New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Change Workflow

by owent in owent/libatbus

A skill your agent uses when: diagnosing or fixing a defect, test/build/runtime failure, or planning and implementing a nontrivial feature, behavior change, cross-module refactor, public API/ABI…

MITAuto-check passedDevelopment

Install Change Workflow

skills CLI
$ npx skills add owent/libatbus --skill change-workflow -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install owent/libatbus change-workflow --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/owent/libatbus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/change-workflow .claude/skills/change-workflow && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
change-workflow
GitHub stars
235
Token cost
~1.2k tokens
SKILL.md length
601 words
Files
2 (incl. references)
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when: diagnosing or fixing a defect, test/build/runtime failure, or planning and implementing a nontrivial feature, behavior change, cross-module refactor, public API/ABI…

  • Works in 4 steps: Route and discover → Keep one change contract → Execute from evidence → …
  • Fixing a defect
  • SKILL.md covers 1. Route and discover, 2. Keep one change contract, 3. Execute from evidence and 4. Verify and close, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Change Workflow is an agent skill from owent/libatbus. Use when: diagnosing or fixing a defect, test/build/runtime failure, or planning and implementing a nontrivial feature, behavior change, cross-module refactor, public API/ABI, data model/migration, security, or deployment change. Do not use when: only making a small documentation, formatting, comment, or routine local edit with a clear verification path.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/upstream-methods.md`).

It sits in Development. The repository describes itself as: 用于搭建高性能、全异步、树形结构的BUS消息系统的跨平台框架库. The licence is MIT.

When your agent uses it

  • Fixing a defect
  • Test/build/runtime failure
  • Planning and implementing a nontrivial feature
  • Behavior change

Example prompts

  • “/change-workflow”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Route and discover
  2. Keep one change contract
  3. Execute from evidence
  4. Verify and close

What it can do on your machine

Read from SKILL.md and the folder at commit d46c04d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Change Workflow loads about 1.2k tokens when it runs, and up to ~1.8k if it reads all its reference files. Until then it costs about 93 tokens; SKILL.md has 601 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~93
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from owent/libatbus at commit d46c04d, republished under its MIT licence (© owent). 601 words, ~1,221 tokens.

Download SKILL.mdSave it as .claude/skills/change-workflow/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
change-workflow
description
Use when: diagnosing or fixing a defect, test/build/runtime failure, or planning and implementing a nontrivial feature, behavior change, cross-module refactor, public API/ABI, data model/migration, security, or deployment change. Do not use when: only making a small documentation, formatting, comment, or routine local edit with a clear verification path.

Change Workflow

Apply a risk-scaled, repository-native workflow. Do not create OpenSpec or Superpowers directories, invoke their commands, or claim to use them unless the current checkout and harness prove that integration exists.

1. Route and discover

  • Inspect the exact code path, tests, generated inputs, configuration, recent relevant changes, and current failure or behavior before choosing a solution. Separate evidence from assumptions.
  • For a defect, reproduce the original symptom and identify the first causal boundary before editing.
  • For a nontrivial or high-risk change, establish a reviewable change contract before implementation.
  • When requirements or architecture remain materially ambiguous after source inspection, explore read-only first. Ask only the focused question needed to unblock a consequential choice, compare two or three viable approaches with a recommendation, and obtain approval before taking a materially different or irreversible path.

2. Keep one change contract

  • Reuse the repository's existing issue, specification, ADR, roadmap item, design file, or active task plan. Create a new persistent artifact only when repository policy, review/handoff needs, or the user's request requires one.
  • Record only what the change needs: intent and verified current behavior; in-scope and out-of-scope work; affected consumers; added, modified, or removed behavior with concrete acceptance scenarios; design decisions and constraints; ordered tasks; compatibility and rollback; and commands that will produce acceptance evidence.
  • Keep the contract current when implementation reveals a false assumption, changed dependency, or invalid design. Do not let code silently diverge from the agreed behavior.
  • If a verified openspec/ adoption exists, use its current change artifacts as the sole contract and follow the live profile and commands. Do not duplicate that contract elsewhere or initialize/update OpenSpec without authorization.
  • If verified Superpowers skills are available, use them for execution discipline; they do not replace or duplicate the authoritative change contract. Follow the installed version rather than remembered commands.
Show full SKILL.md (302 more words)Show less

