CtrlK
BlogDocsLog inGet started
Tessl Logo

grant-proposal

Draft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including 面上/青年/优青/杰青/海外优青/重点), ERC (EU), DFG (Germany), SNSF (Switzerland), ARC (Australia), NWO (Netherlands), and generic formats. Use when user says "write grant", "grant proposal", "申請書", "write KAKENHI", "科研費", "基金申请", "写基金", "NSF proposal", or wants to turn research ideas into a funding application.

68

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

70%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable grant-writing skill with strong workflow checkpoints and concrete tooling, but it is verbose with redundant pipeline restatements and inlines reference-grade material rather than splitting it into bundle files.

Suggestions

Consolidate the three pipeline diagrams (overview, ASCII branch, funding-track block) into a single diagram to reduce repetition and tokens.

Move the per-agency specification tables and drafting guidelines into a references/ file (e.g. GRANT_TYPES.md) and summarize them in the body with a clearly signaled link.

Dedupe the 'grant argues for future work vs paper' guidance so it appears once (either Overview or Key Rules) instead of multiple times.

DimensionReasoningScore

Conciseness

Mostly efficient domain-specific content, but the pipeline is diagrammed three times (overview, ASCII branch, funding-track block), the 'grant ≠ paper' point is restated across Overview and Key Rules, and the Composing section re-explains workflows already shown — tightening would remove redundancy.

3 / 5

Actionability

Highly executable with exact MCP tool names (mcp__gemini-review__review_start/review_reply_start/review_status), a JSON state schema, gap-statement and claims-aims-evidence matrix templates, drafting order, and a final checklist; minor gaps remain in prompt templates with [INSERT ...] placeholders.

4 / 5

Workflow Clarity

Phases 0–5 are clearly sequenced with explicit 🚦/⛔ STOP-and-wait checkpoints, compact-recovery resume logic, a severity-tier revision loop (CRITICAL/MAJOR/MINOR), and a final verification checklist — meeting the explicit-validation anchor.

5 / 5

Progressive Disclosure

No bundle files exist (references/scripts/assets all empty) yet the skill is a ~626-line monolith; agency specification tables and per-agency drafting guidelines are inlined where a reference file would improve navigation, and the only signaled references point to external shared-references outside the bundle.

3 / 5

Total

15

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description with comprehensive agency coverage, multilingual natural triggers, and an explicit 'Use when...' clause covering both what and when. Voice is correctly third person.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (draft a structured grant proposal from research ideas and literature) plus comprehensive agency and sub-type coverage (KAKENHI/NSF/NSFC/ERC/DFG/SNSF/ARC/NWO/GENERIC with sub-types like 面上/青年/优青/杰青/海外优青/重点), matching the comprehensive-anchor example.

5 / 5

Completeness

Explicitly answers 'what' (draft a structured grant proposal from research ideas and literature) and 'when' via the 'Use when user says ...' clause with concrete trigger phrases, hitting the top anchor.

5 / 5

Trigger Term Quality

Comprehensive multilingual natural triggers including 'write grant', 'grant proposal', '申請書', 'write KAKENHI', '科研費', '基金申请', '写基金', 'NSF proposal' and the phrasing 'wants to turn research ideas into a funding application', covering synonyms users would actually say.

5 / 5

Distinctiveness Conflict Risk

Clear niche (funding applications) with distinct agency-specific and multilingual triggers, making it unlikely to fire for unrelated skills.

5 / 5

Total

20

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (631 lines); consider splitting into references/ and linking

Warning

relative_links

Relative link issues: 3 suspicious

Warning

Total

14

/

16

Passed

Repository
wanshuiyin/Auto-claude-code-research-in-sleep
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.