Vercel Composition Patterns
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
通过外部对标+对抗迭代让规则/技能/SKILL.md 收敛到可执行状态. An agent skill from KonghaYao/peri.
Install Auto Converge
$ npx skills add KonghaYao/peri --skill auto-converge -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install KonghaYao/peri auto-converge --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/KonghaYao/peri.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/auto-converge .claude/skills/auto-converge && rm -rf skills-srcUse ~/.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/
Install the "auto-converge" agent skill from https://github.com/KonghaYao/peri/tree/main/.claude/skills/auto-converge into .claude/skills/auto-converge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-converge", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/KonghaYao/peri/tree/main/.claude/skills/auto-convergeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add KonghaYao/peri --skill auto-converge -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install KonghaYao/peri auto-converge --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/KonghaYao/peri.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/auto-converge .agents/skills/auto-converge && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "auto-converge" agent skill from https://github.com/KonghaYao/peri/tree/main/.claude/skills/auto-converge into .agents/skills/auto-converge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-converge", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add KonghaYao/peri --skill auto-converge -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install KonghaYao/peri auto-converge --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/KonghaYao/peri.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/auto-converge .cursor/skills/auto-converge && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "auto-converge" agent skill from https://github.com/KonghaYao/peri/tree/main/.claude/skills/auto-converge into .cursor/skills/auto-converge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-converge", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/KonghaYao/peri.git --path .claude/skills/auto-converge--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add KonghaYao/peri --skill auto-converge -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install KonghaYao/peri auto-converge --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/KonghaYao/peri.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/auto-converge .gemini/skills/auto-converge && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "auto-converge" agent skill from https://github.com/KonghaYao/peri/tree/main/.claude/skills/auto-converge into .gemini/skills/auto-converge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-converge", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install KonghaYao/peri auto-convergeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add KonghaYao/peri --skill auto-converge -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/KonghaYao/peri.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/auto-converge .github/skills/auto-converge && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "auto-converge" agent skill from https://github.com/KonghaYao/peri/tree/main/.claude/skills/auto-converge into .github/skills/auto-converge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-converge", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add KonghaYao/peri --skill auto-converge -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install KonghaYao/peri auto-converge --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/KonghaYao/peri.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/auto-converge .opencode/skills/auto-converge && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "auto-converge" agent skill from https://github.com/KonghaYao/peri/tree/main/.claude/skills/auto-converge into .opencode/skills/auto-converge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-converge", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
auto-converge- GitHub stars
- 226
- Token cost
- ~856 tokens
- SKILL.md length
- 263 words
- Files
- 1
- Skills in repo
- 19
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
通过外部对标+对抗迭代让规则/技能/SKILL.md 收敛到可执行状态. An agent skill from KonghaYao/peri.
- Works in 2 steps: 外部对标：先研读高质量参考（同类工具的文档、博客、规范），提取差距和缺失项，不闭门… → 对抗收敛：写样例 → subagent 零容忍审查 → 量化违规数 → 修复 →…
- Development work in your project
- SKILL.md covers 适用于什么, 触发条件, 工作流程 and 收敛循环的关键约束, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Auto Converge is an agent skill from KonghaYao/peri. 通过外部对标+对抗迭代让规则/技能/SKILL.md 收敛到可执行状态。 当用户说"打磨这个 skill""收敛规则""这个 skill 写出来不 work，帮我调" "怎么让 agent 严格按规则执行"时触发。 也适用于任何需要把一份规则文档从"写完了但 agent 不遵守" 变成"agent 能稳定执行"的场景。
Its SKILL.md is about 860 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. The repository describes itself as: Lightweight Rust Agent only use 50MB RAM, but Claude Code Plugin compatible, Dynamic Workflow, Goal, Artifacts, Free Web Search, full feature and better support! The licence is Apache-2.0.
When your agent uses it
- Development work in your project
Example prompts
- “打磨这个 skill”
- “这个 skill 写出来不 work，帮我调”
- “怎么让 agent 严格按规则执行”
- “/auto-converge”
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- 外部对标：先研读高质量参考（同类工具的文档、博客、规范），提取差距和缺失项，不闭门造车
- 对抗收敛：写样例 → subagent 零容忍审查 → 量化违规数 → 修复 → 重复直到违规 < 5，规则不是改一次就对的
What it can do on your machine
Read from SKILL.md and the folder at commit d7ee444. 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
Auto Converge loads about 856 tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 263 words of instructions outside code blocks.
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 KonghaYao/peri at commit d7ee444, republished under its Apache-2.0 licence (© KonghaYao). 263 words, ~856 tokens.
