Agentacct Workflow
mikehasa/agentacct
A skill your agent uses when working in a repo with agentacct MCP configured, or when asked to track coding-agent work, smoke-test agentacct integrations, or report objective AI-agent task evidence.
Run a local smoke test for the Stata-MCP server. An agent skill from SepineTam/mcp-for-stata.
Install MCP Smoke Test
$ npx skills add SepineTam/mcp-for-stata --skill mcp-smoke-test -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install SepineTam/mcp-for-stata mcp-smoke-test --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/SepineTam/mcp-for-stata.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/mcp-smoke-test .claude/skills/mcp-smoke-test && 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 "mcp-smoke-test" agent skill from https://github.com/SepineTam/mcp-for-stata/tree/master/.claude/skills/mcp-smoke-test into .claude/skills/mcp-smoke-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-smoke-test", 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/SepineTam/mcp-for-stata/tree/master/.claude/skills/mcp-smoke-testType 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 SepineTam/mcp-for-stata --skill mcp-smoke-test -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install SepineTam/mcp-for-stata mcp-smoke-test --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/SepineTam/mcp-for-stata.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/mcp-smoke-test .agents/skills/mcp-smoke-test && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mcp-smoke-test" agent skill from https://github.com/SepineTam/mcp-for-stata/tree/master/.claude/skills/mcp-smoke-test into .agents/skills/mcp-smoke-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-smoke-test", 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 SepineTam/mcp-for-stata --skill mcp-smoke-test -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install SepineTam/mcp-for-stata mcp-smoke-test --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/SepineTam/mcp-for-stata.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/mcp-smoke-test .cursor/skills/mcp-smoke-test && 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 "mcp-smoke-test" agent skill from https://github.com/SepineTam/mcp-for-stata/tree/master/.claude/skills/mcp-smoke-test into .cursor/skills/mcp-smoke-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-smoke-test", 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/SepineTam/mcp-for-stata.git --path .claude/skills/mcp-smoke-test--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 SepineTam/mcp-for-stata --skill mcp-smoke-test -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install SepineTam/mcp-for-stata mcp-smoke-test --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/SepineTam/mcp-for-stata.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/mcp-smoke-test .gemini/skills/mcp-smoke-test && 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 "mcp-smoke-test" agent skill from https://github.com/SepineTam/mcp-for-stata/tree/master/.claude/skills/mcp-smoke-test into .gemini/skills/mcp-smoke-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-smoke-test", 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 SepineTam/mcp-for-stata mcp-smoke-testInstalls 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 SepineTam/mcp-for-stata --skill mcp-smoke-test -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/SepineTam/mcp-for-stata.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/mcp-smoke-test .github/skills/mcp-smoke-test && 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 "mcp-smoke-test" agent skill from https://github.com/SepineTam/mcp-for-stata/tree/master/.claude/skills/mcp-smoke-test into .github/skills/mcp-smoke-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-smoke-test", 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 SepineTam/mcp-for-stata --skill mcp-smoke-test -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install SepineTam/mcp-for-stata mcp-smoke-test --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/SepineTam/mcp-for-stata.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/mcp-smoke-test .opencode/skills/mcp-smoke-test && 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 "mcp-smoke-test" agent skill from https://github.com/SepineTam/mcp-for-stata/tree/master/.claude/skills/mcp-smoke-test into .opencode/skills/mcp-smoke-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-smoke-test", 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
mcp-smoke-test- GitHub stars
- 264
- Token cost
- ~1.4k tokens
- SKILL.md length
- 576 words
- Files
- 8 (incl. scripts)
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Run a local smoke test for the Stata-MCP server. An agent skill from SepineTam/mcp-for-stata.
- Works in 4 steps: Ensure the MCP server is registered → Run smoke tests → Clean up → …
- Tasks that involve QA and bug reports
- SKILL.md covers When to use, Before you start, Step 1: Ensure the MCP server… and Step 2: Run smoke tests, plus 3 more sections
- Runs Shell and Python scripts from its folder; calls claude and bash; reaches raw.githubusercontent.com
What it does
MCP Smoke Test is an agent skill from SepineTam/mcp-for-stata. Run a local smoke test for the Stata-MCP server.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including scripts (for example `examples.md`, `scripts/cleanup.sh` and `scripts/gen_mock_data.py`).