3. Execute from evidence

  • Debug systematically: read the full error, reproduce consistently, trace inputs and state across component boundaries, compare with a working path, state one root-cause hypothesis, and test one variable at a time.
  • After three failed fix hypotheses, stop stacking patches and re-evaluate the architecture or missing evidence with the user before another implementation attempt.
  • For behavior changes and defects, prefer RED-GREEN-REFACTOR: add the smallest regression or acceptance test, run it and confirm it fails for the intended reason, implement the minimum change, run it green, then refactor while staying green. If test-first is impractical for generated, configuration-only, or environment-dependent work, state why and define an observable alternative check before editing.
  • Work in small dependency-ordered batches. After each batch, review contract compliance first and code quality second; update the contract before continuing if discoveries change scope or design.
  • Load local engineering-guidelines, testing, and build Skills for their domain-specific rules and commands instead of duplicating them here.

4. Verify and close

  • Map every acceptance scenario to fresh evidence. Re-run the original symptom, then focused tests, affected integration tests, build/lint checks, and broader regression coverage in proportion to risk.
  • Before any completion claim, identify the proving command, run it fully, read the exit status and failure/skip counts, and report the actual result. A silent, skipped, stale, or partial run is not green evidence.
  • Inspect the final diff and status for scope, accidental generated output, unrelated formatting, and staging boundaries.
  • Reconcile durable behavior and design decisions into the repository's long-lived source of truth. Retire temporary artifacts only when repository policy or user scope calls for it; use the verified archive flow if OpenSpec is active.
  • Report verified behavior, commands and results, deliberate gaps, and remaining risks without overstating confidence.

Reference

  • Read upstream methods only when verifying or changing OpenSpec/Superpowers adoption, integration, or policy.

© owent, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in .agents/skills/change-workflow of owent/libatbus.

  • SKILL.md
  • references/upstream-methods.md

Open the folder on GitHubat commit d46c04d

Compare with similar skills

Change Workflow next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Change Workflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Change Workflow this skillowent/libatbus235—~1.2kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Design Rationale Investigatorcursor/plugins10k9 repos~2.6kAutomated safety check: PassNone
Simple Englishmoeru-ai/airi50k2 repos~4.6kAutomated safety check: PassMIT
Mole CLI Release Flowtw93/Mole70k—~2.5kAutomated safety check: PassGPL-3.0
Babysit PR To Pass CIsgl-project/sglang37k2 repos~3kAutomated safety check: PassApache-2.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Code Design Rationale Investigator

    cursor/plugins

    Official

    Digs into why code is shaped the way it is by checking git history, pull requests and connected tools in parallel, then reporting a cited read on the tradeoffs.

    10k GitHub starsUsed in 9 repos~2.6k tokens
    DevelopmentAuto-check passed

  • Simple English

    moeru-ai/airi

    Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop.

    50k GitHub starsUsed in 2 repos~4.6k tokens
    DevelopmentAuto-check passed

  • Mole CLI Release Flow

    tw93/Mole

    Runbook for assessing and executing a Mole CLI release: distribution channels, pre-flight checks, capital-V tags, build artifacts and the handoff to curated release notes.

    70k GitHub stars~2.5k tokensUpdated today
    DevelopmentAuto-check passed

  • Babysit PR To Pass CI

    sgl-project/sglang

    Start and persistently pursue a goal to babysit an SGLang pull request until selected GitHub Actions workflows pass on the latest PR head.

