CC gao-cost
Knowledge base from the GAO Cost Estimating and Assessment Guide (GAO-20-195G). Use for program cost estimating: the four characteristics of a reliable estimate (comprehensive, well documented, accurate, credible) and the 18 best practices; the 12-step cost estimating process (purpose, plan, technical baseline, WBS, ground rules and assumptions, data, point estimate, sensitivity, risk/uncertainty, document, present, update); estimating methods (analogy, parametric, engineering build-up, learning curves); Monte Carlo risk/uncertainty analysis, confidence levels and contingency; auditing and validating an estimate against the characteristics; earned value management (EIA-748, BCWS/BCWP/ACWP, CPI/SPI/TCPI, EAC, PMB, IBR); and specialized techniques (software cost estimating, learning curves, Analysis of Alternatives, WBS templates, the Green Book internal-control framework). This is the cost-estimating companion to the GAO Schedule and Technology Readiness Assessment guides. Does not cover schedule estimating/risk in depth (see the GAO Schedule Assessment Guide), agency-specific cost models, or the full text of referenced standards (EIA-748, MIL-STD-881D, the Green Book) — these are named, not reproduced.
Knowledge base from the GAO Cost Estimating and Assessment Guide (GAO-20-195G).
As a process C 64/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches
How to improve
- Shorten the description to 1024 characters.
- 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: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1221 chars, limit 1024
Process rating: all ten parameters 64/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 53 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3765 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1221: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +4Structure: 15 headings
- +3Step-by-step instructions: 53 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.