数据布局
Review the “数据布局” section in the pinned source before continuing.
affaan-m/ECC
Use it for engineering tasks; the detail page covers purpose, installation, and practical steps.
npx skills add https://github.com/affaan-m/ECC --skill "docs/zh-CN/skills/ck"Source checked Jul 28, 2026·Refresh due Oct 26, 2026
Reorganized from the pinned upstream SKILL.md
你是上下文管家助手。当用户调用任何 /ck: 命令时, 运行相应的 Node.js 脚本,并将其标准输出原样呈现给用户。 脚本位于:/.claude/skills/ck/commands/(使用 $HOME 展开 )。
npx skills add https://github.com/affaan-m/ECC --skill "docs/zh-CN/skills/ck"The pinned source supports a structured brief, but not an expanded tutorial. Only detected inputs, outputs, and sections are shown.
252 source words · 11 usable sections
Documentation workflow
Sections are extracted automatically from the pinned SKILL.md and link back to the source.
Review the “数据布局” section in the pinned source before continuing.
脚本输出包含自动检测信息的 JSON。将其作为确认草稿呈现:
脚本输出包含自动检测信息的 JSON。将其作为确认草稿呈现:
这是唯一需要 LLM 分析的命令。 分析当前对话:
Documentation checklist
The source section “数据布局” has been checked.
The source section “命令” has been checked.
The source section “/ck:init — 注册项目” has been checked.
The source section “/ck:save — 保存会话状态” has been checked.
Static permission evidence
These are source excerpts matched by deterministic rules, not findings of malicious behavior, safety, or actual execution.
SKILL.md · L26
node "$HOME/.claude/skills/ck/commands/init.mjs"The documentation asks the agent to run terminal commands or scripts.
SKILL.md · L77
node "$HOME/.claude/skills/ck/commands/resume.mjs" [arg]The documentation asks the agent to run terminal commands or scripts.
Choose a different workflow
Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions.
A separate implementation from affaan-m/ECC; compare its source, maintenance signals, and permission requirements.
Open source detailUse it for engineering tasks; the detail page covers purpose, installation, and practical steps.
A separate implementation from affaan-m/ECC; compare its source, maintenance signals, and permission requirements.
Open source detailAudit skill SKILL.md files for compliance with the agentskills.io specification and house conventions. Checks frontmatter fields (name, description, compatibility, metadata, argument-hint), metadata sub-fields (author, scope, layer, confirms), and layer/suffix consistency. Use when adding new skills, reviewing skill quality, or ensuring all skills follow the spec. Triggers: "audit skills", "check skill spec", "skill compliance", "are my skills up to spec", "/claude-skill-spec-audit".
A separate implementation from jackchuka/skills; compare its source, maintenance signals, and permission requirements.
Open source detailFAQ
你是上下文管家助手。当用户调用任何 /ck: 命令时, 运行相应的 Node.js 脚本,并将其标准输出原样呈现给用户。 脚本位于:/.claude/skills/ck/commands/(使用 $HOME 展开 )。
The source record exposes this install command: npx skills add https://github.com/affaan-m/ECC --skill "docs/zh-CN/skills/ck". Inspect the command and pinned source before running it.
The pinned source record declares support for: claude code.
Static rules flagged exec-script in the source; the page lists the matching lines and excerpts.
Quality breakdown
Based on traceable docs and repository signals; stars are not treated as quality.
Compare before choosing
These links are selected from shared tasks, functions, stacks, platforms, and same-name variants. Compare the source owner, documentation, permissions, and maintenance signals.
Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions.
Use it for engineering tasks; the detail page covers purpose, installation, and practical steps.
Audit skill SKILL.md files for compliance with the agentskills.io specification and house conventions. Checks frontmatter fields (name, description, compatibility, metadata, argument-hint), metadata sub-fields (author, scope, layer, confirms), and layer/suffix consistency. Use when adding new skills, reviewing skill quality, or ensuring all skills follow the spec. Triggers: "audit skills", "check skill spec", "skill compliance", "are my skills up to spec", "/claude-skill-spec-audit".
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
GAN-inspired Generator-Evaluator agent harness for building high-quality applications autonomously. Based on Anthropic's March 2026 harness design paper.
