kernel/pi-skillopt

manual-testing

Playbook for running a manual, end-to-end test of the pi-skillopt plugin in a real pi session — drive the skillopt-create / taskpack / finalize skills against an example, watch the loop progress, and analyze the run. Use when asked to "manually test…

원문 언어: 영어

skillopt-create

Set up and run a SkillOpt-style optimization loop for a single agent SKILL.md, scored by Harbor rollouts. Gathers the skill, the rollout environment (backend, agent, model, preloads), generates a task pack if none exists, then starts the loop. Use when asked…

원문 언어: 영어

skillopt-finalize

Close out a skillopt run — measure the optimized skill on the held-out test split, produce best_skill.md, and emit a clean diff + report against the original skill. Use when a skillopt loop has plateaued or the user asks to "finalize", "wrap up the skillopt…

원문 언어: 영어

skillopt-taskpack

Generate a Harbor task pack (tasks + verifiers + split manifest) from just a SKILL.md, so the skill can be scored by rollouts. Derives representative tasks from what the skill teaches, defines objective verifiers (outcome + skill-adherence), and emits…

원문 언어: 영어

jq-surgeon

Query and transform JSON with the jq CLI so the result is both correct and consumable by the next step. Covers raw vs encoded output, missing-key and error semantics, safe value injection with --arg/--argjson, multi-input handling, and the core transform…

원문 언어: 영어

reversible-migrations

Teaches an agent to author SQL schema migrations as reversible up/down pairs against a populated SQLite database, applied with the sqlite3 CLI. Every change ships as NNNN_name.up.sql plus NNNN_name.down.sql, where the down returns the database to its exact…

원문 언어: 영어

format-answer

Toy skill used by the hello-harbor example. Teaches an agent to answer a question by writing the value, wrapped in <answer></answer> tags, to the file the task names.

원문 언어: 영어