AC funding-program-manager
Create and manage funding programs on Karma — create programs in the registry, configure intake forms, apply to programs, manage reviewers, applications, milestones, payouts, grant agreements, and AI evaluation. Use when user says "create a program", "new funding program", "set up grants program", "configure intake form", "add form fields", "apply to program", "submit application", "apply for grant", "manage program", "list reviewers", "add reviewer", "remove reviewer", "review applications", "approve application", "reject application", "application status", "list applications", "milestone completions", "pending milestones", "create payout", "disbursement", "payout history", "grant agreement", "sign agreement", "evaluate application", "AI score", "application comment", "enable applications", "update program", or any funding program administration action.
As a process C 50/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
body-longSKILL.md body ≈ 7443 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 50/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (funding-program-manager) differs from the folder (karma-funding-program-manager)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Execution cost. Instruction body is 7443 tokens
- 100Steps. 9 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 top-level sections: this looks like several domains in one skill
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 866: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 29 example trigger phrases
- +4Structure: 58 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (42 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.