It sits in Testing & QA, covering QA and bug reports, Econometrics and empirical research and MCP servers. It works with Model Context Protocol. The repository describes itself as: Stata-MCP: A MCP server for integrating Stata into your agent loop with a safety-first design. The licence is AGPL-3.0.
When your agent uses it
- Tasks that involve QA and bug reports
- Tasks that involve Econometrics and empirical research
- Tasks that involve MCP servers
Example prompts
- “/mcp-smoke-test”
Requirements
- Python 3
- A Bash shell
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit d339615. 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
Ships 5 files in scripts/ (Shell and Python), which the agent can run.
Shell commands in SKILL.md call:
claudebash
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
raw.githubusercontent.com
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
MCP Smoke Test loads about 1.4k tokens when it runs. Until then it costs about 16 tokens; SKILL.md has 576 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); the scripts in this folder are not scanned.
SKILL.md
The full file from SepineTam/mcp-for-stata at commit d339615, republished under its AGPL-3.0 licence (© SepineTam). 576 words, ~1,382 tokens.
Download SKILL.mdSave it as
.claude/skills/mcp-smoke-test/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.- name
- mcp-smoke-test
- description
- Run a local smoke test for the Stata-MCP server.
MCP Smoke Test for Stata-MCP
This skill performs an end-to-end smoke test of the local Stata-MCP server. It checks installation, runs representative data and Stata commands, and reports pass/fail status for each tool.
When to use
- The user asks whether Stata-MCP is working.
- The user wants to verify a new MCP server configuration.
- The user says a tool is broken or unavailable.
- The user asks for a smoke test, sanity check, or end-to-end test.
Before you start
- Make sure the current working directory is the project root.
- Confirm whether the project virtual environment exists at
./.venv/bin/stata-mcp. If it does not exist, use the globally installedstata-mcpcommand instead. - Ensure
~/.statamcp/debug.tomlexists and enables beta security. Use.claude/skills/mcp-smoke-test/config/debug.example.tomlas a template.
Step 1: Ensure the MCP server is registered
Check whether the MCP server stata-mcp-local-smoke-test is available by listing
Claude MCP servers:
claude mcp listIf stata-mcp-local-smoke-test is missing, add it with the debug configuration:
claude mcp add stata-mcp-local-smoke-test -s local -- $(pwd)/.venv/bin/stata-mcp -c ~/.statamcp/debug.tomlIf ./.venv does not exist, use:
claude mcp add stata-mcp-local-smoke-test -s local -- stata-mcp -c ~/.statamcp/debug.tomlAfter adding, if the server is still not available, tell the user:
MCP server was added but is not yet visible. Please restart the Claude process and then invoke the smoke test again.
Step 2: Run smoke tests
Run the preparation script. It clears cached summaries, locates or generates a
suitable auto.dta, and copies the boundary test files to /tmp:
bash .claude/skills/mcp-smoke-test/scripts/prepare_smoke_test.shThen use the mcp__stata-mcp-local-smoke-test tools (or the server name registered above)
to execute each test below. Record the result for each item.
For concrete tool-call parameters, expected outputs, and troubleshooting, see
.claude/skills/mcp-smoke-test/examples.md.
Test A — get_data_info on a local Stata sample file
Try the first existing file from this list:
/Applications/Stata/auto.dta/Applications/StataNow/auto.dta
Expected result: JSON summary with 74 observations and 12 variables.
Test B — get_data_info on an allowed URL
Use this URL (already in the allowlist):
https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csvExpected result: JSON summary with 150 observations and 5 variables.
Test C — stata_do with a legal dofile
Run the bundled dofile .claude/skills/mcp-smoke-test/scripts/legal.do with stata_do.
Expected result: execution succeeds and returns log file paths.
Test D — stata_do security boundary (negative test)
Run the copied dofile /tmp/mcp_smoke_test_boundary.do with stata_do.
Expected result: blocked by the security guard because the dofile is outside the allowed working directory.
