DevOps Pipeline Management
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
在 OpenClaw 平台执行网页自动 QA 测试(自动操作 + 采证 + 报告 + 修复提示包)。当用户要求做自动化回归、演示级测试、失败证据归档或生成可直接交给下一窗口的修复 Prompt 时使用。
$ npx skills add LeoYeAI/openclaw-master-skills --skill auto-qa -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills auto-qa --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/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/auto-qa .claude/skills/auto-qa && 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-qa" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/auto-qa into .claude/skills/auto-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-qa", 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/LeoYeAI/openclaw-master-skills/tree/main/skills/auto-qaType 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 LeoYeAI/openclaw-master-skills --skill auto-qa -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills auto-qa --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/auto-qa .agents/skills/auto-qa && 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-qa" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/auto-qa into .agents/skills/auto-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-qa", 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 LeoYeAI/openclaw-master-skills --skill auto-qa -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills auto-qa --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/auto-qa .cursor/skills/auto-qa && 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-qa" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/auto-qa into .cursor/skills/auto-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-qa", 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/LeoYeAI/openclaw-master-skills.git --path skills/auto-qa--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 LeoYeAI/openclaw-master-skills --skill auto-qa -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills auto-qa --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/auto-qa .gemini/skills/auto-qa && 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-qa" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/auto-qa into .gemini/skills/auto-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-qa", 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 LeoYeAI/openclaw-master-skills auto-qaInstalls 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 LeoYeAI/openclaw-master-skills --skill auto-qa -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/auto-qa .github/skills/auto-qa && 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-qa" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/auto-qa into .github/skills/auto-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-qa", 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 LeoYeAI/openclaw-master-skills --skill auto-qa -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills auto-qa --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/auto-qa .opencode/skills/auto-qa && 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-qa" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/auto-qa into .opencode/skills/auto-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-qa", 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.
auto-qa在 OpenClaw 平台执行网页自动 QA 测试(自动操作 + 采证 + 报告 + 修复提示包)。当用户要求做自动化回归、演示级测试、失败证据归档或生成可直接交给下一窗口的修复 Prompt 时使用。
Auto QA is an agent skill from LeoYeAI/openclaw-master-skills. 在 OpenClaw 平台执行网页自动 QA 测试(自动操作 + 采证 + 报告 + 修复提示包)。当用户要求做自动化回归、演示级测试、失败证据归档或生成可直接交给下一窗口的修复 Prompt 时使用。
Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts and reference files (for example `_meta.json`, `references/state_snapshot_20260220.md` and `scenarios/generic_visual_template.json`).
The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
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.
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3pnpmFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
wehub.usFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Auto QA loads about 3k tokens when it runs, and up to ~5.3k if it reads all its reference files. Until then it costs about 27 tokens; SKILL.md has 622 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.
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); the scripts in this folder are not scanned.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 622 words, ~3,022 tokens.
