사용 방법
- 설치 명령을 복사하고 자신의 에이전트 환경에 설치하기 전에 소스 패키지를 확인하세요.
- 필요한 도구, 인증 정보, 지원 환경은 원본 문서에서 확인하세요.
- 입력과 원하는 산출물을 설명하고 출처와 결과를 대조하세요.
npx skills add https://github.com/mikubaka88/ccfa-skills --skill ccf-paper-writer시작 전 확인
- 설치에는 모델 구독, API 한도, 파일 접근 권한이 포함되지 않습니다.
- 별점 수와 설치 수는 활동 지표이며 독립적인 품질·보안 검증이 아닙니다.
원본 저장소의 제목, 예시, 코드, 표, 링크, 이미지를 유지해 표시합니다.
CCF Paper Writer
Preflight And Ownership
Apply ccf-humanization first, then ccf-common; reuse applicable active rules at handoffs. Both preflights remain required in every mode. Handoff mode is PARTIAL, under the preserved metadata and Common's handoff rules.
Own manuscript prose, compression, and presentation text. Assessment without rewriting belongs to ccf-paper-reviewer; rebuttal belongs to ccf-rebuttal-writer. Preserve the supplied problem, mechanism, setting, measurements, citation keys, and conclusion unless research changes are authorized. Respect the user's format, markup, boundaries, no-browsing and no-new-files instructions. An inspection request alone does not authorize rewriting.
For file edits, reuse the canonical source and one stable working directory under artifact-contracts.md, default ccfa-workfiles/<purpose>/<artifact-id>/. Update in place; preserve inputs, includes, labels, citations, equations, and floats. Check UTF-8/Chinese text and requested exports. Do not create dated or v2 manuscript copies for ordinary iterations.
Writing Standard
Compose from the supplied scientific propositions and the reader's path through them. Develop computations, distinctions, implications, or interpretations according to the passage's purpose. Connect sentences through their actual reason, consequence, evidence, or comparison; internal readiness checks and imagined reviewer objections are not the narrative. Preserve necessary uncertainty, assumptions, negative findings, technical terms, and the author's sentence-final emphasis and broader significance. Do not invent mechanisms, citations, measurements, or empirical superiority.
An ordinary clear local edit needs the active baseline, actual text, and relevant constraints. Read humanization-policy.md or prose-quality-guardrails.md for an actual expression/logic problem or requested humanization; load the relevant sections rather than both full guides by default. Punctuation thresholds belong to Humanization. Supporting phrase checks never replace semantic reading or require removing correct technical language.
Mode Navigation
| Requested work | Relevant guidance |
|---|---|
polish: local passage | Revise directly in the source format; load a reference only for a specific factual, citation, logic, or style question. |
draft: section | Relevant section module; storyline-blueprint.md for substantial introduction/global argument work. |
draft: complete manuscript | materials-to-manuscript.md, storyline and relevant section/checklist guidance. Complete substantive explanations before length fitting; results-pending drafts remain valid. |
submission-fit | The aligned content first, then target venue guide, length-budget-policy.md and compression-rules.md; verify exact official year/track rules through ccf-submission-checker. |
compress | compression-rules.md; preserve scientific relationships, facts and numbers. |
presentation | The source paper and presentation guidance in section-modules.md. |
Naming a venue alone does not trigger a page quota. Read references/venue-guides/index.md and the matched guide when audience/format affects the work; output-style-policy.md preserves supplied templates and governs the disclosed NeurIPS fallback for new LaTeX without one. An abstract, caption, local edit, or exact JSON response does not require whole-paper planning, exemplar analysis, reviewer panels, or a venue guide.
For substantive drafting or expression rewriting, inspect relevant real passages through exemplar-style-analysis.md. reference_style_search defaults to on: reuse matched originals and search for additional good writing for the actual question, reusing completed applicable searches across paragraphs. auto limits extra discovery to gaps; off skips unrequested extra discovery, not supplied references or explicit searches. Choose quality and function without a paper-count quota. Reuse conventional language and technical terms, not distinctive source sentences or scientific claims; keep one author voice.
Draft, Check, Deliver
- Recover the requested artifact, evidence, argument and routine choices from existing context. Ask only for a missing decision that changes the science or deliverable; continue independent work. A long coordinated revision can use writing-execution.md and
scripts/writing_runtime.pyfor current targets, necessary transitions, source positions and checked patches. Short edits stay direct; section IDs do not imply separate agents. - Resolve support before asserting dependent facts. Use citation-workflow.md and
ccf-literature-searcherfor missing sources; useccf-integrity-auditorfor unresolved support/numerical conflicts. Reuse verified evidence and preserve bibliography keys. Reported comparisons use experiment-discipline.md when identity/protocol matters; drafting a supplied design requires no new runs. - Draft the requested prose. materials-to-manuscript.md owns conflicting-material and result-status handling: retain supplied results and honor an entirely deferred experiment section. By default, leave missing values and dependent analysis unwritten. Only an explicit task request or
results_pending_draft=onenables its marked, conditional results-pending completion mode, including the automatic whole-draft alignment pass. Missing details constrain relevant claims without becoming repeated progress disclaimers. Use research-writing-patterns.md only when alternative explanations or structure help; table-style-guide.md covers source tables, with visual redesign owned byccf-visual-composer. - Check the resulting argument and factual preservation once. For a full section/paper run
scripts/check_prose_quality.pywhen available, inspect real issues in context, and retain justified scientific language. Use--strictonly for requested strict lint; rerun changed/unresolved content only. Substantial argument/evidence changes need a scopedccf-paper-revieweralignment check unless covered; carry the phase and missing-result status. Such a check does not start acceptance scoring or experiments. Reuse matching completed coverage; extra independent review follows its existing switch or explicit request. - For full LaTeX with an available engine, compile and inspect errors, references, and affected layouts; fix overflow and broken references. Keep builds in the established task directory, preserve includes/configuration, and export PDF after success. Page count is informational during content drafting. Recompile affected changes without chasing harmless warnings or looping to fill pages.
Return the actual text/artifact first in the user's format. Ordinary local edits need no status report. For full files give paths, substantive changes, actual checks, and concrete remaining author inputs. Draft completion is distinct from evidence completeness or submission readiness. Requested reviewer-driven edits use expert-review-loop.md and score-lifting-loop.md, without writer-owned rescoring or promised score gains.

