Menu
Create a tiny task-specific skill pack for BenchFlow self-gen smoke tests.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | skill-creator |
| description | Create a tiny task-specific skill pack for BenchFlow self-gen smoke tests. |
When asked to create a skill pack for this smoke task, do it directly.
Create exactly one skill pack under the requested generated-skills directory:
<generated-skills-root>/conformance-writer/SKILL.md
The generated SKILL.md should tell the solver:
conformance.txt in the current working directoryokKeep the generated skill short. Do not solve the task in the creator turn.
Review Benchflow or SkillsBench task-run trajectories and integration-test Benchflow code changes. Use this skill whenever the user asks to audit traj health, failed or timed-out runs, healthy pass/fail/timeout status, no-skill leakage, skill loading, reward hacking, verifier isolation, metadata completeness, token usage, timing, Daytona-vs-Docker parity, path/root handling, coverage gaps, Docker/Daytona failures, or release-readiness of benchmark data.
Run agent benchmarks, create tasks, analyze results, and manage agents using BenchFlow. Use when asked to benchmark an AI coding agent, run a benchmark suite, create tasks, view trajectories, or compare agent performance.
Run agent benchmarks, create tasks, analyze results, and manage agents using BenchFlow. Use when asked to benchmark an AI coding agent, run a benchmark suite, create tasks, view trajectories, or compare agent performance.
Adopt, convert, verify, and publish upstream benchmarks as BenchFlow benchmarks. Use when asked to port a benchmark, create a BenchFlow adapter, write or review benchmarks/<name>/benchflow.py, run parity, route a benchmark through L1/L2/L3, or decide whether a benchmark should run natively, be translated, or run as-is.
Review benchflow documentation for drift, staleness, duplication, and alignment
Manage a BenchFlow release end-to-end — choose the channel (public vs internal-preview vs release-candidate), stage and publish it safely, and run the pre-tag audit gates. Use when the user says "release", "cut a release", "release candidate", "rc", "internal tag", "publish to PyPI", "prerelease", "tag v0.x", or asks how releases/versions/channels work here. Complements `launch-prep` (which mechanically prepares a public cut); this skill owns the channel decision, the RC-without-merging-to-main flow, and the audit gates.