.claude/skills/auto-qa/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.用于一期 MVP:
场景定义组件demo/scenarios/*.json执行编排器src/skills/auto-qa/scripts/run_autoqa.pyopenclaw browser 执行动作。浏览器执行器(OpenClaw 内置能力)openclaw browser ...证据归档组件demo/artifacts/run-<run_id>/报告生成组件demo/reports/run-<run_id>/report.json、demo/reports/run-<run_id>/report.html修复任务包生成组件demo/reports/run-<run_id>/fix_plan.json、next_window_prompt.md、standby_prompt.txt稳定性增强组件src/skills/auto-qa/scripts/run_autoqa.py门禁断言组件src/skills/auto-qa/scripts/run_autoqa.pyerror -> 违规(critical)4xx -> 违规(critical)5xx -> 违规(blocker)gateViolationsgateViolationCountsBySeverityriskLevelreleaseDecision(GO / CONDITIONAL_GO / NO_GO)reviewStatus(consistent / needs_inspection)reviewConclusion(复核一致 / 复核需进一步检验)reviewFindings(需进一步检验时的具体项)Trace 对齐组件demo/reports/run-<run_id>/step_trace_map.json报告通知组件src/skills/auto-qa/scripts/run_autoqa.py(运行参数触发)report.html 全页图并发送到聊天频道。--notify-channel 时触发。--notify-target 时,自动从 openclaw status --json 最近会话推断目标(当前频道优先)。screenshot + console + network + tracereport.jsonreport.htmlfix_plan.jsonnext_window_prompt.mdstandby_prompt.txtdemo/
scenarios/
mvp_smoke.json
_generated/ ← agent 智能生成的临时 scenario 存放目录
artifacts/
run-<run_id>/
steps.json
console.json
network.json
health_checks.json
trace.zip
screenshots/
reports/
run-<run_id>/
report.json
report.html
report_full.png
step_trace_map.json
fix_plan.json
next_window_prompt.md
standby_prompt.txt{
"name": "MVP Smoke",
"autoScreenshot": true,
"continueOnFailure": false,
"steps": [
{ "id": "step-001", "action": "open", "url": "https://example.com", "expected": "页面可访问" },
{ "id": "step-002", "action": "wait", "text": "Example Domain", "expected": "标题出现" },
{
"id": "step-003",
"action": "assert_text_contains",
"value": "Example Domain",
"expected": "正文包含关键字"
}
]
}{
"name": "WeHub Smoke",
"gates": {
"enabled": true,
"minPassRate": 95,
"console": {
"errorAsFailure": true,
"ignoreMessagePatterns": ["known harmless error"]
},
"network": {
"sameOrigin4xxAsFailure": true,
"sameOrigin5xxAsFailure": true,
"thirdParty5xxAsFailure": false,
"ignoreUrlPatterns": ["/favicon.ico"],
"ignoreStatusCodes": [401]
}
},
"steps": []
}{
"name": "Visual Demo",
"visual": {
"enabled": true,
"focusTabBeforeStep": true,
"preActionWaitMs": 220,
"postActionWaitMs": 420,
"highlightBeforeClick": true,
"highlightBeforeType": true,
"highlightWaitMs": 480
},
"steps": []
}说明:
focusTabBeforeStep:每步前尽量聚焦受控 tab,减少后台节流导致的观感抖动。preActionWaitMs/postActionWaitMs:动作前后节奏等待,提升"可见点击/跳转"观感。highlightBeforeClick/highlightBeforeType:动作前高亮目标元素。opennavigatesnapshotclickhovertypepressbackscrollclick_link_same_originwaitevaluateassert_url_containsassert_text_containsscreenshotnooprun_autoqa.py 在加载 scenario 时自动执行 pre-flight 校验:
action 字段action 值必须在上述"支持动作"列表内,否则报错并列出全部合法值open/navigate 须含 url;click/hover/type 须含 ref;assert_* 须含 value校验在执行前触发,出错时给出明确的 step 索引和原因——不会默默失败。
生成 scenario 时请确保遵守上述约束。id 字段建议保留(格式 step-NNN),缺省时引擎会自动补全。
{
"exploration": {
"enabled": true,
"maxDepth": 3,
"maxChildrenPerNode": 5,
"maxPages": 30,
"maxDurationMinutes": 15,
"sameOriginOnly": true
},
"steps": [
