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.

65

Quality

80%

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 ./.claude/skills/research-grants/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

A comprehensive, well-structured grant-writing skill with concrete agency guidance, real templates, and a clear phased workflow, but it is verbose and keeps too much detail inline rather than pushing it to the existing reference files.

Suggestions

Trim generic writing advice ('Writing Principles', 'Common Mistakes to Avoid') that Claude already knows, or move it to a reference file, to improve conciseness.

Move the per-agency 'Review Criteria' and 'Common Proposal Types' detail into the corresponding reference files, keeping SKILL.md a lean overview that points to them.

Reduce the Overview section's restatement of what grant writing is; lead directly with agency-specific triggers and structure.

DimensionReasoningScore

Conciseness

The ~900-line body contains genuine agency-specific detail but is padded with generic writing advice ('Use active voice', 'Choose strong verbs') and an overview restating what grant writing is; mostly efficient but could be tightened.

2 / 3

Actionability

As an instruction skill it gives concrete, actionable structure — named forms (CM03), page limits, Specific Aims structure, budget categories — plus real templates, satisfying the instruction-skill actionability bar.

3 / 3

Workflow Clarity

The 'Workflow for Grant Development' section sequences five phases with activities, outputs, and timeframes, and includes an internal-review/mock-review feedback phase; grant writing is not a destructive operation so no validation cap applies.

3 / 3

Progressive Disclosure

References are well-signaled and one-level-deep (all referenced files exist), but the body is a long monolithic overview with substantial inline detail (review criteria, common mistakes, writing principles, proposal types) that overlaps the reference files and could be split out.

2 / 3

Total

10

/

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, well-targeted description that names concrete actions and agencies, but it omits an explicit 'Use when...' trigger clause, capping completeness.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when writing or revising research proposals for NSF, NIH, DOE, DARPA, or Taiwan NSTC submissions').

Consider including common user phrasings like 'specific aims page', 'broader impacts statement', or 'budget justification' as explicit trigger terms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements' — matching the multi-action anchor.

3 / 3

Completeness

Clearly answers 'what' but lacks any explicit 'Use when...' trigger clause, so per the rubric guideline completeness is capped at 2.

2 / 3

Trigger Term Quality

Natural terms a user would say ('research proposals', NSF, NIH, DOE, DARPA, NSTC) are well covered; naming the specific agencies gives strong trigger coverage.

3 / 3

Distinctiveness Conflict Risk

Naming five specific funding agencies creates a clear niche with distinct triggers, unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

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

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
K-Dense-AI/claude-scientific-writer
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.