    37k GitHub starsUsed in 2 repos~3k tokens
    DevelopmentAuto-check passed

  • Ansible Development Context

    ansible/ansible

    Load Ansible project development guidelines, testing conventions, PR review processes, and code structure reference into context

    71k GitHub stars~427 tokensUpdated yesterday
    DevelopmentAuto-check passed

More from owent/libatbus

  • Testing

    owent/libatbus

    A skill your agent uses when: designing, writing, reviewing, or running libatbus unit tests, filtering private-framework cases, testing topology/channel behavior, or diagnosing Windows test…

    235 GitHub stars~1k tokensUpdated 27 days ago
    Auto-check passed

  • Libatbus Protocol Crypto

    owent/libatbus

    A skill your agent uses when: working on libatbus protocol transport, ECDH handshakes, cipher/compression negotiation, message framing, access token auth, connectioncontext, or crypto-related tests.

    235 GitHub stars~4.3k tokensUpdated 27 days ago
    Auto-check passed

  • AI Agent Maintenance

    owent/libatbus

    A skill your agent uses when: initializing, auditing, or optimizing repository AI guidance, including AGENTS.md/CLAUDE.md bridges, Agent Skills, trigger descriptions, progressive disclosure, source…

    235 GitHub stars~1.4k tokensUpdated 27 days ago
    Auto-check passed

  • Shell Tooling

    owent/libatbus

    A skill your agent uses when: running terminal commands, writing or debugging shell/PowerShell scripts, choosing or installing CLI tools, or diagnosing command failures, quoting/escaping errors, or…

    235 GitHub stars~1.4k tokensUpdated 27 days ago
    Auto-check passed

  • Engineering Guidelines

    owent/libatbus

    A skill your agent uses when: writing or reviewing C++, public headers, template function visibility, exported API ABI, ATFWUTILSYMBOLVISIBLE, or ATFWUTILFORCEINLINE.

    235 GitHub stars~386 tokensUpdated 27 days ago
    Auto-check passed

Categories

Questions about Change Workflow

What does Change Workflow do?

A skill your agent uses when: diagnosing or fixing a defect, test/build/runtime failure, or planning and implementing a nontrivial feature, behavior change, cross-module refactor, public API/ABI…. Change Workflow is an agent skill from owent/libatbus. Use when: diagnosing or fixing a defect, test/build/runtime failure, or planning and implementing a nontrivial feature, behavior change, cross-module refactor, public API/ABI, data model/migration, security, or deployment change.

When should I use Change Workflow?

Change Workflow fits situations like: fixing a defect; test/build/runtime failure; planning and implementing a nontrivial feature; behavior change.

How do I install Change Workflow in Claude Code?

Run `npx skills add owent/libatbus --skill change-workflow -a claude-code`. Or copy the skill folder (.agents/skills/change-workflow in owent/libatbus) into .claude/skills/change-workflow in your project. Claude Code loads it when a task matches its description.

How do I install Change Workflow in Codex?

Run `npx skills add owent/libatbus --skill change-workflow -a codex`. Or copy the skill folder (.agents/skills/change-workflow in owent/libatbus) into .agents/skills/change-workflow in your project. Codex loads it when a task matches its description.

Can I use Change Workflow in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add owent/libatbus --skill change-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/change-workflow, .gemini/skills/change-workflow, .github/skills/change-workflow and .opencode/skills/change-workflow in your project.

What does Change Workflow need to run?

SKILL.md names no scripts, command-line tools or credentials: Change Workflow is instructions for the agent only.

Does Change Workflow access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Change Workflow safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Change Workflow use?

Change Workflow is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Change Workflow use?

About 1.2k tokens (SKILL.md is roughly 4.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 607 tokens, read only when the agent opens those files.

What are the alternatives to Change Workflow?

Skills that share tags, products or a category with Change Workflow: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Code Design Rationale Investigator (cursor/plugins, 10k stars), Simple English (moeru-ai/airi, 50k stars) and Mole CLI Release Flow (tw93/Mole, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Change Workflow?

owent (a GitHub user) maintains it in owent/libatbus, which has 235 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on September 11, 2026.

Source: owent/libatbus on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.