Show full SKILL.md (218 more words)Show less
Test E — read_log on the generated log
Read the text log returned by Test C. Expected result: log content includes regression output.
Test F — help for a Stata command
Run help with argument regress. Expected result: Stata help text for regress.
Test G — ado_package_install (optional, requires user approval)
If the user confirms, attempt to install a small SSC package such as estout.
Expected result: user approval prompt, then installation log.
If the user declines or the tool is not registered (non-unsafe profile), mark this test as skipped.
Step 3: Clean up
Run the cleanup script to remove temporary files and cached summaries:
bash .claude/skills/mcp-smoke-test/scripts/cleanup.shDo not delete log files or data summaries; they are useful for diagnosis.
Step 4: Report results
Return a concise Chinese report using this template:
# Stata-MCP 冒烟测试报告
## 服务器状态
- 注册状态：<已注册 / 新注册 / 需重启>
- 配置文件：`~/.statamcp/debug.toml`
## 测试结果
- [ ] Test A 本地 auto.dta 读取：<通过 / 失败 / 跳过> — 原因
- [ ] Test B URL 鸢尾花数据集读取：<通过 / 失败 / 跳过> — 原因
- [ ] Test C 合法 dofile 执行：<通过 / 失败 / 跳过> — 原因
- [ ] Test D 安全边界拦截：<通过 / 失败 / 跳过> — 原因
- [ ] Test E 日志读取：<通过 / 失败 / 跳过> — 原因
- [ ] Test F help 命令：<通过 / 失败 / 跳过> — 原因
- [ ] Test G ado 包安装：<通过 / 失败 / 跳过> — 原因
## 总结
<一句话结论：全部通过 / 部分失败 / 需要用户操作>Only mark a test as passed when you observed the expected result. For failures, include the exact error message or tool response.
Resources
| Resource | Path | Purpose |
|---|---|---|
| Example config | .claude/skills/mcp-smoke-test/config/debug.example.toml | Template for ~/.statamcp/debug.toml with beta security enabled |
| Usage examples | .claude/skills/mcp-smoke-test/examples.md | Concrete tool calls, expected outputs, and troubleshooting |
| Legal dofile | .claude/skills/mcp-smoke-test/scripts/legal.do | Valid dofile for Test C |
| Boundary dofile | .claude/skills/mcp-smoke-test/scripts/boundary.do | Dofile that references /tmp/auto.dta for Test D |
| Mock data generator | .claude/skills/mcp-smoke-test/scripts/gen_mock_data.py | Generates auto.dta when the system sample is unavailable |
| Prepare script | .claude/skills/mcp-smoke-test/scripts/prepare_smoke_test.sh | Sets up all test artifacts |
| Cleanup script | .claude/skills/mcp-smoke-test/scripts/cleanup.sh | Removes temporary test artifacts |
© SepineTam, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 7 other files (scripts) in .claude/skills/mcp-smoke-test of SepineTam/mcp-for-stata.
- SKILL.md
- config/debug.example.toml
- examples.md
- scripts/boundary.do
- scripts/cleanup.sh
- scripts/gen_mock_data.py
- scripts/legal.do
- scripts/prepare_smoke_test.sh
Open the folder on GitHubat commit d339615
Compare with similar skills
MCP Smoke Test 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 |
|---|---|---|---|---|---|---|
| MCP Smoke Test this skillSepineTam/mcp-for-stata | 264 | — | ~1.4k | Automated safety check: Pass | AGPL-3.0 | |
| Agentacct Workflowmikehasa/agentacct | 766 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Glance TestDebugBase/glance | 156 | — | ~827 | Automated safety check: Pass | MIT | |
| Windows QA EngineerCodeAlive-AI/ai-driven-development | 159 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Testing Scope MCPdaydreamlive/scope | 452 | — | ~1.2k | Automated safety check: Pass | Custom licence | |
| Live Linear Smoketacticlaunch/mcp-linear | 147 | — | ~251 | Automated safety check: Pass | MIT |
Similar skills
Glance Test
DebugBase/glance
Run E2E browser tests on any web application using Glance MCP.
