AC aegis
AI Development Quality Guardian — contract-driven, design-first quality guardrails for AI-assisted full-stack development. Five-layer defense: Design → Contract → Implementation → Verification → PM. Prevents project chaos at scale. Activate when: starting a feature, setting up a project, dispatching coding tasks, reviewing PRs, or managing multi-agent workflows. Also triggers on projects with a contracts/ directory (implementation guardrails auto-activate).
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 22. 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 54/100
- 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
- 40Consistency. Frontmatter name (aegis) differs from the folder (aegis-quality-guardian)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 4 branches
- 100Steps. 71 steps
- 100Execution cost. Instruction body is 2622 tokens
- 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 10 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)
- +3Output format is not stated: the model decides each time
- -31 of 7 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 461: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 71 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (3 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.