Workflow guardrail candidates
Skill jscraik/Agent-Skills/codex/agents/evals/workflow-guardrail-candidates
Binary calibration pack for recurring workflow guardrail recommendations.From its SKILL.md
npx -y skills add jscraik/Agent-Skills --skill workflow-guardrail-candidatesAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 8 stars8 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
0.6 KB, 97 tokens by cl100k_base, as published. Nobody here has run it
Workflow Guardrail Candidates
This directory is the runnable source root for the workflow-guardrail-candidates eval pack.
Layout
references/evals.yamlholds the claim-to-case routing and calibration expectations.evals/contains per-case task and criteria files.tessl.jsonmarks the staged project root for the eval runner.workflow-guardrail-candidates.jsonpreserves the canonical pack content used to generate the staged source.
What ships with it: 25 files
13.1 KB alongside SKILL.md
evals/
- linear-p0-blocking/criteria.json246 B
- linear-p0-blocking/task.md158 B
- mise-uv-cache-drift/criteria.json260 B
- mise-uv-cache-drift/task.md146 B
- missing-closeout-evidence/criteria.json266 B
- missing-closeout-evidence/task.md94 B
- semgrep-anti-pattern/criteria.json248 B
- semgrep-anti-pattern/task.md128 B
- stale-feature-flag/criteria.json259 B
- stale-feature-flag/task.md88 B
- subagent-artifact-missing/criteria.json266 B
- subagent-artifact-missing/task.md95 B
references/
- contract.yaml1.2 KB
- evals.yaml2.4 KB
- scorer-calibration/examples.jsonl1.1 KB
- scorer-calibration/manifest.json771 B
- scorer-calibration/raw/concise-evidence-beats-verbose.json183 B
- scorer-calibration/raw/copied-rubric-rejected.json164 B
- scorer-calibration/raw/held-out-zero-to-one.json177 B
- scorer-calibration/raw/obvious-correct-candidate-routing.json181 B
- scorer-calibration/raw/obvious-wrong-no-evidence.json162 B
- scorer-calibration/raw/skill-name-only-not-enough.json168 B
- task-profile.json1.2 KB
- tessl.json173 B
- workflow-guardrail-candidates.json3.1 KB