Download SKILL.mdSave it as
.claude/skills/auto-converge/SKILL.md (or your agent's skills folder).- name
- auto-converge
- description
- 通过外部对标+对抗迭代让规则/技能/SKILL.md 收敛到可执行状态。 当用户说"打磨这个 skill""收敛规则""这个 skill 写出来不 work，帮我调" "怎么让 agent 严格按规则执行"时触发。 也适用于任何需要把一份规则文档从"写完了但 agent 不遵守" 变成"agent 能稳定执行"的场景。
auto-converge——让规则从写完了变成能执行
两个策略驱动——
- 外部对标：先研读高质量参考（同类工具的文档、博客、规范），提取差距和缺失项，不闭门造车
- 对抗收敛：写样例 → subagent 零容忍审查 → 量化违规数 → 修复 → 重复直到违规 < 5，规则不是改一次就对的
两条策略必须同时执行。只看参考不迭代，规则停留在理论正确但 agent 执行不走；只迭代不看参考，规则在低水平收敛但没有吸收业界最佳实践。
适用于什么
不限于 SKILL.md——任何需要 agent 稳定遵守的规范都可以收敛。常见场景——
| 用户说的 | 实际要收敛的东西 | 样例是什么 |
|---|---|---|
| "这个 prompt 写好了但 agent 返回格式老不对" | prompt 模板 | 一组 agent 的实际输出 |
| "团队的 code review checklist 没人真按那个查" | review 检查清单 | 对同一段代码的审查记录 |
| "想让 agent 写的 API 文档风格统一" | 文档写作规范 | 几篇按规范写的 API 文档 |
| "这个部署检查表每次都有项漏掉" | 部署 checklist | 模拟执行记录 |
| "agent 回复用户的语气不统一" | 回复风格指南 | agent 对话记录 |
| "这个 project README 永远写不规范" | README 模板/规范 | 按模板写的 README |
| "git commit message 格式老不一致" | commit 规范 | 一组 commit message |
| "这个 skill 写出来了但 agent 不遵守" | SKILL.md 规则 | 按 skill 写的输出 |
| "想让 agent 列出来的东西都有这个格式" | 输出格式规范 | 格式化的输出样例 |
核心模式不变——只要你能说明agent 应该遵守什么且有参考源可以学习，auto-converge 就能做。收敛对象可以是 markdown 文件、prompt 字符串、JSON schema、checklist、或者任何有规则的文本文档。
触发条件
- 用户描述了一个规范/规则但 agent 屡次违反
- 用户给了一个文件路径，说"让它能执行""让它变得可验证"
- 用户说"帮我打磨""收敛""这个写出来不 work"
如果用户只说了"agent 做得不好"但没明确规范在哪——先帮他把规范落到文件里，再收敛。收敛的前提是规范有地方写。
工作流程
第 1 步：澄清三个问题
在开始对标之前，必须确认以下三点。不问清楚就动手，收敛方向可能和用户实际需求完全错位——
- 收敛什么东西？——如果有现成文件，拿路径。如果没有，帮用户把规范写下来再收敛。文件格式不限（.md、.json、.txt、prompt 字符串都可以）。
- "agent 遵守"怎么验证？——对 commit 规范来说是生成的 message 是否合规，对 prompt 来说是 agent 的输出是否按格式，对 checklist 来说是检查项是否全部覆盖。这个验证方式决定了样例长什么样。
- 参考源是什么？——没有参考不启动。参考可以是同类项目的文档、官方规范（如 Conventional Commits）、用户认为写得好的范例、或者实际运行中成功的输出记录。外部对标是收敛的方向感来源。
第 2 步：对标差距分析
并行读目标规范和参考源，产出对标差距清单——逐项列出参考有而目标规范缺的东西，按优先级排序。差距清单不追求全面，追求可操作：每条差距必须能在第 3 步转化为一条写前红灯或一条规则补充。
第 3 步：提取写前红灯 checklist
从对标差距清单中提炼 5-10 条写前自检项，作为生成样例前 30 秒扫一眼的红灯。红灯覆盖的不是"好的写法"（那是规则层面的事），而是"写完必然会犯、审查再修、下次还会犯"的机械性违规——对 commit 规范来说是前缀格式/语言/长度，对 prompt 来说是占位符/转义/必填字段。
红灯清单嵌入目标规范的执行流程中，放在"生成输出"之前。写完再查就是抓虫，写之前查是避坑。
第 4 步：对抗收敛循环
每轮——
- 按当前规范生成一组样例——样例形式取决于第 1 步确认的验证方式（commit message、prompt 输出、代码审查记录、README 草稿等等）。数量以 5-10 个为宜，太少测不全，太多审查成本高。
- 派 subagent 审查——独立上下文，prompt 中嵌入目标规范全文（不是摘要），要求零容忍、只报违规、逐条给出位置+原文+规则+建议。审查 subagent 的默认倾向是放水——prompt 里必须写明"宁可误判也不漏判"。
- 量化——统计违规数，按类别分类。
- 决策——
- 违规 < 5 且无系统性类别（某类违规 > 2）→ 收敛，进入第 5 步
- 违规 ≥ 5 或有系统性类别 → 修复样例 + 调整规范（补红灯、强化条款、新增反例），进入下一轮
- 换场景——每轮样例换个场景/主题，避免 agent 从"按规则做"退化为"背答案"。不同场景是对规则泛化能力的压力测试。
收敛判定标准：违规 < 5 且无任何违规类别超过 2 处。连续 2 轮违规数不降反升→回滚上轮规则变更后重新分析（通常是新增规则过于模糊或互相矛盾）。
第 5 步：输出收敛报告
包含——
- 违规收敛曲线（每轮违规数）
- 规范文件变更清单（新增/修改了哪些规则）
- 样例列表（每轮主题+是否通过）
- 残留问题（若未完全收敛则标注原因和建议）
- 红灯 checklist 最终版本
收敛循环的关键约束
审查 subagent 的 prompt 必须嵌入规范全文。 不能用摘要，不能在 prompt 里口头描述规则——subagent 只能对照原文审查，不能用自己对规则的理解替代原文。prompt 中必须包含"零容忍、只报违规"的对抗指令。
样例必须涉及不同场景/主题。 同一场景连写多轮会让 agent 退化为背答案——违规数表面下降，换个场景就反弹。
规则调整必须有针对性。 审查挑出 A 类违规后不要本能地往规范里加一堆 A 类细则——先判断违规是"规则不够细"还是"执行没注意到"。规则细就补规则，执行问题就补红灯。规则膨胀是收敛的敌人。
规范的格式不能成为审查的盲区。 如果目标规范是一段 prompt，审查 subagent 的 prompt 里要包含规范原文 + 对格式的明确检查项（如"输出是否包含必填字段""占位符是否全部替换"）。格式类违规 subagent 有时会忽略，需要显式提醒。
参考案例
| 案例 | 规范类型 | 收敛轮数 | 终局违规 |
|---|---|---|---|
blog-writer SKILL.md | 写作规则（~50 条） | 6 | 3 |
git-commit-style SKILL.md | 格式规范（8 条） | 1 | 1 |
完整记录见对应 git 提交 5757b879。
© KonghaYao, Apache-2.0. 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 .claude/skills/auto-converge of KonghaYao/peri.
Open the folder on GitHubat commit d7ee444
Compare with similar skills
Auto Converge 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Auto Converge this skillKonghaYao/peri | 226 | — | ~856 | Automated safety check: Pass | Apache-2.0 | |
