공개 Claude Code 마켓플레이스의 플러그인 14개입니다. 각 플러그인은 함께 설치되는 스킬, 슬래시 명령, 에이전트, 훅 또는 MCP 서버를 묶습니다.
필터와 일치하는 14개의 플러그인을 표시합니다.
humanize-promsdanyg/humanize-pro1
saramchaekeenkim1202/saramchae1.claude-plugin/marketplace.json이 포함된 repo를 제출하면 모든 plugin을 목록에 추가합니다.
marketplace 제출Scientific paper writing, source-traced review, and de-AI rewriting for top-tier journals (ApJ/MNRAS/PRD/JCAP-class) and NSF/NIH proposals. Ships 12 skills and 40 tools under one typed standard: scientific-integrity blockers that cannot be waived as style preferences, a zero-target L0 lexicon, ranked advisories, explicit measurement states so missing calibration never reads as clean, claim-first rewriting gated on hard scientific-fidelity eligibility, a mechanical length budget with a machine-built removal map and a required-shrink gate, corpus-calibrated salience-hierarchy, domain-register (with an exhaustive zero-hit vocabulary audit), collocation, and discourse-texture (given/new cohesion, epistemic hedging) axes, each judged against the field's own per-section distribution at the unit it was calibrated at, a residue axis that gates the trace an edit leaves, A-R review with narrative-spine and adversarial-escalation dimensions, registry-verified bibliographies (CrossRef, DataCite, a
writingSix skills for scientific writing: edit research prose, structure an IMRaD manuscript, run the writing process, handle peer review and publication ethics, draft grants and letters, and write for general audiences.
writingSixteen portable editorial-system skills for agents.
writingKills AI smell in Italian text. Hard bans, deterministic scanner, 3 modes (rewrite / audit / targeted fix), voice calibration, quad-pass audit, anglo-calque suppression, return of living Italian. | Elimina l'odore di IA dal testo italiano: ban assoluti, scanner deterministico, 3 modalità, calibrazione della voce, audit quad-pass, soppressione dei calchi dall'inglese.
writingMake AI-drafted text read like a person wrote it, for the channel it ships in. De-AI pass, channel fit, voice profiles, and a two-gate audit before delivery.
writingStrips the AI tells and the translationese out of a document, and fixes its shape. saramchae-ko covers Korean, saramchae covers everything else. Each ships a scanner that measures before a word is rewritten.
writingTurkish humanizer: writes and repairs Turkish that reads as human-written — native sentence architecture, register-aware intervention, and technical terms left intact
writingWrite technical and agent-facing text in ASD-STE100 Simplified Technical English. Benchmarked: 95.5% fewer STE violations than baseline across 12 models.
writingMarketing copy where every claim is traced to a fetched source, labeled, and adversarially verified before it ships
writingDetect and repair AI slop in prose, code, documentation, commits and agent output. Reports defects, never authorship. Runs deterministic scanners for vendor residue, placeholders, citations and packages, then structural procedures (deletion, inversion, stranger, attribution, load-bearing) that each emit a verifiable artifact. Stylistic markers are evidence-tiered and route to structural tests instead of failing on their own.
writingRewrites pt-BR technical text with 9 controlled-language rules, frozen terminology and AI-filler removal. Regression suite included.
writing把 AI 寫的繁體中文改寫成自然、有人味的台灣風格文字，附可驗證的事實保留檢查。
writingУбивает запах нейросети в русском тексте: 64 паттерна в 14 категориях, 21 жёсткий бан, 3 режима, калибровка голоса, quad-pass аудит. Пригодится, чтобы очеловечить ответы клиентам, посты и письма из контентных скиллов пака. | Kills AI smell in Russian text.
writingBiên tập văn tiếng Việt bỏ dấu văn AI: danh mục dấu hiệu có nguồn trích dẫn, máy quét deterministic, kiểm bảo toàn số liệu
writing
