Agent skill

Revision Workflow

by BingHanOfUESTC in BingHanOfUESTC/open_agent_team

Versioned fiction revision workflow. An agent skill from BingHanOfUESTC/open_agent_team.

MITAuto-check passedDevelopment

Install Revision Workflow

skills CLI
$ npx skills add BingHanOfUESTC/open_agent_team --skill revision-workflow -a claude-code

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

GitHub CLI
$ gh skill install BingHanOfUESTC/open_agent_team revision-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/BingHanOfUESTC/open_agent_team.git skills-src && mkdir -p .claude/skills && cp -r skills-src/teams/story_team/skills/revision-workflow .claude/skills/revision-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
revision-workflow
GitHub stars
106
Token cost
~264 tokens
SKILL.md length
20 words
Files
1
Skills in repo
30
Repo updated
First seen
Licence
MIT

At a glance

Versioned fiction revision workflow. An agent skill from BingHanOfUESTC/open_agent_team.

  • Works in 5 steps: 固定循环 → 返修计划必须可验证 → change_log 必须证明真实修改 → …
  • Coordinating critique-revision loops
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Applying review findings

What it does

Revision Workflow is an agent skill from BingHanOfUESTC/open_agent_team. Versioned fiction revision workflow. Use when coordinating critique-revision loops, applying review findings, proving that changes were actually made, and deciding whether a draft has passed or needs another revision.

Its SKILL.md is about 260 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Code review and Creative writing and fiction. The repository describes itself as: Build persistent multi-agent teams that collaborate like real organizations to deliver complex tasks. The licence is MIT.

When your agent uses it

  • Coordinating critique-revision loops
  • Applying review findings
  • Proving that changes were actually made
  • Deciding whether a draft has passed

Example prompts

  • “/revision-workflow”

Workflow steps

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

  1. 固定循环
  2. 返修计划必须可验证
  3. change_log 必须证明真实修改
  4. 禁止伪返修
  5. 复评重点

What it can do on your machine

Read from SKILL.md and the folder at commit 7e28736. 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

Revision Workflow loads about 264 tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 20 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~264

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 BingHanOfUESTC/open_agent_team at commit 7e28736, republished under its MIT licence (© BingHanOfUESTC). 20 words, ~264 tokens.

Download SKILL.mdSave it as .claude/skills/revision-workflow/SKILL.md (or your agent's skills folder).
name
revision-workflow
description
Versioned fiction revision workflow. Use when coordinating critique-revision loops, applying review findings, proving that changes were actually made, and deciding whether a draft has passed or needs another revision.
type
workflow
model-invocable
false

Revision Workflow

返修不是写 todo。返修是产生一个更强的新稿,并用复评证明它解决了旧稿的问题。


1. 固定循环

text
draft_vNN
critic_vNN
reader_impact_vNN
revision_plan_vNN_to_vNN+1
change_log_vNN_to_vNN+1
draft_vNN+1
critic_vNN+1
reader_impact_vNN+1
iteration_status update

循环直到通过或达到上限。


2. 返修计划必须可验证

每条返修计划必须包含:

text
对应 review finding
影响位置
采取动作:删除 / 合并 / 重写 / 移动 / 新增 / 压缩
预期改善的评分维度
验证方式

3. change_log 必须证明真实修改

change_log 不写“已优化”。必须写:

text
旧稿问题
新稿改法
涉及段落或场景
为什么这个改法比旧稿更有压力、更可信或更有余味
残留风险

4. 禁止伪返修

text
只同义改写句子,但结构问题仍在
只新增解释,试图说服读者相信人物
只把 critic 的话复制进计划,没有输出完整新稿
只润色语言,不处理 P0 动机、结构、开头问题
新稿没有复评就进入终稿

5. 复评重点

复评不是重新夸一遍。必须检查:

text
上一轮 P0 是否消失
新稿是否产生新的 P0
分数是否真实上升
开头、人物、结构、语言、余震是否达到门槛
reader impact 的流失点是否减少

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

Files

Just SKILL.md in teams/story_team/skills/revision-workflow of BingHanOfUESTC/open_agent_team.

Open the folder on GitHubat commit 7e28736

Compare with similar skills

Revision 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.

Revision Workflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Revision Workflow this skillBingHanOfUESTC/open_agent_team106—~264Automated safety check: PassMIT
Docs GuardamElnagdy/guard-skills1.3k—~2.1kAutomated safety check: PassMIT
AristotleK-Dense-AI/mimeographs129—~1.6kAutomated safety check: PassMIT
Writing Styleumputun/cc-thingz484—~1.3kAutomated safety check: PassMIT
3dgs Training Debuggerjaccen/Awesome-Gaussian-Skills161—~7kAutomated safety check: PassApache-2.0
ReviewSethGammon/Citadel923—~2.1kAutomated safety check: PassMIT

Similar skills

  • Docs Guard

    amElnagdy/guard-skills

    Checks generated or edited documentation against the source code, flagging invented symbols, outdated samples and unverifiable claims before publishing.

    1.3k GitHub stars~2.1k tokensUpdated 3 mo ago
    DevelopmentAuto-check passed
  • Aristotle

    K-Dense-AI/mimeographs

    Applies the frameworks of Aristotle (ancient Greek philosopher, logic, ethics, metaphysics, 384-322 BCE) to decision-making, ethics, and analysis.

