Agent skill

Repomind Summary

by HobbyBear in HobbyBear/tinydocker

每次 AI 完成代码修改、问答或排查结论后,且最终答复前,必须同步做轻量 summary gate 判断;代码写完后也要自动进入 gate。只有发现可复用的新业务知识、用户纠错、手动要求记忆的经验、模块边界、排查经验或知识文档元数据变化时,才执行写入。按类型更新 concepts、modules、troubles 及每个文档自己的 name/description,避免回到集中式索引。

No licenceAuto-check passed

Install Repomind Summary

skills CLI
$ npx skills add HobbyBear/tinydocker --skill repomind-summary -a claude-code

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

GitHub CLI
$ gh skill install HobbyBear/tinydocker repomind-summary --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/HobbyBear/tinydocker.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/repomind-summary .claude/skills/repomind-summary && 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
repomind-summary
GitHub stars
165
Token cost
~1.6k tokens
SKILL.md length
346 words
Files
2
Skills in repo
4
Repo updated
First seen
Licence
None found

At a glance

每次 AI 完成代码修改、问答或排查结论后,且最终答复前,必须同步做轻量 summary gate 判断;代码写完后也要自动进入 gate。只有发现可复用的新业务知识、用户纠错、手动要求记忆的经验、模块边界、排查经验或知识文档元数据变化时,才执行写入。按类型更新 concepts、modules、troubles 及每个文档自己的 name/description,避免回到集中式索引。

  • Works in 6 steps: 先做 summary gate,只有值得沉淀才写文件。 → RepoMind 不再维护 index.json;路由元数据写在各知识文档自己的… → 每次进入 summary,都要优先检查索引元数据;description… → …
  • SKILL.md covers 核心原则, 步骤 0:先修正旧格式, 步骤 1:执行 summary gate and 步骤 2:读取待处理发现, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Repomind Summary is an agent skill from HobbyBear/tinydocker. 每次 AI 完成代码修改、问答或排查结论后,且最终答复前,必须同步做轻量 summary gate 判断;代码写完后也要自动进入 gate。只有发现可复用的新业务知识、用户纠错、手动要求记忆的经验、模块边界、排查经验或知识文档元数据变化时,才执行写入。按类型更新 concepts、modules、troubles 及每个文档自己的 name/description,避免回到集中式索引。

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

The repository describes itself as: 🐑 🐑 🐑 本系列教程主要是为了弄清楚容器化的原理,纸上得来终觉浅,绝知此事要躬行,理论始终不及动手实践来的深刻,所以这个系列会用go语言实现一个类似docker的容器化功能,最终能够容器化的运行一个进程。

Example prompts

  • “/repomind-summary”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. 先做 summary gate,只有值得沉淀才写文件。
  2. RepoMind 不再维护 index.json;路由元数据写在各知识文档自己的 frontmatter。
  3. 每次进入 summary,都要优先检查索引元数据;description 是首要检索摘要,modules 的 keywords 是辅助定位词。
  4. 只记录“代码不会直接告诉你的东西”。
  5. 用户纠正业务事实、模块归属、入口位置、排查根因或历史结论时,视为用户确认的修订证据,必须进入完整 summary 流程。
  6. 用户明确要求“记一下 / 总结到知识库 / 以后遇到这个要注意 / 这个经验要沉淀”时,视为手动沉淀请求,必须进入完整 summary 流程。

What it can do on your machine

Read from SKILL.md and the folder at commit 5de1c18. 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 (its code samples are bash and markdown).

    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

Repomind Summary loads about 1.6k tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 346 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 346 words (~1,626 tokens).

name
repomind-summary
metadata.short-description
把可复用知识写回 RepoMind

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in .codex/skills/repomind-summary of HobbyBear/tinydocker.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 5de1c18

Compare with similar skills

Repomind Summary 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.

Repomind Summary compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Repomind Summary this skillHobbyBear/tinydocker165—~1.6kAutomated safety check: PassNone
Gate Testsvercel/next.js143k—~2.7kAutomated safety check: PassMIT
Gateplugin87/ux-ui-agent-skills1.5k—~532Automated safety check: PassMIT
Brain Ingest Gategarrytan/gbrain31k—~3.9kAutomated safety check: PassMIT
Delivery Gateaffaan-m/ECC275k—~1.3kAutomated safety check: PassMIT
Skill Release Gaterohitg00/ai-engineering-from-scratch66k—~1kAutomated safety check: PassMIT

Similar skills

  • Gate Tests

    vercel/next.js

    Official

    How to use the @gate / @force-gate test directives instead of it.skip or fake-green skip patterns.