你是上下文管家助手。当用户调用任何 /ck:* 命令时,
运行相应的 Node.js 脚本,并将其标准输出原样呈现给用户。
脚本位于:~/.claude/skills/ck/commands/(使用 $HOME 展开 ~)。
~/.claude/ck/
├── projects.json ← 路径 → {名称, 上下文目录, 最后更新时间}
└── contexts/<名称>/
├── context.json ← 真实来源(结构化 JSON,v2 版本)
└── CONTEXT.md ← 自动生成的视图 — 请勿手动编辑
/ck:init — 注册项目node "$HOME/.claude/skills/ck/commands/init.mjs"
脚本输出包含自动检测信息的 JSON。将其作为确认草稿呈现:
以下是我找到的内容——请确认或修改:
项目: <name>
描述: <description>
技术栈: <stack>
目标: <goal>
禁止项: <constraints 或 "None">
仓库: <repo 或 "none">
等待用户批准。应用任何编辑。然后将确认后的 JSON 通过管道传递给 save.mjs --init:
echo '<confirmed-json>' | node "$HOME/.claude/skills/ck/commands/save.mjs" --init
确认后的 JSON 模式:{"name":"...","path":"...","description":"...","stack":["..."],"goal":"...","constraints":["..."],"repo":"..." }
/ck:save — 保存会话状态这是唯一需要 LLM 分析的命令。 分析当前对话:
summary:一句话,最多 10 个词,描述已完成的内容leftOff:当前正在积极处理的内容(具体文件/功能/错误)nextSteps:有序的具体后续步骤数组decisions:本次会话所做决策的 {what, why} 数组blockers:当前阻塞项数组(若无则为空数组)goal:仅当本次会话中目标发生更改时才包含更新后的目标字符串,否则省略向用户显示摘要草稿:"Session: '<summary>' — save this? (yes / edit)"
等待确认。然后通过管道传递给 save.mjs:
echo '<json>' | node "$HOME/.claude/skills/ck/commands/save.mjs"
JSON 模式(精确):{"summary":"...","leftOff":"...","nextSteps":["..."],"decisions":[{"what":"...","why":"..."}],"blockers":["..."]}
逐字显示脚本的标准输出确认信息。
/ck:resume [name|number] — 完整简报node "$HOME/.claude/skills/ck/commands/resume.mjs" [arg]
逐字显示输出。然后询问:"从这里继续?还是有什么变化?"
如果用户报告有变化 → 立即运行 /ck:save。
/ck:info [name|number] — 快速快照node "$HOME/.claude/skills/ck/commands/info.mjs" [arg]
逐字显示输出。无需后续提问。
/ck:list — 项目组合视图node "$HOME/.claude/skills/ck/commands/list.mjs"
逐字显示输出。如果用户回复数字或名称 → 运行 /ck:resume。
/ck:forget [name|number] — 移除项目首先解析项目名称(如有需要运行 /ck:list)。
询问:"This will permanently delete context for '<name>'. Are you sure? (yes/no)"
如果是:
node "$HOME/.claude/skills/ck/commands/forget.mjs" [name]
逐字显示确认信息。
/ck:migrate — 将 v1 数据转换为 v2node "$HOME/.claude/skills/ck/commands/migrate.mjs"
首先进行试运行:
node "$HOME/.claude/skills/ck/commands/migrate.mjs" --dry-run
逐字显示输出。将所有 v1 的 CONTEXT.md + meta.json 文件迁移为 v2 的 context.json。
原始文件备份为 meta.json.v1-backup — 不会删除任何内容。
位于 ~/.claude/skills/ck/hooks/session-start.mjs 的钩子必须在
~/.claude/settings.json 中注册,以便在会话启动时自动加载项目上下文:
{
"hooks": {
"SessionStart": [
{ "hooks": [{ "type": "command", "command": "node \"~/.claude/skills/ck/hooks/session-start.mjs\"" }] }
]
}
}
该钩子每次会话注入约 100 个 token(紧凑的 5 行摘要)。它还会检测 未保存的会话、自上次保存以来的 git 活动,以及与 CLAUDE.md 的目标不匹配。
~ 展开为 $HOME。/CK:SAVE、/ck:save、/Ck:Save 均有效。context.json 或 CONTEXT.md — 始终使用脚本。projects.json 格式错误,请告知用户并提供重置为 {} 的选项。