Agent skill
ce-test-creator
Design tests to close documented coverage gaps identified by gap analysis, without padding. Adapts recommendations for Option A/B/C in the Test Quality Method. Use ce-test-author to write tests for already-known targets.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/ce-test-creator
SKILL.md
CE Test Creator
This skill implements the Test Creator role from ADR-030 and mirrors the
prompt in docs/improvement/test-quality-method/test_creator.md.
Required references
docs/improvement/test-quality-method/README.md(canonical method + options)docs/improvement/test-quality-method/test_creator.md(full role prompt)
Use this skill when
- Closing documented coverage gaps.
- Replacing low-value tests with stronger behavioral coverage.
- Adding missing exception, serialization, or contract tests.
Focus option handling
- Option A (Test-Focused): run the full gap-closing workflow.
- Option B (Code-Focused): only propose targeted tests when code-focused changes expose a coverage-gate failure; otherwise return "no new tests needed."
- Option C (Full Cycle): run Option A and coordinate with code-focused findings to avoid adding tests that duplicate soon-to-be-pruned paths.
Core rule
Every new test must add meaningful signal:
- covers unique lines, or
- introduces unique parameter/assertion behavior.
Workflow
- Confirm the selected focus option (
A,B, orC) and scope work accordingly. - Analyze gaps:
python scripts/over_testing/gap_analyzer.py
python scripts/quality/check_coverage_gates.py
- Prioritize targets:
- Tier 1: public API error paths, serialization round-trips, boundary behavior.
- Tier 2: parameter combinations that exercise distinct contracts.
- Tier 3: expensive integration/viz paths (only when needed).
- Design tests for behavioral specificity:
- use public APIs only
- assert outputs/side effects, not just object existence
- parameterize where duplication risk is high
- Cross-check with existing coverage artifacts to avoid duplicates.
Output contract
For each proposed test include:
- target behavior
- target module/function
- why existing tests do not already cover it
- expected coverage/quality gain
- selected focus option (
A,B, orC) and why the proposal fits it
Constraints
- Avoid implementation-detail coupling.
- Avoid coverage padding.
- Route proposals through
ce-devils-advocatefor risk challenge before large batch changes.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?