    129 GitHub stars~1.6k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Writing Style

    umputun/cc-thingz

    A skill your agent uses for technical communication - GitHub/GitLab tickets, PR/MR descriptions, issue comments, code review comments, commit messages.

    484 GitHub stars~1.3k tokensUpdated 4 days ago
    DevelopmentAuto-check passed
  • 3dgs Training Debugger

    jaccen/Awesome-Gaussian-Skills

    Diagnose and fix 3DGS training-time failures: NaN losses, OOM crashes, divergent optimization, floater artifacts, densification failures, hyperparameter sensitivity.

    161 GitHub stars~7k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Review

    SethGammon/Citadel

    5-pass structured code review — correctness, security, performance, readability, consistency

    923 GitHub stars~2.1k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Codd Fable Consult

    yohey-w/codd-dev

    Consult Claude Fable 5 (Anthropic's most capable model for deep, long-horizon reasoning — or whichever model currently holds that role) for a genuinely hard, novel CoDD architectural design…

    115 GitHub stars~3.8k tokensUpdated 25 days ago
    DevelopmentAuto-check passed

More from BingHanOfUESTC/open_agent_team

All 30 skills in this repo
  • Skill Validation And Evaluation

    BingHanOfUESTC/open_agent_team

    A skill your agent uses when validating a newly created or updated agent skill with structure checks, routing positive and negative examples, contamination checks, progressive disclosure review, and…

    106 GitHub stars~303 tokensUpdated 3 mo ago
    Auto-check passed
  • Autoresearch Orchestration

    BingHanOfUESTC/open_agent_team

    A skill your agent uses when autoresearchteam needs to manage an end-to-end research lifecycle from Boss brief to literature, idea, implementation, experiments, synthesis, and LaTeX delivery.

    106 GitHub stars~691 tokensUpdated 3 mo ago
    Auto-check passed
  • Experiment Iteration Loop

    BingHanOfUESTC/open_agent_team

    A skill your agent uses when designing, running, logging, diagnosing, or iterating experiments for the selected research idea.

    106 GitHub stars~446 tokensUpdated 3 mo ago
    Auto-check passed
  • Latex Paper Artifact

    BingHanOfUESTC/open_agent_team

    A skill your agent uses when producing the final arXiv-style LaTeX paper, BibTeX, figures, tables, reproducibility statement, appendix, and artifact manifest.

    106 GitHub stars~635 tokensUpdated 3 mo ago
    Auto-check passed
  • Literature Evidence Mapping

    BingHanOfUESTC/open_agent_team

    A skill your agent uses when discovering papers, mapping related work, reading papers deeply, checking citations, or building evidence cards for an auto research task.

    106 GitHub stars~949 tokensUpdated 3 mo ago
    Auto-check passed
  • Media Asset Sourcing

    BingHanOfUESTC/open_agent_team

    A skill your agent uses when PPT slides need external images, screenshots, logos, product photos, stock-like visuals, diagrams, or videos that must be downloaded, inserted, or linked with source and…

    106 GitHub stars~819 tokensUpdated 3 mo ago
    Auto-check passed

Questions about Revision Workflow

What does Revision Workflow do?

Versioned fiction revision workflow. An agent skill from BingHanOfUESTC/open_agent_team. Revision Workflow is an agent skill from BingHanOfUESTC/open_agent_team. Versioned fiction revision workflow.

When should I use Revision Workflow?

Revision Workflow fits situations like: coordinating critique-revision loops; applying review findings; proving that changes were actually made; deciding whether a draft has passed.

How do I install Revision Workflow in Claude Code?

Run `npx skills add BingHanOfUESTC/open_agent_team --skill revision-workflow -a claude-code`. Or copy the skill folder (teams/story_team/skills/revision-workflow in BingHanOfUESTC/open_agent_team) into .claude/skills/revision-workflow in your project. Claude Code loads it when a task matches its description.

How do I install Revision Workflow in Codex?

Run `npx skills add BingHanOfUESTC/open_agent_team --skill revision-workflow -a codex`. Or copy the skill folder (teams/story_team/skills/revision-workflow in BingHanOfUESTC/open_agent_team) into .agents/skills/revision-workflow in your project. Codex loads it when a task matches its description.

Can I use Revision 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 BingHanOfUESTC/open_agent_team --skill revision-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/revision-workflow, .gemini/skills/revision-workflow, .github/skills/revision-workflow and .opencode/skills/revision-workflow in your project.

What does Revision Workflow need to run?

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

Does Revision 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 Revision 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 Revision Workflow use?

Revision 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 Revision Workflow use?

About 264 tokens (SKILL.md is roughly 1.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Revision Workflow?

Skills that share tags, products or a category with Revision Workflow: Docs Guard (amElnagdy/guard-skills, 1.3k stars), Aristotle (K-Dense-AI/mimeographs, 129 stars), Writing Style (umputun/cc-thingz, 484 stars) and 3dgs Training Debugger (jaccen/Awesome-Gaussian-Skills, 161 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Revision Workflow?

BingHanOfUESTC (a GitHub user) maintains it in BingHanOfUESTC/open_agent_team, which has 106 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on June 23, 2026.

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