How do I install the Kim Ccf Research Shared skill?

Run npx skillmds@latest add conmuyan/kim-ccf-research-shared in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Kim Ccf Research Shared safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Kim Ccf Research Shared?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Kim Ccf Research Shared free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Kim Ccf Research Shared?

ConmuYan (@conmuyan) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Kim Ccf Research Shared by conmuyan

Name: Kim Ccf Research Shared
Author: ConmuYan

Kim Ccf Research Shared

Shared infrastructure for the kim-ccf-research series. This is NOT a skill — it is a namespace providing cross-skill references (routing, task modes, handoff protocols, privacy controls, venue maps, artifact contracts). Every kim-ccf-research-* leaf loads files from ../kim-ccf-research-shared/references/. Never invoke this directly.

ConmuYan Updated Sep 17, 2026

File contents

kim-ccf-research-shared

Not a skill. This directory exists to provide cross-cutting reference material that every kim-ccf-research-* leaf skill may load on demand. The top-level SKILL.md exists only so Claude Code discovers the namespace; the description explicitly says "never invoke this directly" so the orchestrator does not treat it as an action.

What's inside

references/routing.md — intent → leaf-skill matrix; resolves routing ambiguity between kim-ccf-research-idea, kim-ccf-research-idea-review, and kim-ccf-research-experiment.
references/task-modes.md — three modes: exploratory, quick, standard. Each leaf picks one before producing output.
references/handoff-modes.md — partial (confirm before invoking another leaf) vs full (silent passthrough). Default partial.
references/review-output-standards.md — quantitative scoring rules for any leaf that emits scores (idea-review, review, rebuttal).
references/privacy-and-evidence.md — treat rough ideas, draft text, unpublished results as private user data; defines public-safe query transformation for WebSearch / WebFetch.
references/source-registry.yaml — public source provenance IDs (arXiv, OpenReview, NeurIPS, ICML, AAAI, KDD, WWW, ICLR, CVPR, OpenAlex, Semantic Scholar, DBLP). Cite by ID, not by raw URL.
references/ccf-a-venue-map.md — venue-family routing for TPAMI/TKDE /AAAI/KDD/ICML/WWW/ICLR/CVPR; each family has distinct page limits, double-blind rules, and artifact badges.
references/artifact-contracts.md — canonical output paths and filenames per leaf.
references/prose-guardrails.md — (STUB v1.0.0) prose-quality rules for the writing chain; placeholder for v1.1.0.
references/storyline-blueprint.md — (STUB v1.0.0) paper-section ordering and length budgets; placeholder for v1.1.0.
references/venue-guides/index.md — per-venue submission quick reference (page limits, anonymization, supplementary rules).

Versioning

metadata.version bumps whenever the routing rules, handoff protocol, or shared contracts change. Bumps force a coordinated frontmatter bump on every leaf that loads from this directory.

---name: kim-ccf-research-shareddescription: Shared infrastructure for the kim-ccf-research series. This is NOT a skill — it is a namespace providing cross-skill references (routing, task modes, handoff protocols, privacy controls, venue maps, artifact contracts). Every kim-ccf-research-* leaf loads files from ../kim-ccf-research-shared/references/. Never invoke this directly.---# kim-ccf-research-shared> **Not a skill.** This directory exists to provide cross-cutting> reference material that every `kim-ccf-research-*` leaf skill may load> on demand. The top-level `SKILL.md` exists only so Claude Code> discovers the namespace; the description explicitly says "never invoke> this directly" so the orchestrator does not treat it as an action.## What's inside- `references/routing.md` — intent → leaf-skill matrix; resolves routing ambiguity between `kim-ccf-research-idea`, `kim-ccf-research-idea-review`, and `kim-ccf-research-experiment`.- `references/task-modes.md` — three modes: `exploratory`, `quick`, `standard`. Each leaf picks one before producing output.- `references/handoff-modes.md` — `partial` (confirm before invoking another leaf) vs `full` (silent passthrough). Default `partial`.- `references/review-output-standards.md` — quantitative scoring rules for any leaf that emits scores (`idea-review`, `review`, `rebuttal`).- `references/privacy-and-evidence.md` — treat rough ideas, draft text, unpublished results as private user data; defines public-safe query transformation for `WebSearch` / `WebFetch`.- `references/source-registry.yaml` — public source provenance IDs (arXiv, OpenReview, NeurIPS, ICML, AAAI, KDD, WWW, ICLR, CVPR, OpenAlex, Semantic Scholar, DBLP). Cite by ID, not by raw URL.- `references/ccf-a-venue-map.md` — venue-family routing for TPAMI/TKDE /AAAI/KDD/ICML/WWW/ICLR/CVPR; each family has distinct page limits, double-blind rules, and artifact badges.- `references/artifact-contracts.md` — canonical output paths and filenames per leaf.- `references/prose-guardrails.md` — (STUB v1.0.0) prose-quality rules for the writing chain; placeholder for v1.1.0.- `references/storyline-blueprint.md` — (STUB v1.0.0) paper-section ordering and length budgets; placeholder for v1.1.0.- `references/venue-guides/index.md` — per-venue submission quick reference (page limits, anonymization, supplementary rules).## Versioning`metadata.version` bumps whenever the routing rules, handoff protocol,or shared contracts change. Bumps force a coordinated frontmatter bumpon every leaf that loads from this directory.

Frequently asked questions