← Back to Skills Marketplace
moroiser

Skill Manager All In One

by Morois · GitHub ↗ · v4.4.5 · MIT-0
cross-platform ✓ Security Clean
1172
Downloads
0
Stars
11
Active Installs
32
Versions
Install in OpenClaw
/install skill-manager-all-in-one
Description
一站式管理 OpenClaw 技能的创建、修改、发布、更新、升版与审计(技能管理、升版)。 Manage OpenClaw skills: create, modify, publish, update, upgrade, audit.
Usage Guidance
This instruction-only skill appears coherent and is designed to audit and publish skills; before using it, be aware: (1) it will inspect files under your OpenClaw workspace (~/.openclaw/workspace/skills/ and related paths) during its internal verification step — ensure you are comfortable with that file access; (2) publishing steps (clawhub publish, git push, gh release create) will use whatever CLI credentials are present on the machine—verify your GitHub/ClawHub/gh authentication and tokens first; (3) the skill correctly enforces a two-step confirmation before executing publish/delete commands, so never approve actions you haven't reviewed; (4) when the tool asks you to inspect scripts for injection risks, treat that as a genuine manual security check — review any included scripts for os.system/subprocess shell=True/exec/eval and secrets; (5) keep backups of important skill directories and ensure large model files are placed in the recommended cache locations. If you want a stricter posture, require the agent to only produce the publish commands for you to run manually rather than letting it execute them after confirmation.
Capability Analysis
Type: OpenClaw Skill Name: skill-manager-all-in-one Version: 4.4.5 The 'Skill Manager All In One' bundle is a comprehensive framework designed to guide an AI agent through the lifecycle of creating, auditing, and publishing other OpenClaw skills. It contains no executable code but provides highly structured instructions (SKILL.md) and reference guides that prioritize security and safety. Key features include mandatory security checklists (G01-G06) that explicitly warn against shell injection, path injection, and credential leaks, as well as a strict 'two-step verification' protocol requiring explicit user confirmation before any publishing or promotion actions (references/clawhub-publish.md, references/promotion.md).
Capability Assessment
Purpose & Capability
Name/description match the content: SKILL.md is a full workflow for creating, reviewing, publishing, and auditing OpenClaw skills. Referenced tools and actions (clawhub, git, gh, local workspace, model cache) are expected for a skill-management tool and nothing unrelated is requested in metadata (no odd env vars, no unrelated binaries).
Instruction Scope
Instructions are specific and scoped to skill-authoring tasks: creating directories under ~/.openclaw/workspace, editing SKILL.md, running clawhub/git/gh commands, doing two-step verification before publishing, and manually inspecting scripts for injection risks. Note: the workflow requires the agent to read local skill files and scripts during the internal (non-output) verification step — this is appropriate for auditing/publishing but means the agent will access your workspace files. The skill explicitly requires explicit user confirmation before destructive or publish actions, which reduces risk.
Install Mechanism
No install spec and no code files to execute—this is instruction-only, the lowest-risk install mechanism. Nothing is downloaded or written by an installer.
Credentials
The skill declares no required env vars or credentials, which is consistent with being an instruction-only guide. However, many of the runtime commands it instructs (clawhub publish, git push, gh release create, clawhub login) will need the user's existing CLI auth and potentially remote tokens; those are not added or requested by the skill itself. This is proportionate but you should be aware the agent will rely on credentials already present in your environment when performing publish actions.
Persistence & Privilege
always:false and default model invocation allowed. The skill does not request permanent/always-on privilege nor attempts to modify other skills' configs. It requires user confirmation before publishing or destructive operations, limiting autonomous destructive action.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install skill-manager-all-in-one
  3. After installation, invoke the skill by name or use /skill-manager-all-in-one
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v4.4.5
