kim-ccf-research-humanizelisted

Humanize and de-defend publication-facing CCF/AI prose and artifacts as a sidecar preflight, never as the primary task owner. Use before manuscript drafting/revision and before final manuscript experiment text, tables, captions, or method descriptions when Codex must remove defensive writing, boilerplate disclaimers, repetitive improbable edge cases, unnecessary safeguards, generic SHA-256/checksum requirements, duplicated smoke tests, simplified/toy methods, or AI-like risk narration. Do not auto-load as the sole owner for raw experiment planning, retrieval, review, auditing, routing, visual rendering, or assessment-only tasks without publication prose. Keep necessary concerns in a separate user-review warning instead of silently injecting them into files. Do not conceal material evidence, fabricate results, or override venue-mandated disclosures.
ConmuYan/kim-ccf-research · ★ 0 · AI & Automation · score 73

Install: claude install-skill ConmuYan/kim-ccf-research

# CCF Humanization ## Invocation Controls **CCFA Handoff Mode: PARTIAL (Recommended).** Follow `metadata.ccf_skill_controls.handoff_question_mode`, `../kim-ccf-research-shared/references/handoff-modes.md`, and `../kim-ccf-research-shared/references/task-modes.md`. Apply this skill before manuscript-facing work by `ccf-paper-writer` and before publication-facing experiment work by `ccf-experiment-designer`. It is the highest-priority preflight as a sidecar quality layer, not a substitute for either owner. Respect the user's requested format and do not broaden the research scope. ## Core Rule Produce direct academic content, not prose that argues with hypothetical reviewers. Remove defensive framing, generic disclaimers, repeated low-probability cases, ritual safeguards, and process narration that do not change the scientific claim or evidence. Keep a concern outside the artifact as a user-review warning when it needs judgment. Do not edit a source file merely to encode a warning. Humanization must never dilute academic rigor. Preserve technical precision, evidence boundaries, causal and comparative logic, reproducibility-relevant details, calibrated claims, terminology, equations, citations, and venue-required disclosures. Improve the prose by making the scientific argument clearer and more natural, not by making it vaguer, more promotional, or less complete. Keep method confirmation and version-gate status internal. A method must pass the confirmed-full-method gate bef