CtrlK
BlogDocsLog inGet started
Tessl Logo

research-grants

Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements.

56

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/research-grants/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

The content is broad and well-organized into agency overviews, proposal components, review criteria, and a 5-phase workflow, but it is over-long with generic advice Claude already knows and is undermined by a large number of dangling references to bundle files that are not actually present.

Suggestions

Trim generic writing advice and concept definitions Claude already knows (e.g. the 'Writing Principles' and 'Common Mistakes to Avoid' sections, NIH mechanism definitions) to tighten the body and improve conciseness.

Create the missing referenced files or remove the dangling pointers — at minimum provide budget_preparation.md, review_criteria.md, timeline_planning.md, team_building.md, resubmission_strategies.md, the scripts/ directory, timeline_gantt_template.md, and biosketch_templates/ so navigation actually resolves.

Move the inline agency overviews and review-criteria detail into the existing reference files and keep SKILL.md as a lean overview with well-signaled links, so content is appropriately split rather than monolithic.

DimensionReasoningScore

Conciseness

The ~930-line body contains genuine agency-specific detail (e.g. '15-page project description limit', 'Modular budgets ($250K increments)', NIH 'Salary cap applies (~$221,900 for 2024)', NSTC 'CM03 Form'), but is padded with generic writing advice and concept explanations Claude already knows ('Use active voice for clarity', definitions of R01/R21/R03, 'Exceeding Page Limits: Automatic rejection'), so it is mostly useful but could be tightened rather than fully lean.

2 / 3

Actionability

It gives concrete structural guidance (e.g. NIH Specific Aims 'Opening paragraph: Gap in knowledge… 2-4 specific aims… Payoff paragraph') and checklists, but stops short of fully executable specifics, and the one concrete tooling it points to ('scripts/compliance_checker.py: Verify formatting requirements') does not exist, leaving key details missing.

2 / 3

Workflow Clarity

The 'Workflow for Grant Development' lays out a clear 5-phase sequence (Planning, Drafting, Internal Review, Finalization, Submission) with Activities and Outputs, but the validation checkpoints are implicit/generic ('Verify all documents and formatting', 'Revise based on feedback') rather than explicit validate→fix→retry loops, and the referenced verification script is absent.

2 / 3

Progressive Disclosure

There is recognizable structure — a Resources section and clearly signaled one-level-deep 'refer to references/…' pointers — but the body itself is monolithic with content that should live in references, and many referenced paths are broken: 7 of 14 reference files (e.g. budget_preparation.md, review_criteria.md, timeline_planning.md, team_building.md, resubmission_strategies.md, funding_mechanisms.md, research_methods.md), all 3 scripts, 2 of 4 assets, and the biosketch_templates/ directory do not exist.

2 / 3

Total

8

/

12

Passed

Description

82%

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 specific, distinctive description that names the domain and many concrete capabilities with strong natural trigger terms. Its main weakness is the absence of an explicit 'Use when…' trigger clause, which caps completeness at 2.

Suggestions

Add an explicit 'Use when…' clause, e.g. 'Use when writing or revising research grant proposals for NSF, NIH, DOE, DARPA, or Taiwan NSTC, or when the user mentions grant applications, solicitations, specific aims, or broader impacts.'

Include common layperson phrasings such as 'grant writing', 'grant proposal', 'funding application', and 'solicitation / RFP' as additional trigger terms.

DimensionReasoningScore

Specificity

Names multiple concrete capabilities — 'Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance' — alongside the core action 'Write competitive research proposals', matching the multi-action score-3 anchor rather than the single-action score-2 anchor.

3 / 3

Completeness

It clearly answers 'what' but provides no 'Use when…' clause or equivalent explicit trigger guidance, so per the rubric guideline completeness is capped at 2 even though the what-side is comprehensive.

2 / 3

Trigger Term Quality

Natural trigger terms a user would actually say are well covered: the agency acronyms 'NSF, NIH, DOE, DARPA, and Taiwan NSTC' plus 'research proposals', 'broader impacts', 'significance statements', and 'budget preparation' — strong natural coverage rather than jargon.

3 / 3

Distinctiveness Conflict Risk

The niche is tightly scoped to research proposals for five named federal agencies with agency-specific deliverables, making it clearly distinguishable and unlikely to trigger for the wrong skill.

3 / 3

Total

11

/

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 (933 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

referenced_paths_exist

Referenced path issues: 18 missing

Warning

Total

13

/

16

Passed

Repository
foryourhealth111-pixel/Vibe-Skills
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.