1. Major restructure based on D老师 consultation. (1) Mode selector: create/modify/audit/local-test. (2) Phase 1 step 1 has platform/version; Display name/slug moved to Phase 2 step 1. (3) General baseline G01~G06. (4) ClawHub specific CH01~CH09. (5) CH01=Display Name (EN|CN on ClawHub page title bar), CH02=Skill slug (lowercase+hyphens, in directory/publish command). (6) Report template: ID + description for every item. (7) Two-step verification: AI-internal vs user-facing separation. (8) Error recovery: user reject → Phase 1 increment version. (9) All chapter cross-references fixed. (10) Trigger keywords in description (120 chars). (11) 'read which reference' embedded inline in Phase 2 and Phase 3. (12) github-publish.md fully rewritten, aligned with SKILL.md. (13) Fix: clawhub unpublish → clawhub delete. (14) All reference files aligned with consistent 两步验证 headers. 重构SKILL.md:模式选择;Phase 1通用项,Display name/slug移至Phase 2;通用基线G01~G06;ClawHub专项CH01~CH09;CH01/CH02明确描述;汇报模板ID+文字;两步验证动作边界;错误恢复;章节引用修复;触发词融入description;'何时读reference'嵌入Phase 2和Phase 3;github-publish.md完全重写对齐;修复错误命令clawhub unpublish;所有分文件两步验证格式对齐。 2. Fix displayName: set name: field to bilingual 'Skill Manager All In One | 一站式技能管理器'. 修复displayName:name字段改为双语。
v4.4.4
Strengthen two-step verification: explicitly cover all publish-type operations (clawhub publish / git push / gh release create / promotion posts) under mandatory verification. 强化两步验证:明确两步验证适用于所有发布类操作。Add security scan reminder in Phase 3: must click Details ▾ to verify Assessment after publishing. 发布后补充安全扫描确认提示。Fix CLI command example: remove misleading --slug --name from publish command example. 修复发布命令示例。Add warnings in github-publish.md and promotion.md. 补充安全警告。Add Display name to report template: must report both Display name and slug in Phase 2 report. 发布清单补充Display name汇报要求。
v4.4.3
1. Add GitHub Release guide to github-publish.md. Includes two-step verification, Release Notes standards, and gh release create command. 新增 GitHub Release 指南,包含两步验证、Release Notes 规范和 gh release create 命令。 2. Add Release Notes to GitHub publishing checklist. Platform-specific checklist now includes Release Notes standards. GitHub 上传清单新增 Release Notes 规范。 3. Add 'create GitHub Release' to operations index. 操作索引新增'创建 GitHub Release'。 4. Minor fixes and clarification to SKILL.md index structure. SKILL.md 索引结构微调。
v4.4.2
1. Restructure SKILL.md into a lightweight index. Refactor platform-specific publishing guides into separate reference files for better maintainability. 重构 SKILL.md 为精简索引,将平台专项发布指南解耦为独立 reference 文件。 2. Add GitHub as a new publishing platform alongside ClawHub. New principle: two-step verification for all uploads. 新增 GitHub 发布平台,与 ClawHub 并列。确立所有上传操作的两步验证原则。 3. Add one-by-one confirmation principle. Sequential processing and confirmation for multiple files/versions to prevent AI hallucinations and omissions. 新增逐个修改、逐个确认原则,防止批量操作导致的遗漏和 AI 幻觉。
v4.4.1
1. Add complete system_dependencies declaration to _meta.json (clawhub, clawflows, git, find, du, bash). 修复元数据,声明所需系统依赖工具。 2. Add workspace_paths and comprehensive security_notes to _meta.json. 完善元数据工作区路径和安全说明。 3. Address ClawHub security scan warnings: clarify required binaries are not bundled but expected to be pre-installed. 响应安全扫描警告,明确所需工具需预装而非打包。
v4.4.0
1. Restructure entire SKILL.md with three-phase lifecycle (Phase 1: Create/Modify, Phase 2: Pre-publish Verification, Phase 3: Post-publish Maintenance). 重构完整生命周期流程。 2. Separate general verification (de-identification, skill security, logical soundness, language rules, naming rules, changelog rules) from platform-specific checks (ClawHub size limits, symlink, artifacts). 分离通用规范与平台专项规范。 3. Expand directory system with workspace resources directory for large files/models. 扩展目录体系,增设工作区资源目录。 4. Add eight core rules including publish-then-verify and no-batch-operations. 新增八条核心原则。 5. Add operations index for quick lookup. 新增操作索引。
v4.3.0
1. Expand Code Security checklist with 3 new items: metadata consistency (inspect vs actual), prefer subprocess over os.system even for hardcoded strings, and dependency completeness. 扩充代码安全性检查清单,新增三条:元数据一致性、避免 os.system、依赖完整性。
v4.2.0
1. Add code security verification to pre-publish checklist: check for shell injection (os.system/shell=True/eval), Python code injection (exec/eval/python3 -c with string interpolation), path injection, secrets in output, and incomplete dependencies. 新增代码安全性验证至发布前检查清单:检查 Shell 注入、Python 代码注入、路径注入、日志输出泄露、依赖完整性。\n2. Fix title: add "All In One" to SKILL.md heading. 修复标题,SKILL.md 正文标题补全 "All In One"。
