BC gao-agile
Knowledge base from the GAO Agile Assessment Guide (GAO-24-105506, 2023). Use for assessing and managing Agile software development in federal programs: the Agile Manifesto and framework family (Scrum, Kanban, XP, SAFe, DA, DSDM, Lean, DevOps); the three adoption perspectives (team dynamics, program operations, organization environment); requirements decomposition (epics, features, user stories, INVEST, MoSCoW, definition of done); Agile-aware federal contracting (FAR, modular contracting, SOO/PWS/SOW, product owner vs. COR); program monitoring and control (WBS, cost, schedule, EVM at the feature level); Agile metrics (velocity, lead/cycle time, CFD, burn charts); and the auditor's key-question bank. Oversight- and acquisition-oriented: it tells you how to *assess and govern* Agile programs, not how to code. Thin on hands-on engineering practice, deep cost/schedule checklists (see gao-cost, gao-schedule), and any non-US-federal context.
Knowledge base from the GAO Agile Assessment Guide (GAO-24-105506, 2023).
As a process C 62/100 · Has gaps — weak spots: result and completion, when it triggers, 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Risky intent
intent-offensive-securitychapters/ch02-gao-agile-adoption-challenges-federal-response.md:14Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Case study 1: Space Command and Control (Space C2), from GAO-20-146** (Oct. 30, 2019) — a worked example of one of the first DOD software-intensive programs to move from Waterfall into an Agile fr
-
low Risky intent
intent-offensive-securitychapters/ch02-gao-agile-adoption-challenges-federal-response.md:77Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **GAO-20-146** (*Space Command and Control*) — the case study illustrating guidance lag during early DOD Agile adoption.
Files scanned: 15. 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 62/100
- 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. 6 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 58 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3935 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 950: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +4Structure: 18 headings
- +3Step-by-step instructions: 58 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.