CtrlK
BlogDocsLog inGet started
Tessl Logo

inno-grant-proposal

Help professors and researchers write, revise, adapt, and polish grant proposals for US agencies (NSF, NIH, DOE, DARPA, NASA) and Chinese agencies (NSFC 国自然). Use this skill whenever the user mentions grants, proposals, funding applications, 基金申请, 本子, R01, R21, CAREER, 面上, 青年基金, specific aims, 立项依据, broader impacts, or wants to plan, draft, review, or resubmit any research funding proposal — even if they don't explicitly say "grant". Also use this skill when the user wants to adapt a previous proposal for a new submission. Six-phase workflow: profiling → planning → drafting → quality review → simulated peer review → submission prep.

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

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

70%

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

A thorough, well-sequenced workflow skill with strong phase-based structure, validation checkpoints, and state persistence. Its main weaknesses are verbosity (content that could live in reference files or that Claude already knows) and progressive-disclosure gaps: several referenced paths (templates/, config.yaml, CREDITS.md) are missing from the bundle.

Suggestions

Move agency-specific section lists, review-criteria tables, and program catalogs into the existing reference guides and keep SKILL.md as a lean overview that loads them per phase, reducing the body's length and token cost.

Create the missing referenced files (templates/us, templates/cn, config.yaml, CREDITS.md) or remove the dangling references so progressive disclosure is one-level-deep and every cited path resolves.

Tighten abstract drafting guidance (e.g., the five-sentence model) into an executable template or checklist with character-count validation rather than prose description, to raise actionability.

DimensionReasoningScore

Conciseness

The body is a ~910-line monolith that includes some content Claude already knows (e.g., explaining review criteria, re-deriving agency section lists) and verbose table-driven exposition; while much is genuine domain instruction, it is padded and could be tightened or offloaded to reference files, matching 'mostly efficient but includes some unnecessary explanation'.

2 / 3

Actionability

It gives concrete structural templates, JSON schemas, table formats, and explicit script invocations (validate_length.py etc.), but much guidance remains descriptive ('write flowing, expert-level prose', 'synthesize and critique') rather than executable, and key referenced scaffolds live in templates the skill describes but does not inline.

2 / 3

Workflow Clarity

A clear six-phase sequence with entry/exit criteria per phase, numbered steps (0.1–5.5), state-persistence checkpoints, backup-before-write validation, severity-gated progression ('at minimum all P0 items'), and error-handling fallbacks — this matches the 'clear sequence with explicit validation steps; checklists' anchor.

3 / 3

Progressive Disclosure

It references a well-organized bundle (references/us, references/cn, references/common, references/rubrics, scripts/) with lazy-loading guidance, but also repeatedly cites paths that do not exist (templates/us, templates/cn, config.yaml, CREDITS.md) and inlines large amounts of content that belongs in references, so structure is present but partly broken and not cleanly one-level-deep.

2 / 3

Total

9

/

12

Passed

Description

100%

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

An excellent description: it names concrete capabilities, provides rich bilingual trigger terms, explicitly states both what the skill does and when to use it, and occupies a distinctive niche unlikely to conflict with other skills. Voice is appropriately third-person and free of fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'write, revise, adapt, and polish grant proposals' — and enumerates specific agency programs (NSF, NIH, DOE, DARPA, NASA, NSFC) plus a six-phase workflow, matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Clearly answers both 'what' (write/revise/adapt/polish grant proposals for US and Chinese agencies, six-phase workflow) and 'when' via an explicit 'Use this skill whenever...' clause with multiple triggers, satisfying the top anchor for both what AND when.

3 / 3

Trigger Term Quality

Strong coverage of natural user terms including 'grants, proposals, funding applications, 基金申请, 本子, R01, R21, CAREER, 面上, 青年基金, specific aims, 立项依据, broader impacts' — these are exactly the phrases a researcher would say when they need this skill, spanning both English and Chinese.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche — bilingual (US/Chinese) grant-proposal authoring with named agency programs and domain-specific triggers (R01, CAREER, 面上, 本子) — making it unlikely to trigger for the wrong skill.

3 / 3

Total

12

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (937 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 21 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository
OpenLAIR/dr-claw
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.