v4.1.0
1. Add file responsibility matrix to SKILL.md and expand promotion.md with two-step verification, AI psychology checklist, Moltbook bilingual format rules, and data freshness requirements. 新增主文件/分文件职责分工矩阵至 SKILL.md;扩充 promotion.md,加入两步推广验证、AI心理学检查清单、Moltbook双语交替格式规范与数据时效要求。
v4.0.0
1. Add pre-publish checklist covering language order, de-identification, scientificity, AI readability, contextual coherence, stability, and efficiency. 新增发布前检查清单,覆盖语言顺序、去标识化、科学性、AI易读性、上下文连贯性、稳定性与高效性。\n2. Add two-step publishing workflow with mandatory user confirmation between report and upload. 新增两步发布工作流,汇报与上传之间设用户确认环节。\n3. Consolidate naming/writing standards, changelog rules, and reporting format into SKILL.md body for centralized guidance. 整合命名写作规范、changelog规则与汇报格式至SKILL.md正文,统一执行标准。
v3.1.0
Version 3.1.0 - Expanded scope to manage both OpenClaw skills and ClawFlows workflows. - Updated description and body to reflect workflow (ClawFlows) creation, testing, and submission processes. - Added detailed guidance for ClawFlows workflow lifecycle, including development, testing, and PR submission to the registry. - Included reference to new documentation file: `references/clawflows-workflow.md`. - Enhanced bilingual instructions and examples throughout documentation.
v3.0.7
Add mandatory pre-publish version check and full content report workflow. Add skill-creator as authoritative reference. 完善发布前检查流程,新增发布前必须查询 ClawHub 已发布版本并向用户汇报完整信息的强制步骤,同时引用 skill-creator 作为技能创建的权威参考来源。
v3.0.6
Refine the skill into a cleaner bilingual guidance system for creating and managing OpenClaw skills. 将本技能整理为更清晰的双语指导系统,用于制作与管理 OpenClaw 技能。 Improve progressive disclosure by keeping core rules in SKILL.md and moving operational details into focused references. 优化渐进式披露结构,将核心规则保留在 SKILL.md,并将操作细节拆分到更聚焦的 references 中。 Strengthen publishing standards for names, descriptions, changelogs, and promotion copy with clearer public-facing quality rules. 强化名称、描述、changelog 与宣传文案的发布标准,明确面向公开页面的质量要求。 Update guidance to reflect current ClawHub CLI behavior, including newer commands, inspect options, and tool-selection checks. 更新指导内容以匹配当前 ClawHub CLI 行为,补充较新的命令、inspect 参数与工具选择前检查。
v3.0.5
Refined ClawHub workflows, CLI guidance, and safer publishing notes. 优化 ClawHub 工作流、CLI 指南与更安全的发布说明。
v3.0.4
Removed heartbeat-related content (belongs to other skills). Added strong emphasis: MUST get user consent before ANY operation, especially publish/update/promote. 删除心跳相关内容(属于其他技能)。强调查:任何操作前必须获得用户同意,特别是发布/更新/宣传。
v3.0.3
Updated promotion template: skill link and install command on separate lines, added attractive description tips, added post-publish logging to memory. 更新宣传模版:技能链接和安装命令单独一行、新增描述优化技巧、新增发布后记忆记录。
v3.0.2
Optimized triggers for higher sensitivity: added more keywords for ClawHub, skill management, publish, audit, promote. 优化激活词提高灵敏度:增加 ClawHub、技能管理、发布、审计、宣传等关键词。
v3.0.1
Added pre-publish privacy check: check each skill for leaked personal sensitive info before promoting. 新增发布前隐私检查:宣传前逐一检查技能是否泄露个人敏感信息。
v3.0.0
Major restructure: modular references (terminology, search-audit, create-publish-update, dashboard-promote), added browser tool for viewing skills, added promotion template for published skills. 重大重构:模块化 references 结构,新增 browser 工具查看技能,新增已发布技能宣传模版。
v1.0.3
Reorganized into modular references structure: terminology, search-audit, create-publish-update, dashboard. Added browser tool method for viewing published skills. 重构为模块化 references 结构:术语、搜索审计、创建发布更新、仪表板。新增 browser 工具查看已发布技能方法。
Metadata
Slug skill-manager-all-in-one
Version 4.4.5
License MIT-0
All-time Installs 11
Active Installs 11
Total Versions 32
Frequently Asked Questions

What is Skill Manager All In One?

一站式管理 OpenClaw 技能的创建、修改、发布、更新、升版与审计(技能管理、升版)。 Manage OpenClaw skills: create, modify, publish, update, upgrade, audit. It is an AI Agent Skill for Claude Code / OpenClaw, with 1172 downloads so far.

How do I install Skill Manager All In One?

Run "/install skill-manager-all-in-one" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Skill Manager All In One free?

Yes, Skill Manager All In One is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Skill Manager All In One support?

Skill Manager All In One is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Skill Manager All In One?

It is built and maintained by Morois (@moroiser); the current version is v4.4.5.

💬 Comments