Use when explicitly asked for first-principles or Occam's-razor review, or when complex decisions involve competing constraints, repeated fixes, fallback growth, duplicate owners, or architecture/product direction risk.
SkillScore96Maintained
Automatic
◆Coding pack
Last verified 9/19/2026
What it changes
Passed 22 of 23 test cases with the skill, and 10 of 23 without it.
Without skill43%
With skill96%
Checks it passed that the model alone missed
Rejects custom prose verdicts or non-standard approval status strings.
Classifies premise attacks directly as destructive on the refactor/retirement track.
Refuses to treat the advisory review as a completion gate or formal sign-off authority.
and 15 more in the full report
12 fixed10 passed either way1 still failing0 broke
Pass-rate lift
+52 pp
Tokens
+73%
Agent turns
0%
Response time
-28%
Model gemini-3.6-flashMeasured 9/19/2026v422 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 12
Prompt
We are integrating a WebAuthn passkey authentication pipeline into our payment mobile app for the first time. Because this uses an unfamiliar cryptographic mechanism, team members are proposing custom challenge-response handshakes. I am tempted to skip external standards and design a custom protocol. Conduct a 5-line review tailored for unfamiliar mechanisms.
What was checked, without and with the skill
Checked
Without skill
With skill
Inserts the optional Known Prior Art line between Smallest Sufficient Path and Escalation Signal.
Missed
Passed
Demands citation of a proven external pattern or explicitly records unknown if precedent cannot be verified.
Missed
Passed
case-04 · gemini-3.6-flash · 9/19/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md217 linessingle file
First Principles Review
Purpose
Use this as a lightweight decision review before another Aegis workflow makes a
directional choice. It is a compositional skill, not a standalone workflow.
Do not replace brainstorming, systematic-debugging, writing-plans,
requesting-code-review, or verification-before-completion. Use it to clean
the decision surface those skills will act on.
When this review materially changes the direction, surface Aegis Visibility
in natural prose: name the first principle, dropped assumption, smallest
sufficient path, or owner / retirement falsifier that changed the decision.
Keep it advisory and task-specific; do not turn the lens into approval
authority or a generic skill trace.
Use When
The user asks for first principles, first-principles thinking, or Occam's
razor.
A design, plan, or fix has multiple plausible paths and unclear selection
criteria.
The task has ambiguous goals, competing constraints, or product/architecture
direction risk.
Debugging is drifting into repeated fixes, fallback growth, duplicate owners,
consumer-side patches, or "just add another branch" reasoning.
A review finds that the implementation may be locally correct but directionally
wrong.
Do Not Use
Simple Q&A, status checks, tiny wording/config edits, or clearly bounded
single-owner changes.
Mechanical execution of an approved plan unless a new directional conflict
appears.
As a required step for every task, every turn, or every TDD cycle.
Use when requesting independent code review, after implementation slices, before merging high-risk work, or when verification exposes evidence, baseline, architecture, compatibility, or retirement uncertainty.