    143k GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Gate

    plugin87/ux-ui-agent-skills

    Run the one-command quality gate and report the real N/N result.

    1.5k GitHub stars~532 tokensUpdated today
    Frontend & DesignAuto-check passed
  • Brain Ingest Gate

    garrytan/gbrain

    Pre-write quality gate for content entering the brain. An agent skill from garrytan/gbrain.

    31k GitHub stars~3.9k tokensUpdated today
    Testing & QAAuto-check passed
  • Delivery Gate

    affaan-m/ECC

    Stop hook that blocks Claude from finishing until quality checks pass.

    275k GitHub stars~1.3k tokensUpdated 3 days ago
    Auto-check passed
  • Skill Release Gate

    rohitg00/ai-engineering-from-scratch

    Evaluates an Agent Skill bundle before release for structure, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity and host portability.

    66k GitHub stars~1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Speak Summary

    github/awesome-copilot

    Official

    Convert text, markdown, or a summary produced by another skill into a listenable MP3 using local CPU-only neural text-to-speech.

    40k GitHub stars~1.6k tokensUpdated today
    Media & CreativeAuto-check passed

More from HobbyBear/tinydocker

  • Repomind Init

    HobbyBear/tinydocker

    初始化 RepoMind 业务知识库。全量重建 graphify 图谱,保守生成高置信 concepts/modules 文档,并为每个知识文件写入 name/description 元数据。执行前会自动修正旧格式;初始化结束后会询问是否继续导入 PRD 业务知识。

    165 GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check passed
  • Repomind Prd

    HobbyBear/tinydocker

    同步历史 PRD/需求文档。先修正旧知识文件格式,再从 PRD 中提取业务概念,对照当前代码确认实际实现,合并更新 .repomind/concepts/ 的业务卡片与元数据;必要时再交给 repomind-summary 补充模块侧知识。

    165 GitHub stars~757 tokensUpdated 3 mo ago
    Auto-check passed
  • Repomind Query

    HobbyBear/tinydocker

    查阅业务逻辑、定位代码、排查问题,需求分析,方案设计时优先自动触发。先用每个 knowledge 文档的 name/description 元数据做 skill-style 路由,再按需打开 concepts、modules、troubles 和最小代码证据;代码定位优先使用模块文档入口和平台代码搜索小上下文,只有调用链、影响面或跨模块关系不足时才补查 graphify…

    165 GitHub stars~1.9k tokensUpdated 3 mo ago
    Auto-check passed

Questions about Repomind Summary

What does Repomind Summary do?

每次 AI 完成代码修改、问答或排查结论后,且最终答复前,必须同步做轻量 summary gate 判断;代码写完后也要自动进入 gate。只有发现可复用的新业务知识、用户纠错、手动要求记忆的经验、模块边界、排查经验或知识文档元数据变化时,才执行写入。按类型更新 concepts、modules、troubles 及每个文档自己的 name/description,避免回到集中式索引。. Repomind Summary is an agent skill from HobbyBear/tinydocker.

How do I install Repomind Summary in Claude Code?

Run `npx skills add HobbyBear/tinydocker --skill repomind-summary -a claude-code`. Or copy the skill folder (.codex/skills/repomind-summary in HobbyBear/tinydocker) into .claude/skills/repomind-summary in your project. Claude Code loads it when a task matches its description.

How do I install Repomind Summary in Codex?

Run `npx skills add HobbyBear/tinydocker --skill repomind-summary -a codex`. Or copy the skill folder (.codex/skills/repomind-summary in HobbyBear/tinydocker) into .agents/skills/repomind-summary in your project. Codex loads it when a task matches its description.

Can I use Repomind Summary 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 HobbyBear/tinydocker --skill repomind-summary -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/repomind-summary, .gemini/skills/repomind-summary, .github/skills/repomind-summary and .opencode/skills/repomind-summary in your project.

What does Repomind Summary need to run?

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

Does Repomind Summary 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 Repomind Summary 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 Repomind Summary use?

No licence was found for Repomind Summary or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Repomind Summary use?

About 1.6k tokens (SKILL.md is roughly 6.5k 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 Repomind Summary?

Skills that share tags, products or a category with Repomind Summary: Gate Tests (vercel/next.js, 143k stars), Gate (plugin87/ux-ui-agent-skills, 1.5k stars), Brain Ingest Gate (garrytan/gbrain, 31k stars) and Delivery Gate (affaan-m/ECC, 275k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Repomind Summary?

HobbyBear (a GitHub user) maintains it in HobbyBear/tinydocker, which has 165 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on July 6, 2026.

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