メニュー
Use when the user wants Microsoft SkillOpt, self-evolving agent skills, skill optimization from rollouts, validation-gated skill edits, token-cost reduction, thrashing detection, or Tokut/Token Cut remediation.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when the user asks about Eidos, Eidos AGI, platform status, `eidos do`, closeout, cleanup before done, docket-task orchestration, evidence verification, praxis learning, gateway routing, vault/secrets, plugins, or which Eidos AGI specialist system should handle a task. This skill tells Codex to call the installed `eidos` CLI first; MCP and plugins should only point to CLIs, while CLIs provide progressive reveal of the deeper tool graph.
Investigate current context before predicting likely futures, failures, user objections, and concrete changes. Use when Zoltar needs to research an app, plugin, architecture, workflow, plan, decision, or implementation and answer what is likely to go wrong, what evidence supports it, what complaint or failure is being prevented, and what should change today.
Answer a specific foresight decision question with researched evidence, a clear judgment, likely futures, user complaint prediction, and concrete changes. Use when Daniel asks whether an idea, implementation, plugin, architecture, or workflow is likely to be regretted, whether it is the right thing in the right place with the right authority, or what decision should be made given future effects.
Compatibility entrypoint for Zoltar foresight. Use when Daniel mentions Zoltar, asks to predict the future, asks for second-order effects, asks what he will complain about, or wants future-backed product/spec changes; route the work through researched evidence, judgment, structured output, doer/checker handoff, and self-improvement notes rather than generic prediction.
Maintain and check the Eidos marketplace when plugins must work in both Claude Code and Codex. Use when adding, refactoring, auditing, or debugging marketplace plugins, dual-host packaging, .claude-plugin and .codex-plugin manifests, root marketplace entries, source/store/cache drift, install proof, or host-neutral plugin payloads.
Challenge whether a Zoltar prediction, product idea, plugin, workflow, category framing, or architecture is overfit to existing market patterns. Use when Daniel asks for a Challenger Matrix, anti-consensus review, category redefinition, frontier user needs, non-consensus futures, Doubter voice, or whether an answer is too derivative, market-shaped, competitor-shaped, or copied from current agent/product patterns.
| name | use-skillopt |
| description | Use when the user wants Microsoft SkillOpt, self-evolving agent skills, skill optimization from rollouts, validation-gated skill edits, token-cost reduction, thrashing detection, or Tokut/Token Cut remediation. |
SkillOpt trains a natural-language skill document as the external state of a
frozen agent. Use it when the work has scored rollout evidence and the output
should be a reusable best_skill.md, not a one-off prompt rewrite.
Before running an optimization loop, identify:
If any of these are missing, create the contract first. Do not treat vague "make this better" feedback as enough evidence for SkillOpt.
For Tokut-style cost reduction, turn token telemetry into scored rollout evidence. Look for:
Score the runs on both task success and waste reduction. The optimized skill should prevent the repeated behavior, preserve successful behavior, and make the next run cheaper without hiding required verification.
Use the bundled bootstrap script when the upstream Microsoft repo is not already present:
plugins/skillopt/scripts/skillopt-bootstrap /tmp/skillopt
The script clones https://github.com/microsoft/SkillOpt.git and checks out
the release ref configured by SKILLOPT_REF, defaulting to v0.1.0.
best_skill.md as code before deployment.A useful SkillOpt run should end with:
best_skill.mdDo not put secrets, private messages, customer data, account data, raw browser sessions, or unrestricted logs into SkillOpt datasets. Stop before replacing a live global skill, changing production agent policy, or enabling an automated remediation loop unless the user explicitly approves that deployment.