Skill Benchmark: tilegym-cutile-python
❌ Overall verdict: FAIL — Publication blocked
The skill should be reviewed before publication. Address the blocking findings below, then rerun Skill Evaluator.
Evaluation Metadata
- Skill:
tilegym-cutile-python - Evaluation date: 2026-10-16
- Evaluator version:
1.5.6 - Agents: Claude Code (
aws/anthropic/bedrock-claude-opus-4-8), Codex (openai/openai/gpt-5.5) - Tasks: 3 evaluation tasks (2 positive, 1 negative)
- Dataset digest:
sha256:8288ba1fc833c22b44a0957b327f0c48f0c9288983f830241d752d6e9dc68716(skill-evaluator-dataset-snapshot/1) - Attempts per task: 1
- Environment:
k8s-sandbox - Tier 2 evidence: required for publication
- Tier 3 evidence: required for publication
Each task attempt ran in its own isolated sandbox pod.
What This Report Answers
The three-tier evaluation checks whether the skill:
- is safe to use;
- produces correct answers;
- is discovered and activated when needed;
- helps the agent complete the user's goal and expected workflow; and
- avoids wasted skill and tool usage.
Results at a Glance
| Measure | Claude Code (Baseline → Skill Uplift) | Codex (Baseline → Skill Uplift) |
|---|---|---|
| Overall | 91.8% — baseline ran, but no comparable score was available; uplift unavailable | 91.9% — baseline ran, but no comparable score was available; uplift unavailable |
| Security | 100.0% → 100.0% (±0.0 points) | 100.0% → 100.0% (±0.0 points) |
| Correctness | 100.0% → 100.0% (±0.0 points) | 100.0% → 100.0% (±0.0 points) |
| Discoverability | 87.5% — baseline ran, but no comparable score was available; uplift unavailable | 88.0% — baseline ran, but no comparable score was available; uplift unavailable |
| Effectiveness | 75.8% → 91.1% (+15.3 points) | 84.8% → 84.5% (-0.3 points) |
| Efficiency | 80.3% — baseline ran, but no comparable score was available; uplift unavailable | 87.1% — baseline ran, but no comparable score was available; uplift unavailable |
How to read this table: baseline is the same task attempted without the target skill. Scores are rounded to one decimal; threshold-adjacent values use additional precision so their displayed band matches the verdict. Uplift is derived from those displayed scores and shown in percentage points.
Example: 47.0% → 92.0% (+45.0 points) means the skill-assisted run scored 92.0%, 45.0 percentage points above its 47.0% no-skill baseline.
A partial dimension was calculated from only the available configured signals; review the detailed report before relying on it.
Token Usage
Actual Tier 3 execution usage is reported for every observed agent/case pair and both conditions.
| Agent | Dataset case | With skill | Without skill | Delta | Change | Coverage |
|---|---|---|---|---|---|---|
| claude-code | All cases | 1,721,825 | 124,427 | +1,597,398 | +1283.80% | skill 3/3; base 3/3 |
| claude-code | 01-write-rmsnorm-cutile-kernel | 916,155 | 35,828 | +880,327 | +2457.09% | skill 1/1; base 1/1 |
| claude-code | 02-write-softmax-cutile-kernel | 745,855 | 29,052 | +716,803 | +2467.31% | skill 1/1; base 1/1 |
| claude-code | 03-kubernetes-yaml-negative | 59,815 | 59,547 | +268 | +0.45% | skill 1/1; base 1/1 |
| codex | All cases | 463,706 | 261,198 | +202,508 | +77.53% | skill 3/3; base 3/3 |
| codex | 01-write-rmsnorm-cutile-kernel | 168,952 | 69,425 | +99,527 | +143.36% | skill 1/1; base 1/1 |
| codex | 02-write-softmax-cutile-kernel | 281,235 | 178,290 | +102,945 | +57.74% | skill 1/1; base 1/1 |
| codex | 03-kubernetes-yaml-negative | 13,519 | 13,483 | +36 | +0.27% | skill 1/1; base 1/1 |
| ALL AGENTS | Dataset aggregate | 2,185,531 | 385,625 | +1,799,906 | +466.75% | skill 6/6; base 6/6 |
Prompt tokens include cached reads, so total tokens are prompt + completion (cached is not added twice). The Efficiency score uses (prompt - cached) + completion. N/A means the relevant trajectory counters were not available; coverage is never estimated.
