🛠️
AI EngineeringPython

Run History Skill Upgrader

by dongshuyan

Run History Skill Upgrader is an AI Engineering skill for Claude Code, published by dongshuyan in compass-skills.

701 stars58 forkson dongshuyan/compass-skillsAdded 2026/08/23+1% in starsRepository updated 2026/08/09
agent-memoryagent-skillagent-skillsai-agentsai-coding-agentai-skillsclaude-codeclaude-skillscodex-skillsdeveloper-toolslocal-firstopenai-codexpersonal-aiprompt-engineeringskill-mdskill-md-skillsmpskills-shskillsmptask-managementworkflow-automation
Install in seconds
Install Run History Skill Upgrader
Copy Run History Skill Upgrader into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/dongshuyan/compass-skills/tree/master/skills/run-history-skill-upgrader ~/.claude/skills/run-history-skill-upgrader

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/dongshuyan/compass-skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/run-history-skill-upgrader/SKILL.md in dongshuyan/compass-skills
Installs to
~/.claude/skills/run-history-skill-upgrader
Collection
One of 7 skills cataloged from this repository
Category
AI Engineering2451 skills

What Run History Skill Upgrader does

Run History Skill Upgrader plans structural improvements for an existing skill using run evidence, validation failures, source drift, platform drift, and user feedback. It is used to propose and, after explicit approval, apply changes when a skill needs maintenance or cleanup.

Run History Skill Upgrader is cataloged under AI Engineering on DirSkills. Run History Skill Upgrader comes from a repository tagged agent-memory, agent-skill, agent-skills, ai-agents and ai-coding-agent.

Documentation

README

Run History Skill Upgrader

Language Policy

Write all user-facing output in the user's language. Default to Chinese when the language is unknown.

Role

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.

Portability

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/.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Run History Skill Upgrader

  • What else does dongshuyan publish alongside Run History Skill Upgrader?

    Run History Skill Upgrader is one of 7 skills that DirSkills catalogs from dongshuyan/compass-skills, the repository it ships in. Its siblings there include Academic Humanizer, Run History Skill Builder and Session Handoff Prompt. Each one is a separate skill with its own page in this directory, installs the same way Run History Skill Upgrader does, and is maintained by dongshuyan in that same repository. The rest of the collection is listed on the dongshuyan/compass-skills page.

  • How does Run History Skill Upgrader compare to other AI Engineering skills?

    Run History Skill Upgrader ranks #1718 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Run History Skill Upgrader against them. Open each page to compare what they document and how they install.

More from dongshuyan/compass-skills

Run History Skill Upgrader is one of 7 skills cataloged on DirSkills from dongshuyan/compass-skills.

See all 7 skills
✍️
1w ago

Academic Humanizer

Academic Humanizer minimally revises English or Chinese academic prose to remove formulaic or mechanically repetitive phrasing while preserving claims, terminology, and scholarly register. Use it for papers, abstracts, grants, cover letters, and reviewer responses when you want to humanize text without changing meaning.
Writing
70158
🧠
1w ago

Run History Skill Builder

Run History Skill Builder turns completed tasks, browser flows, logs, or recovered workflows into a new reusable skill package or a reviewed design plan. Use it when you need to extract a workflow from evidence, summarize lessons, or hand off an upgrade for an existing skill.
AI Engineering
70158
🔁
1w ago

Session Handoff Prompt

Session Handoff Prompt creates a paste-ready continuation prompt for resuming a long or degraded agent session. Use it when starting a fresh session needs the current objective, verified facts, and next actions preserved.
AI Engineering
70158
1w ago

Task Clarifier

Task Clarifier asks structured questions to resolve a user's goals, constraints, and success criteria before work begins. Use it when a request is vague, conflicting, or needs explicit confirmation.
AI Engineering
70158
🌲
1w ago

Task Forest

Task Forest maintains a repo-local task DAG for the current workspace. Use it to initialize or update task structure, track progress and history, save proposals, or export a client-readable HTML view.
Automation
70158
🗂️
1w ago

User Profile Keeper

User Profile Keeper maintains a local persistent user profile for agent harnesses. Use it to create, update, query, correct, delete, export, or audit profile facts and collaboration preferences when explicitly invoked.
AI Engineering
70158