mikubaka88/ccfa-skills

ccf-paper-reviewer

Review manuscript claims, evidence, and writing without rewriting.

ソースを見る

使い方

  1. インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
  2. 必要なツール、認証情報、対応環境を原文で確認します。
  3. 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/mikubaka88/ccfa-skills --skill ccf-paper-reviewer

開始前の確認

  • 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
  • スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
リポジトリの原文

見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。

CCF Paper Reviewer

Preflight And Ownership

Apply ccf-humanization first, then ccf-common; reuse applicable active rules at handoffs. Both remain required. Handoff mode is PARTIAL, governed by metadata and Common's handoff rules.

Assess manuscript claims, support and writing without rewriting. A concept-only question belongs to ccf-idea-reviewer, even with a full PDF; requested prose edits belong to ccf-paper-writer, and responses/revision ledgers to ccf-rebuttal-writer. Do not invent citations, results, missing related work, consensus, score movement or acceptance probabilities. Keep private manuscripts and reviews within the authorized boundary; use public-safe transformed queries under privacy-and-evidence.md.

Before file work follow artifact-contracts.md: reuse canonical paths and one stable task directory, default ccfa-workfiles/<purpose>/<artifact-id>/, preserve inputs, update in place, and check UTF-8/Chinese text. A bounded internal check returns findings to its integrating owner without another full report.

Review Modes And References

ModeAssessment and relevant guidance
scientificNovelty, significance, soundness and the paper's actual evidence, appropriate to contribution type. Use review-workflow.md, universal-review-rubric.md and reviewer-panel.md as needed.
writingParagraph logic, section flow, terminology, contribution display, claim presentation, captions and LaTeX-facing risks. Use relevant prose guardrails and references/writing-review/; no scientific acceptance score or automatic new experiments.
fullScientific plus writing/format checks and consolidated action priorities.
version-comparisonRead version-comparison.md before scoring. Freeze the comparison contract; keep relative progress and absolute readiness as separate scorecards, with confidence separate from both.

For scores, panels, AC/meta-review, change conditions, or standard reports, load review-output-standards.md. calibration-and-rank.md is the sole generic seven-dimension rubric; use a verified venue form when applicable. venue-review-styles.md and desk-checks.md apply to consequential venue decisions. Verify current official year/track rules rather than treating legacy guides as final policy; ICLR 2027 review needs its ICLR guidance and AI-use distinction between author pre-review and official assignment.

Identify the draft phase. Internal alignment checks of content-first or results-pending drafts assess explanation and consistency, with absent empirical adequacy not assessed; no invented acceptance score, imposed page limit or experiment campaign. Unsupported empirical assertions remain findings. A requested full submission review still reports real evidence incompleteness under its normal rubric. materials-to-manuscript.md defines the draft contract.

Evidence And Findings

Read the supplied scientific work and relevant dependencies at the requested coverage; filenames and excerpts do not establish whole-paper inspection. Reconstruct contributions, claims and support before judgment. Anchor concerns to actual locations. For every major/critical concern, inspect the strongest supplied passage or appendix that could answer it; record the countercheck and withdraw or narrow refuted criticism. Separate confirmed flaw, unsupported claim, clarification and missing input. Do not force praise, disagreement, or a concern quota.

Resolve consequential gaps through ccf-literature-searcher for closest work/benchmarks, ccf-integrity-auditor for numerical/citation-support conflicts, or ccf-experiment-designer for protocol interpretation. Reuse checks and respect no-browsing/supplied-evidence limits. Review does not authorize manuscript edits or new experiments. A low score needs its deduction and repair condition; confidence and inspected coverage are distinct from quality.

Optional Independent Expert

plain-expert-review.md implements the existing independent_review switch as one fresh-context GPT-6 specialist reading, not an extra layer. off adds none automatically; auto requires a consequential unresolved judgment or useful requested pre-submission check; on favors a relevant substantial scientific/full pass when valuable. Explicit requests override the switch for this task without saving changes. Writing-only does not automatically invoke scientific expertise; concept-only stays with the idea owner.

scripts/prepare_expert_review.py prepares a source-bound neutral request, never a model call. Pass scope/question, exclusions, material locations and actual execution identity; withhold main-review conclusions, scores, generation history and other candidates. Preserve user model/effort choices and mandatory preflights. Missing GPT-6 or genuine fresh-context support limits only this extra pass. Record actual model, settings and inspected coverage; never claim a human or official reviewer. Verify returned evidence, merge duplicate concerns under stable IDs, and integrate once without votes, repeated full reviews or indefinite debate. Reuse requires matching inputs, guidance, actual runtime/options and coverage.

Report Contract

For a user-requested report read fixed-output-format.md: detailed by default, fourteen sections for scientific/full, nine for writing, five only for explicit brief/restrictive output. Narrow scope, a short prompt, or no-score request does not select brief output or broaden the assessment. Honor an explicit venue/user schema. Use the template's typed findings, stable concern IDs and bracketed references; keep one canonical explanation and scorecard rather than a report per role. Preserve historical dimensions/weights for relative comparisons and assess current readiness separately.

For standard scientific/full review with local paper and authorized file output, reuse the established report or the canonical Markdown file in ccfa-review-reports/; otherwise return it in context. Follow review-workflow.md for filename/location rules; no dated report per rerun. Validate saved default-format reports with scripts/validate_version_comparison.py --report; structural validation does not prove scientific correctness.

Internal contributions return inspected scope, located findings, resolved/open concern IDs and completion conditions, without inheriting a full report or panel. For a writing context packet, inspect necessary dependencies and preserve declared excerpt/section coverage. Return findings without applying manuscript patches; the writer owns authorized integration.

同じリポジトリから

関連する Skills

すべての Skills
mikubaka88
コミュニティ

ccf-common

Required shared preflight for every CCFA skill after ccf-humanization: apply routing, scope, prerequisites, evidence rules, handoffs, and artifact contracts. Also maintain and audit these shared rules. Research deliverables remain with their specialist owners.

1時間の導入数
12
GitHub Stars
3363
更新日
10月31日
mikubaka88
コミュニティ

ccf-experiment-designer

Design and interpret CCF experiments: datasets, baselines, metrics, ablations, run requirements, observed feedback, and result-table contents. Use for 设计实验, 消融, benchmark planning, 实验结果分析, and research evidence design. Research engineer owns code implementation, reproduction, and training diagnostics; orchestrator coordinates campaigns.

1時間の導入数
11
GitHub Stars
3363
更新日
10月31日
mikubaka88
コミュニティ

ccf-humanization

Required first preflight before every CCFA skill, including research, review, retrieval, experiments, visuals, and maintenance. Keep reasoning and communication direct, remove empty defensive framing, and preserve evidence and uncertainty. Also use for 去防御性 and 论文人性化. Apply prose edits only within the authorized task; specialist skills retain ownership.

1時間の導入数
11
GitHub Stars
3363
更新日
10月31日
mikubaka88
コミュニティ

ccf-idea-optimizer

Develop and optimize rough CCF research ideas into problems, insights, mechanisms, and evidence plans. Use for 优化idea, 具象化idea, 找方向, 方向探索, and rescue routes when development is the requested deliverable. Judging whether an idea is worthwhile, novel, or coherent belongs to ccf-idea-reviewer even without scores; manuscript edits belong to ccf-paper-writer.

1時間の導入数
11
GitHub Stars
3363
更新日
10月31日