Tier Status
| Tier | Purpose | Status | Evidence |
|---|---|---|---|
| Tier 1 | Static validation | FAILED | 11 validator(s); 28 finding(s) |
| Tier 2 | Semantic deduplication | PASSED WITH OBSERVATIONS | 2 validator(s); 1 finding(s) |
| Tier 3 | Live agent evaluation | PASS | 2 agent(s); 3 task(s) |
Findings and Observations
<details> <summary>Show detailed findings and successful checks</summary>- CRITICAL CONTENT_DEDUP/llm_cluster_count_limit: Tier 2 found more than 50 clusters requiring LLM review. (
skills/tilegym-cutile-python) - MEDIUM SECURITY/Skill Enumeration (AS3): Agent Snooping: skills/tilegym-cutile-python/SKILL.md (
BENCHMARK.md:72) - MEDIUM SECURITY/Skill Enumeration (AS3): Agent Snooping: skills/tilegym-cutile-python/SKILL.md (
BENCHMARK.md:73) - MEDIUM SECURITY/Skill Enumeration (AS3): Agent Snooping: skills/tilegym-cutile-python/SKILL.md (
BENCHMARK.md:74) - MEDIUM SECURITY/Skill Enumeration (AS3): Agent Snooping: skills/tilegym-cutile-python/SKILL.md (
BENCHMARK.md:75) - 24 additional finding(s) are available in the full evaluation artifacts.
Scoring Methodology
<details> <summary>Show dimension definitions, source signals, and thresholds</summary>| Dimension | Question | Scored signals |
|---|---|---|
| Security | Is it safe to use? | security (100%) |
| Correctness | Is the answer correct? | accuracy (100%) |
| Discoverability | Was the right skill loaded when needed? | skill_execution (100%) |
| Effectiveness | Did the skill help complete the task? | goal_accuracy (50%) + behavior_check (50%) |
| Efficiency | Did it avoid wasted tool calls and token usage? | skill_efficiency (50%) + token_efficiency (50%) |
- Dimension bands: PASS at 50% or above; NEUTRAL from 40% to below 50%; FAIL below 40%.
- Overall Tier 3 lift: PASS at +5 points or more; FAIL at -10 points or less; values between those bands are NEUTRAL.
- Overall verdict: PASS only when every configured dimension passes for at least one supported agent. Lift is reported as diagnostic evidence and does not override this gate.
- The 50% attempt pass threshold is a separate per-task gate; it is not the dimension pass threshold.
- Effectiveness is the equal-weight mean of goal completion (
goal_accuracy) and expected workflow adherence (behavior_check). - Efficiency is 50% tool-call productivity (the backward-compatible
skill_efficiencywire id) and 50%token_efficiency. Positive-case skill routing is scored under Discoverability, not Efficiency; a negative case without a routing target is N/A. N/A sources are omitted, remaining weights are renormalized, and the dimension is marked partial.
Signals present in this run:
security(Security): unsafe operations, secret leakage, and unauthorized access.skill_execution(Skill Execution): whether the expected skill was selected, decoys were avoided, and the workflow executed.skill_efficiency(Tool Productivity): tool-call productivity (legacy wire id; routing is scored under Discoverability).accuracy(Accuracy): final-answer correctness against the reference answer.goal_accuracy(Goal Accuracy): whether the user's goal was achieved.behavior_check(Behavior Check): whether the expected workflow behavior was followed.token_efficiency(Token Efficiency): actual uncached prompt plus completion usage (50% of Efficiency).
Freshness
Regenerate this benchmark when the skill, evaluation dataset, target agent/model, evaluator version, environment, or scoring policy changes.