{ "id": "step-010", "action": "click_link_same_origin", "depth": 2 },
{ "id": "step-011", "action": "back", "returnEdge": true, "depth": 2 }
]
}说明:
depth:步骤所属探索层级(用于覆盖统计)。returnEdge=true:该步骤计入"返回边"覆盖统计(back 动作默认计入)。在仓库根目录执行:
python3 src/skills/auto-qa/scripts/run_autoqa.py \
--scenario-id wehub_demo \
--browser-profile openclaw \
--auto-start-browser当用户表达"跑 QA / 再测一次 / 做自动回归 / 开始测试"等执行意图时,默认进入直接执行,不先回复"计划确认"。
正常流程不使用预设脚本。场景(scenario)应由 agent 智能生成。
优先级 1:用户给了测试要求(自然语言)
用户可能说:"测一下登录功能"、"检查购物车流程"、"用以下用例做自动 QA 测试:……"。
agent 必须:
openclaw browser open <url> 打开目标openclaw browser snapshot --interactive --labels 扫描页面结构demo/scenarios/_generated/<run-id>.json--scenario <path> --force-direct-scenario-path 执行严禁忽略用户的任何测试要求。 如果页面上找不到用户要求的元素,在 scenario 中仍要包含该步骤并标注 expected,让执行引擎报告失败——而不是静默跳过。
优先级 2:用户只给了 URL,没有具体要求
agent 必须:
openclaw browser open <url> 打开目标openclaw browser snapshot --interactive --labels 扫描页面结构demo/scenarios/_generated/<run-id>.json 并执行生成的 scenario 必须基于实际页面内容,不能凭空猜测。 每个 step 的 ref、url、text 必须来自 snapshot 的真实数据。
优先级 3(极端后备):snapshot 失败或浏览器不可用
仅当以上两种方式都失败时(如浏览器无法启动、目标不可达),才回退到预设脚本:
defaultScenarioId 或 generic_template预设脚本(scenario-id)仅用于以下场景:
常用参数:
--scenario <path>:直传 scenario JSON 路径(需配合 --force-direct-scenario-path)--scenario-id <id>:从注册表选择场景(仅调试/演示;默认注册表:demo/scenarios/registry.json)--scenario-registry <path>:指定场景注册表路径--scenario-var key=value:覆盖场景变量(可重复;用于模板场景的 {{start_url}}/{{start_domain}} 等占位)--allow-direct-scenario-path:允许接收 --scenario <path> 直传请求(默认关闭;默认会回退注册表默认场景)--force-direct-scenario-path:强制执行直传路径(智能生成场景时必须开启)--run-id <id>:手动指定 run id--output-root demo:输出根目录--allow-external-scenario:允许执行仓库 demo/scenarios 目录外的场景(默认关闭,防误跑)--allow-legacy-scenario:允许执行 meta.legacy=true 的旧场景(默认关闭)--no-trace:关闭 trace 录制--browser-bin <bin>:指定 OpenClaw 可执行名(默认 openclaw)--browser-cmd "<cmd>":指定完整命令前缀(例如 pnpm --dir src openclaw)--max-step-retries <n>:每步默认重试次数(默认 1)--retry-wait-ms <ms>:重试间隔(默认 800)--showcase-recheck:启用复核执行并与主执行结果对照(默认开启)--showcase-continue-on-failure:复核执行遇到差异后是否继续(默认开启)--showcase-max-step-retries <n>:复核执行默认重试次数(默认 0)--showcase-retry-wait-ms <ms>:复核执行重试间隔(默认 500)--showcase-time-budget-ms <ms>:复核执行时间预算(默认 90000,超时即提前收口并继续产出最终报告)--resume-from-step-id <stepId>:从指定步骤开始续跑--resume-from-run-id <runId>:从某次历史失败 run 的首个失败步骤续跑--resume-last-failed:从同一场景最近一次失败 run 自动续跑--health-check-interval <off|on-failure|each-step>:健康检查频率(默认 on-failure)--trace-start-mode <auto|immediate|after-first-step>:trace 启动时机(默认 auto)--notify-channel <channel>:自动发送报告截图到指定频道(支持 discord/.../auto/current,不依赖固定频道名)--notify-target <target>:频道目标(不传则自动推断最近会话目标)--notify-account <id>:可选 accountId--notify-message <text>:可选通知文案--notify-auto-current-channel:未显式指定频道/目标时,自动发到最近活跃会话(默认开启)--notify-max-session-age-ms <ms>:自动推断会话的最大"最近活跃时间"(默认 30 分钟)--cleanup-orphan-openclaw-processes:运行前自动清理多余 OpenClaw 专用 Chrome 进程(默认开启)最终形态执行约束(当前实现):
3;默认"失败优先截图"(analysisAutoScreenshot=false),保留 console/network/trace 全量采证。open,复核执行自动改为同 tab navigate,避免额外新开 tab。needs_inspection,不阻塞本轮交付。partial_timeout,并继续生成 report.html/report_full.png 与回传。执行超时建议(重要):
exec 调脚本时,必须设置 timeout >= 900 秒。你关心的"炫酷演示 + 不打断主画面工作"建议这样跑:
