Lists a concrete action ('Draft a structured grant proposal from research ideas and literature') and enumerates multiple specific funding agencies with sub-types (e.g., NSFC sub-categories like 面上/青年/优青/杰青/海外优青/重点). This is highly specific about what the skill does.

Clearly answers 'what' (draft structured grant proposals from research ideas, supporting multiple funding agencies) and 'when' (explicit 'Use when...' clause with specific trigger phrases and a general condition about turning research ideas into funding applications).

Excellent coverage of natural trigger terms across multiple languages: 'write grant', 'grant proposal', '申請書', '科研費', '基金申请', '写基金', 'NSF proposal', 'funding application', plus agency names like KAKENHI, NSF, NSFC, ERC, DFG, etc. These are terms users would naturally say.

Highly distinctive niche: grant proposal writing for specific funding agencies. The combination of agency names (KAKENHI, NSF, NSFC, ERC, DFG, SNSF, ARC, NWO) and multilingual trigger terms makes it very unlikely to conflict with other skills.

Extremely verbose at ~500+ lines. Explains concepts Claude already knows (e.g., 'Grant proposals argue for future work (feasibility + potential), not completed work (results + claims)'), includes extensive tables of grant agency details that could be in separate reference files, and repeats information across sections (e.g., grant-specific cultural norms appear in both the specifications table and the drafting guidelines).

Provides concrete workflow steps, checkpoint formats, and file output structures, but much of the 'actionable' content is actually orchestration of other sub-skills (e.g., '/research-lit', '/research-review') rather than executable code. The Codex MCP calls are specific but the actual grant-writing instructions are more descriptive than prescriptive — telling Claude to 'write complete prose' without showing examples of good grant prose.

Excellent multi-phase workflow (Phase 0-5) with explicit checkpoints marked by ⛔ STOP symbols, user confirmation gates, state persistence via JSON, resume logic, and a clear revision feedback loop with severity levels (CRITICAL/MAJOR/MINOR). The final checklist provides thorough validation.

Monolithic wall of text with no references to external files. The grant type specifications (KAKENHI, NSF, NSFC, ERC, DFG, SNSF, ARC, NWO) should each be in separate reference files. The entire document is ~500+ lines when the SKILL.md should be an overview pointing to detailed materials for each grant type, drafting guidelines, and review templates.