stark-ai-de/agent-skills / incubator/skills/skill-maintenance/skillopt-setup
skillopt-setup
FlaggedSet up Microsoft SkillOpt for Agent Skills improvement. Use when installing SkillOpt, preparing per-skill train/val/test eval splits, configuring Codex CLI or provider-backed execution, running SkillOpt against SKILL.md bodies, reviewing best_skill.md, or importing optimized skill changes. Do not use for ordinary skill authoring or manual repo validation.
assets/agent-skills-benchmark/config.hybrid-codex-target.yaml
View on GitHub_base_: ../_base_/default.yaml
env:
name: agent_skills
run_profile: <run-profile>
skill_init: .agents/skillopt-work/<skill>/initial/skill-body.md
split_mode: split_dir
split_dir: <split-dir>
visual_eval_policy: <visual-eval-policy>
out_root: .agents/skillopt-work/<skill>/outputs/<run-name>
reflection_backend: native
judge_backend: codex_cli
codex_cli_judge_model: ${SKILLOPT_JUDGE_MODEL}
codex_cli_judge_timeout: 240
codex_cli_judge_sandbox: read-only
exec_timeout: 240
tool_rollout_for_visual_assertions: true
require_drawio_cli_for_visual_rollouts: true
visual_exec_timeout: 120
workers: 4
max_turns: 1
train:
num_epochs: 4
batch_size: 20
seed: 42
gradient:
minibatch_size: 8
merge_batch_size: 8
analyst_workers: 8
max_analyst_rounds: 3
failure_only: false
optimizer:
learning_rate: 4
min_learning_rate: 2
lr_scheduler: cosine
skill_update_mode: patch
use_slow_update: true
slow_update_samples: 20
slow_update_gate_with_selection: false
use_meta_skill: true
longitudinal_pair_policy: mixed
use_skill_aware_reflection: false
skill_aware_appendix_source: both
skill_aware_consolidate_threshold: 0
evaluation:
use_gate: true
eval_test: true
sel_env_num: 0
test_env_num: 0
model:
optimizer_backend: openai_chat
optimizer: ${SKILLOPT_OPTIMIZER_MODEL}
target_backend: codex_exec
target: ${SKILLOPT_TARGET_MODEL}
codex_exec_path: codex
codex_exec_use_sdk: cli
codex_exec_full_auto: false
codex_exec_reasoning_effort: none
codex_exec_sandbox: workspace-write
codex_exec_network_access: false
codex_exec_web_search: false
codex_exec_approval_policy: never
codex_trace_to_optimizer: true
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |