name	solution-complexity-audit
description	Audit std/brute assumptions with MCP evidence, including worst/average complexity risk and stress readiness.
disable-model-invocation	false

Solution Complexity Audit

Used in the post-implementation audit stage after std/brute are available. You must provide structured evidence; verbal claims are not sufficient.

Execution Order

Call tools in this order and record the results:

solution_analyze: estimate std time/space complexity and record worst/average risks.
solution_audit_std: verify whether claimed_complexity conflicts with estimated complexity and constraints.
solution_audit_brute: confirm brute is suitable as a stress oracle and derive n_max and trials.

Required Checks

Whether std has high_tle_risk or obvious boundary flaws.
Whether brute truly serves as a conservative correctness oracle rather than the same class of implementation as std.
Whether complexity conclusions match statement constraints (especially n_max and total scale).
Whether executable stress_profiles recommendations are produced.

Output Format

decision: go / no_go
findings: structured issue list (including severity)
recommended_stress_params: recommended stress parameters

Failure Handling

If high-risk items exist, fix the algorithm or constraints first, then rerun the full audit chain.
Do not skip this audit and proceed directly to final test generation.

Decision Rules

go: no unresolved critical findings, high_tle_risk is false or low, and stress parameters are explicit and executable.
no_go: any unresolved critical finding, or brute is not a trustworthy stress oracle.

Más de este repositorio

mismo repositorio

agent-skill-governance

SummerOneTwo/AutoCode

Define and enforce project-wide quality standards for agent and skill documents. Use when creating, reviewing, or refactoring files under agents/ and skills/ to keep structure, terminology, and output contracts consistent.

2026-04-300

problem-validate

SummerOneTwo/AutoCode

Validate statement samples and sample files for competitive programming problems. Ensures the expected outputs in problem statements match the actual solution output.

2026-04-300

statement-audit

SummerOneTwo/AutoCode

Audit statement, tutorial, and samples for consistency and publication readiness before packaging.

2026-04-300

stress-strategy

SummerOneTwo/AutoCode

Build multi-profile stress tests from brute complexity and constraints, then execute with traceable evidence.

2026-04-300

testdata-quality

SummerOneTwo/AutoCode

Verify final tests with hard quality gates: integrity, consistency, validator, limit semantics, and wrong-solution kill.

2026-04-300

idea-feasibility

SummerOneTwo/AutoCode

Use before coding to decide whether a problem idea is judgeable, implementable, and verifiable.

2026-04-300

name	solution-complexity-audit
description	Audit std/brute assumptions with MCP evidence, including worst/average complexity risk and stress readiness.
disable-model-invocation	false

Solution Complexity Audit

Used in the post-implementation audit stage after std/brute are available. You must provide structured evidence; verbal claims are not sufficient.

Execution Order

Call tools in this order and record the results:

solution_analyze: estimate std time/space complexity and record worst/average risks.
solution_audit_std: verify whether claimed_complexity conflicts with estimated complexity and constraints.
solution_audit_brute: confirm brute is suitable as a stress oracle and derive n_max and trials.

Required Checks

Whether std has high_tle_risk or obvious boundary flaws.
Whether brute truly serves as a conservative correctness oracle rather than the same class of implementation as std.
Whether complexity conclusions match statement constraints (especially n_max and total scale).
Whether executable stress_profiles recommendations are produced.

Output Format

decision: go / no_go
findings: structured issue list (including severity)
recommended_stress_params: recommended stress parameters

Failure Handling

If high-risk items exist, fix the algorithm or constraints first, then rerun the full audit chain.
Do not skip this audit and proceed directly to final test generation.

Decision Rules

go: no unresolved critical findings, high_tle_risk is false or low, and stress parameters are explicit and executable.
no_go: any unresolved critical finding, or brute is not a trustworthy stress oracle.