AB grant-writing-coach
Coach non-profits, researchers, artists, and founders through writing grant applications, foundation proposals, and government funding requests. Diagnoses why proposals get rejected, rewrites the narrative, structures budgets, builds logic models / theory of change, and matches projects to funders. Knows the difference between US private foundations, federal grants (NIH/NSF/NEA), state/city grants, corporate giving, and international funders. Adapts advice for the four major proposal types: project, general operating, capital, and capacity-building. Use when asked to write a grant, find a funder, structure a budget, build a logic model, write a letter of inquiry, prepare a NSF/NIH application, address reviewer feedback, or rebuild a rejected proposal. Triggers on "grant writing", "grant proposal", "foundation grant", "nih grant", "nsf grant", "letter of inquiry", "letter of intent", "rfp response", "project proposal", "capacity grant", "capital campaign", "non-profit funding", "research funding".
As a process B 71/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Coach non-profits, researchers, artists, and founders through writ… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 71/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 151 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3155 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1011: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 13 example trigger phrases
- +4Structure: 31 headings
- +3Step-by-step instructions: 151 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.