| Vercel Composition Patternssupabase/supabase | 111k | 58 repos | ~726 | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 297k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 25 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 4 repos | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Typescript Advanced Types
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
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.
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
Greploop
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
More from KonghaYao/peri
All 19 skills in this repoLangfuse and LLM Gateway Logs
KonghaYao/peri
Queries Langfuse traces, prompts, datasets and sessions, and analyzes local LLM gateway logs for requests, context growth, token use and cache hits.
Learn From History Audit
KonghaYao/peri
Audits recent agent conversation history and turns repeated failures and successes into testable harness improvement proposals that later audits can check.
SSH Remote Command CLI
KonghaYao/peri
Runs commands, reads and edits files, and copies data on remote machines through a single-file Node script that wraps the system ssh and scp, in Chinese.
Advisor Consultation
KonghaYao/peri
Sends a compact, redacted decision packet to a tool-free Opus advisor subagent when a task has high-risk trade-offs or stalled investigations, then weighs the answer.
Scheduled Tasks Cron
KonghaYao/peri
Registers, lists and removes recurring agent tasks with five-field cron expressions, and sets safety rules so a schedule is created only when the user clearly asks.
Heavy Verify Loop for Peri TUI
KonghaYao/peri
Verifies and repairs a feature by using the real Peri terminal UI as a user would, looping verify, decide, fix and review until a fresh round shows no blockers.
Related
Categories
Questions about Auto Converge
What does Auto Converge do?
通过外部对标+对抗迭代让规则/技能/SKILL.md 收敛到可执行状态. An agent skill from KonghaYao/peri. Auto Converge is an agent skill from KonghaYao/peri.
When should I use Auto Converge?
Auto Converge fits situations like: development work in your project.
How do I install Auto Converge in Claude Code?
Run `npx skills add KonghaYao/peri --skill auto-converge -a claude-code`. Or copy the skill folder (.claude/skills/auto-converge in KonghaYao/peri) into .claude/skills/auto-converge in your project. Claude Code loads it when a task matches its description.
How do I install Auto Converge in Codex?
Run `npx skills add KonghaYao/peri --skill auto-converge -a codex`. Or copy the skill folder (.claude/skills/auto-converge in KonghaYao/peri) into .agents/skills/auto-converge in your project. Codex loads it when a task matches its description.
Can I use Auto Converge 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 KonghaYao/peri --skill auto-converge -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/auto-converge, .gemini/skills/auto-converge, .github/skills/auto-converge and .opencode/skills/auto-converge in your project.
What does Auto Converge need to run?
SKILL.md names no scripts, command-line tools or credentials: Auto Converge is instructions for the agent only.
Does Auto Converge 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 Auto Converge 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 Auto Converge use?
Auto Converge is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Auto Converge use?
About 856 tokens (SKILL.md is roughly 3.4k 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 Auto Converge?
Skills that share tags, products or a category with Auto Converge: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Auto Converge?
KonghaYao (a GitHub user) maintains it in KonghaYao/peri, which has 226 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 10, 2026.
Source: KonghaYao/peri on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.