AC grants-program-marketing
Complete system for designing, marketing, and operating a Web3 grants program. Use this skill whenever the user asks about launching or improving a grants program, attracting quality applicants to a DAO or protocol grants round, reviewing grant applications, communicating grant results, or building the marketing strategy for a grants ecosystem. Also trigger for phrases like "our grants program", "attract builders to apply", "grant application review", "communicate grants", "grants V2/V3", "grantee spotlight", "grants page copy", "how to market a hackathon", or any variation of funding program management in Web3, DeFi, DAO, or protocol contexts.
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 48 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2675 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 652: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 48 items
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.