python3 src/skills/auto-qa/scripts/run_autoqa.py \
--scenario-id wehub_demo \
--browser-profile openclaw \
--auto-start-browser \
--max-step-retries 1 \
--health-check-interval on-failure说明:
trace-start-mode=auto 下,若首步是 open/navigate,trace 会延后到第一步后启动,减少 about:blank 首屏干扰。report_full.png,兼容名 report_screenshot.png)。--no-notify-auto-current-channel 关闭)。/Users/chikakochou/OpenClaw/demo/scenarios/wehub_visual_demo.jsonwehub_demo(演示门禁配置,已忽略已知 index.css 404 噪音)wehub_release(发布判定,不忽略已知 4xx)运行示例(含自动发当前 Discord 频道):
python3 src/skills/auto-qa/scripts/run_autoqa.py \
--scenario-id wehub_demo \
--browser-profile openclaw \
--auto-start-browser/Users/chikakochou/OpenClaw/demo/scenarios/generic_visual_template.jsongeneric_template{{start_url}}{{start_domain}}python3 src/skills/auto-qa/scripts/run_autoqa.py \
--scenario-id generic_template \
--scenario-var start_url=http://wehub.us/ \
--scenario-var start_domain=wehub.us \
--browser-profile openclaw \
--auto-start-browserfix_plan.json:next_window_prompt.md:可直接贴到下一窗口执行standby_prompt.txt:一句确认即可启动修复流程wehub-gate-sample-20260220-v2/Users/chikakochou/.openclaw/workspace/demo/reports/run-wehub-gate-sample-20260220-v2/report.json/Users/chikakochou/.openclaw/workspace/demo/reports/run-wehub-gate-sample-20260220-v2/report.htmlreleaseDecision = NO_GOriskLevel = highopenclaw browser trace start/stop 在嵌套子命令下丢失 --browser-profile 参数的问题。chrome)。trace start/stop 在 --browser-profile openclaw 下可正常生成 trace。wehub-trace-fix-20260221-v1 已验证 tracePath 存在且报告无 trace warning。openclaw browser 无法连接,请先启动 OpenClaw 网关/浏览器服务。click/type 依赖快照 ref,场景需要提供稳定 ref 或结合 wait/evaluate 先定位。© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 8 other files (scripts, references) in skills/auto-qa of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
在 OpenClaw 平台执行网页自动 QA 测试(自动操作 + 采证 + 报告 + 修复提示包)。当用户要求做自动化回归、演示级测试、失败证据归档或生成可直接交给下一窗口的修复 Prompt 时使用。. Auto QA is an agent skill from LeoYeAI/openclaw-master-skills.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill auto-qa -a claude-code`. Or copy the skill folder (skills/auto-qa in LeoYeAI/openclaw-master-skills) into .claude/skills/auto-qa in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill auto-qa -a codex`. Or copy the skill folder (skills/auto-qa in LeoYeAI/openclaw-master-skills) into .agents/skills/auto-qa in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill auto-qa -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-qa, .gemini/skills/auto-qa, .github/skills/auto-qa and .opencode/skills/auto-qa in your project.
Going by SKILL.md and its folder, Auto QA needs Python for the scripts in its folder and the command-line tools its instructions call (python3 and pnpm). Our summary lists: Python 3.
SKILL.md names 1 domain. In commands or code: wehub.us; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Auto QA is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.2k tokens, read only when the agent opens those files.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,160 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.