checkpoint-ambiguity-review
Audits tests to ensure they enforce explicit specs rather than ambiguous interpretations.
Install
mkdir -p .claude/skills/checkpoint-ambiguity-review && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18667" && unzip -o skill.zip -d .claude/skills/checkpoint-ambiguity-review && rm skill.zipInstalls to .claude/skills/checkpoint-ambiguity-review
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Review checkpoint specs and tests to identify tests that encode ambiguous interpretations rather than explicit requirements. Use when asked to check checkpoint_N.md against test_checkpoint_N.py, when auditing tests for ambiguity, or when reviewing snapshot eval failures for interpretive issues.Key capabilities
- →Collect problem name and checkpoint number
- →Read checkpoint spec and test files
- →Extract explicit requirements from the spec
- →Map test assertions to spec clauses or implied behaviors
- →Flag ambiguous interpretations in tests
How it works
The skill reads a checkpoint's specification and associated tests to identify assertions that enforce non-explicit interpretations. It flags these ambiguities with explanations and proposed resolutions.
Inputs & outputs
When to use checkpoint-ambiguity-review
- →Auditing test ambiguity
- →Comparing specs with tests
- →Reviewing snapshot failures
About this skill
Checkpoint Ambiguity Review
Overview
Review a checkpoint's spec and tests to find tests that enforce a reasonable but non-explicit interpretation, and report those cases with rationale and fixes.
Workflow
1) Collect inputs
- Problem name and checkpoint number (N).
- Test file path(s) and checkpoint spec path (if not provided, infer):
- Spec:
problems/{problem}/checkpoint_{N}.md - Tests:
problems/{problem}/tests/test_checkpoint_{N}.py - Also scan
problems/{problem}/tests/conftest.pyandproblems/{problem}/tests/data/if they influence expectations.
- Spec:
- Optional: snapshot path for ambiguity verification.
2) Read the spec and tests
- Extract explicit requirements from the spec.
- Map each test assertion to a specific spec clause or an implied behavior.
- Note any test assumptions that are not spelled out in the spec.
3) Flag ambiguous interpretations
Only report tests that enforce an interpretation that could reasonably differ given the spec wording. Do not report tests that are simply incorrect against explicit requirements.
Common ambiguity cues:
- Output ordering when the spec does not mandate order.
- Tie-breaking rules that are unstated.
- Whitespace, casing, or formatting details not defined by the spec.
- Rounding or precision requirements not defined.
- Error handling for invalid inputs when not specified.
- Boundary behavior (inclusive/exclusive) not stated.
- Default values or optional fields not defined.
- Determinism or randomness expectations not specified.
- Multiple reasonable data structure representations (list vs set, map order).
4) Optional snapshot verification
If a snapshot is provided, run:
slop-code --quiet eval-snapshot {snapshot} -p {problem} -o /tmp/eval -c {N} -e configs/environments/docker-python3.12-uv.yaml --json
Use failures to corroborate ambiguity, not to invent it. A failing test is ambiguous only if the spec supports multiple reasonable interpretations.
5) Report format
Use the following structure for each ambiguous test:
## {test name} ({path}::{node_id})
**Why:** {spec language + alternate interpretation that could be valid}
**Fix:** {proposed test relaxation or spec clarification}
Keep entries concise and actionable. If no ambiguity is found, state that clearly (e.g., "No ambiguity issues found.").
When not to use it
- →When reporting tests that are simply incorrect against explicit requirements
- →When the user needs to fix code directly without ambiguity analysis
Limitations
- →Only reports tests that enforce an interpretation that could reasonably differ given the spec wording
- →Does not fix the code or spec directly, only provides recommendations
- →Optional snapshot verification requires `slop-code` tool
How it compares
This skill systematically identifies and reports ambiguities between specifications and tests, providing actionable fixes, unlike a manual review that might overlook subtle interpretive differences.
Compared to similar skills
checkpoint-ambiguity-review side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| checkpoint-ambiguity-review (this skill) | 0 | 7mo | Review | Intermediate |
| python-testing-patterns | 77 | 2mo | Review | Intermediate |
| python-playground | 2 | 4mo | Review | Beginner |
| mflux-manual-testing | 2 | 1mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by SprocketLab
View all by SprocketLab →You might also like
python-testing-patterns
wshobson
Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.
python-playground
pydantic
Run and test Python code in a dedicated playground directory. Use when you need to execute Python scripts, test code snippets, investigate CPython behavior, or experiment with Python without affecting the main codebase.
mflux-manual-testing
filipstrand
Manually validate mflux CLIs by exercising the changed paths and reviewing output images/artifacts.
examples-auto-run
openai
Run python examples in auto mode with logging, rerun helpers, and background control.
extract-fuzzer-repro
noir-lang
Extract a Noir reproduction project from fuzzer failure logs in GitHub Actions. Use when a CI fuzzer test fails and you need to create a local reproduction.
klingai-known-pitfalls
jeremylongshore
Manage avoid common mistakes when using Kling AI. Use when troubleshooting issues or learning best practices to prevent problems. Trigger with phrases like 'klingai pitfalls', 'kling ai mistakes', 'klingai gotchas', 'klingai best practices'.