Windows QA Engineer
CodeAlive-AI/ai-driven-development
A skill your agent uses when testing Windows 11 desktop apps (WinForms/WPF/UWP) via UFO UIA/Win32 automation MCP.
Testing Scope MCP
daydreamlive/scope
Test Daydream Scope through its stdio MCP server, including disconnected startup, connecttoscope, direct Python stdio client fallback, and lightweight smoke tests.
Live Linear Smoke
tacticlaunch/mcp-linear
Run safe live smoke tests for mcp-linear against a real Linear workspace.
- Official
GitHub Issues
github/awesome-copilot
Create, update, and manage GitHub issues using MCP tools. An agent skill from github/awesome-copilot.
More from SepineTam/mcp-for-stata
Stata Audit
SepineTam/mcp-for-stata
Inspect, validate, summarize, and render local Stata-MCP audit evidence under .statamcp.
Diagnostic Dofile
SepineTam/mcp-for-stata
A skill your agent uses when the user needs to inspect, audit, or diagnose the safety of a Stata do-file.
Stata Discover
SepineTam/mcp-for-stata
A skill your agent uses when you need to find Stata on the user's machine or configure stata-mcp to use it.
Rfc Impl Generator
SepineTam/mcp-for-stata
Generate RFC and IMPL documents from a user-provided feature/fix description.
Stata Skill
SepineTam/mcp-for-stata
A packaged Stata Runner skill via official MCP-for-Stata server including statado, adopackageinstall, help, readlog and getdatainfo tools.
Related
Works with
Categories
Questions about MCP Smoke Test
What does MCP Smoke Test do?
Run a local smoke test for the Stata-MCP server. An agent skill from SepineTam/mcp-for-stata. MCP Smoke Test is an agent skill from SepineTam/mcp-for-stata. Run a local smoke test for the Stata-MCP server.
When should I use MCP Smoke Test?
MCP Smoke Test fits situations like: tasks that involve QA and bug reports; tasks that involve Econometrics and empirical research; tasks that involve MCP servers.
How do I install MCP Smoke Test in Claude Code?
Run `npx skills add SepineTam/mcp-for-stata --skill mcp-smoke-test -a claude-code`. Or copy the skill folder (.claude/skills/mcp-smoke-test in SepineTam/mcp-for-stata) into .claude/skills/mcp-smoke-test in your project. Claude Code loads it when a task matches its description.
How do I install MCP Smoke Test in Codex?
Run `npx skills add SepineTam/mcp-for-stata --skill mcp-smoke-test -a codex`. Or copy the skill folder (.claude/skills/mcp-smoke-test in SepineTam/mcp-for-stata) into .agents/skills/mcp-smoke-test in your project. Codex loads it when a task matches its description.
Can I use MCP Smoke Test 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 SepineTam/mcp-for-stata --skill mcp-smoke-test -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mcp-smoke-test, .gemini/skills/mcp-smoke-test, .github/skills/mcp-smoke-test and .opencode/skills/mcp-smoke-test in your project.
What does MCP Smoke Test need to run?
Going by SKILL.md and its folder, MCP Smoke Test needs a shell and Python for the scripts in its folder and the command-line tools its instructions call (claude and bash). Our summary lists: Python 3; A Bash shell.
Does MCP Smoke Test access the network?
SKILL.md names 1 domain. In commands or code: raw.githubusercontent.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is MCP Smoke Test 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does MCP Smoke Test use?
MCP Smoke Test is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does MCP Smoke Test use?
About 1.4k tokens (SKILL.md is roughly 5.5k 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 MCP Smoke Test?
Skills that share tags, products or a category with MCP Smoke Test: Agentacct Workflow (mikehasa/agentacct, 766 stars), Glance Test (DebugBase/glance, 156 stars), Windows QA Engineer (CodeAlive-AI/ai-driven-development, 159 stars) and Testing Scope MCP (daydreamlive/scope, 452 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains MCP Smoke Test?
SepineTam (a GitHub user) maintains it in SepineTam/mcp-for-stata, which has 264 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 6, 2026.
Source: SepineTam/mcp-for-stata on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.