice, voice persona, exemplar, blueprint extraction, mimic this paper, rewrite my draft, whole-document rewrite.
patent-disclosure
Write and evaluate invention disclosures a patent professional can file. Guides the full workflow: claim drafting, prior-art search, the eleven-section disclosure written in the recommended order, and a four-axis self-assessment (novelty, non-obviousness, commercial value, subject-matter eligibility) with target scores. Domain-independent; a per-project context file supplies the technology domain, prior-art starting points, and commercial material. Triggers: patent disclosure, invention disclosure, patentability, is this patentable, prior art search, claim drafting, four-axis, Alice/Mayo, patent claim, IP disclosure, file a patent.
pattern-language
Write an Alexandrian pattern language (pattern-language.yaml) for a repository: read the existing materials, mine recurring force-configurations, and emit a YAML file in the fixed format shared by the existing pattern languages (declarative-agents, agent-failure-modes). Also validates and extends existing languages. Triggers: pattern language, design patterns yaml, extract patterns, mine patterns, pattern-language.yaml, Alexander patterns, forces and solution, pattern grammar, write the patterns file.
tune-anchors
Sweep anchor selections over a writing-voice corpus and report which tag query produces the best register outcome. Runs match-voice then tighten-style over (article × arm) combinations, ranks arms on the four-axis register composite, and optionally verifies the top candidates with an external detector. Triggers: tune anchors, sweep anchors, which anchors should I use, calibrate writing-voice, onboard corpus.
match-structure
Paragraph and sentence-level style metrics for a research corpus. Computes quantitative profiles (sentence/paragraph distributions, passive voice, hedging, word/phrase/idiom frequencies, per-section metrics), corpus aggregation, term over/underuse comparison, and a plagiarism similarity guard (n-gram shingling with baseline exclusion). Provides voice anchor retrieval from writing-voice exemplars via tf-idf. The section-level driver (compare, blueprint, rewrite) moved to match-outline. Triggers: style profile, quantitative metrics, sentence stats, frequency tables, plagiarism check, similarity check, voice anchors, corpus profile, word frequency.
brainstorm-article
Generate or select a Substack article idea from the brainstorm directory, assess its readiness, and develop it into a publishable outline. Prioritize
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.