Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →sediman-agent/how
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Can critique architecture. Use why for motivation.
Passed 3 of 9 test cases with the skill, and 2 of 9 without it.
and 3 more in the full report
6 fixed1 passed either way11 still failing4 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
When running architectural critique on our file upload pipeline, what model is assigned to the Critic B subagent?
| Checked | Without skill | With skill |
|---|---|---|
| Assigns model gpt-5.3-codex-high-fast to Critic B. | Missed | Passed |
The instructions your model reads when the skill loads.
Explore the codebase to answer "how does X work?" questions. Produce clear architectural explanations at the level of a senior engineer onboarding onto a subsystem. Enough to build a working mental model, not annotated source code.
Two modes:
Parse what the user is asking about:
Identify the scope. If ambiguous, state your best-guess interpretation before exploring. Don't ask. Let the user redirect if you're off.
Assess complexity to decide the approach:
When in doubt, lean simple. You can always spawn explorers if the explainer hits a wall.
Decompose the question into 2-4 parallel exploration angles, each a distinct slice of the subsystem so explorers don't duplicate work. Example split for "how does the rate limiter work?":
The right decomposition depends on the question. Use your judgment. Narrow questions: 2 explorers is fine. Broad subsystems: up to 4.
Spawn all explorers in a single message:
test cases passed, vs 2 / 9 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.