- name
SKILL.md
技能文件保留在发布者的仓库中。
在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add dongshuyan/compass-skills --skill run-history-skill-upgrader -a cursor -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add dongshuyan/compass-skills --skill run-history-skill-upgrader -a claude-code -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add dongshuyan/compass-skills --skill run-history-skill-upgrader -a codex -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add dongshuyan/compass-skills --skill run-history-skill-upgrader -a grok -y在 Grok Bot 聊天中发送复制的消息。Bot 会从 GitHub 获取这个 SKILL.md,并添加到你所有 Bot 共享的技能中。
Install this skill: https://github.com/dongshuyan/compass-skills/tree/HEAD/skills/run-history-skill-upgrader来自发布者
Write all user-facing output in the user's language. Default to Chinese when the language is unknown.
Turn real run feedback into structural net improvement for an existing skill. Upgrades may add, modify, merge, delete, deprecate, or decide not to change anything.
This skill is agent-agnostic. It should work in Codex, Claude Code, OpenCode, OpenClaw, Hermes, and similar local agent hosts that can read SKILL.md plus optional references/, scripts/, evals/, and agents/.
<skill-dir> from the directory that contains this SKILL.md.<python> mean the host's available Python launcher: python3, python, or py -3.<skill-dir>/scripts/... describe path segments, not a required separator style. On Windows, use the separator style that your shell or harness accepts.This skill always starts in plan_only.
plan_only: read the target skill and the agreed evidence scope, then produce a concrete upgrade plan and stop.apply_after_approval: modify files only after the user explicitly approves that specific plan.The following are not approval by themselves:
Valid approval must clearly point to the current plan, for example "approve plan A", "apply the plan above", or "yes, execute that upgrade plan".
plan_only unless explicit post-plan approval already exists in the current conversation.no_change, maintenance_note_only, prune_or_consolidate, local_refactor, cross_reference_refactor, major_refactor, or deprecate_or_replace_source.Strong evidence:
Weak evidence unless corroborated:
Before applying changes:
SKILL.md, relevant references/, scripts/, evals/, and optional agent metadata;Do not write credentials, browser sessions, private account data, unrelated personal paths, or hidden prompts into the target skill.
Run the bundled validator for this upgrader skill:
<python> <skill-dir>/scripts/validate_upgrade_artifacts.py --skill <skill-dir>
This bundled validator checks package structure, the portable Agent Skills frontmatter field set, referenced paths, JSON shape, Python syntax, common private-path leaks, and the upgrader's required approval terms. Its dependency-free frontmatter preflight accepts scalar fields, block text, and one-level string metadata; it rejects other YAML forms instead of guessing. A specific host may accept different syntax or a narrower field set, so its canonical validator remains authoritative for installation there. Neither structural check runs the eval cases or proves that an upgrade improves behavior.
Then run the target skill's own validator and the smallest relevant technical checks:
python -m py_compile for modified Python scripts;python -m json.tool for edited JSON files;description changed;Do not claim that the upgrade is complete if validation was skipped or failed.
Report:
references/evidence-and-scope.mdreferences/upgrade-decision-protocol.mdreferences/validation-and-regression.mdreferences/examples.mdscripts/validate_upgrade_artifacts.pyevals/evals.jsonUse real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only after explicit approval, apply structural upgrades to an existing skill. Use when the user
---name: run-history-skill-upgraderdescription: Use real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only…---# skills/run-history-skill-upgrader/SKILL.md概览
Use real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only after explicit approval, apply structural upgrades to an existing skill. Use when the user asks to improve an existing skill from recent runs, recurring failures, outdated sources, excessive bloat, changed platform behavior, or validated workflow feedback. Do not use to create a brand-new skill or to execute the business workflow itself.
常见问题
从发布者处下载 skills/run-history-skill-upgrader/SKILL.md,或复制路径后打开仓库。PlugMCP 只收录该技能,不托管文件。
发布者将它存放在 https://github.com/dongshuyan/compass-skills。
Claude、Cursor、Codex 和 Grok Build 可以读取你从发布者仓库添加的 SKILL.md。在聊天中发送技能的 GitHub 文件夹链接,Grok Bot 就会安装它。