hashgraph-online/awesome-codex-plugins / plugins/boshu2/agentops/skills/skill-builder
skill-builder
VerifiedCreate, repair, audit or consolidate agent skills (SKILL.md packages). Use when: writing or fixing a skill, its description or structure. Not for one-off lessons; use Memory.
references/skill-auditor.feature
View on GitHub# Executable contract for Skill Builder audit; coverage in test_skill_audit.bats
# and skillshealth evidence tests. No skill/provider trial runs during this audit.
Feature: Skill audit separates evidence without an optimization rank
@covered-by:cli/internal/skillshealth/evidence_test.go::TestEvidenceSeparatesUntestedOutcomes
Scenario: Untested conformant package
Given a valid package for the selected static profile
When the default audit runs
Then static conformance passes
And effects and behavioral evidence remain NOT_PROVEN
And no aggregate score or quality verdict is emitted
@covered-by:cli/internal/skillshealth/evidence_test.go::TestEvidenceEquivalentLayoutAndIrrelevantAdditions
Scenario: Layout and irrelevant additions do not improve substantive evidence
Given equivalent concise layouts and optional unreferenced files
When the default audit runs
Then substantive conformance and behavioral results are unchanged
And necessary prohibitions never become blocking authoring defects
@covered-by:cli/internal/skillshealth/evidence_test.go::TestEvidenceConformanceNegativesCannotBeDecoratedAway
Scenario: Concrete defects survive decoration
Given a missing required resource or unsupported portable field
When labels and irrelevant helpers are added
Then the concrete conformance defect still fails
@covered-by:cli/internal/skillshealth/evidence_test.go::TestEvidenceReachableRemoteExecutionAndInvariance
Scenario: Located reachable effects
Given SKILL.md links a script piping a remote response into a shell
When the default audit runs
Then the report locates that conditional execution path
And safety remains NOT_PROVEN after adding reassuring labels
@covered-by:tests/integration/test_skill_audit.bats::known-bad
@covered-by:tests/scripts/skill-audit-rubric-pass.bats::audit-report-legacy.json
Scenario: Explicit legacy field and exit compatibility
When the audit runs with --legacy
Then audit-report-legacy.json describes the complete old report
And the accepted S1 field and exit behavior is preserved
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |