AB nonprofit_rbm_logic_model
Build donor-ready nonprofit RBM logic models, theory of change, logframes, concept notes, LOIs, full proposal sections, MEAL indicators, evidence-gap trackers, donor-fit reviews, risk and safeguarding matrices, budget logic summaries, and defensible Go / Conditional Go / No-Go submission decisions. Use for grant writing, nonprofit proposal design, results-based management, monitoring and evaluation, impact pathways, outcomes, outputs, assumptions, indicators, baselines, targets, verification plans, and submission readiness.
As a process B 74/100 · Nearly there — weak spots: inputs and preconditions, consistency, running it twice
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
name-formatname should be kebab-case (lowercase letters, digits, hyphens)
Process rating: all ten parameters 74/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (nonprofit_rbm_logic_model) differs from the folder (nonprofit-rbm-logic-model)
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 228 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 19 branches, has a failure section
- 100Execution cost. Instruction body is 3862 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 24 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 529: enough signal without eating the budget
- +4Structure: 42 headings
- +3Step-by-step instructions: 228 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.