Fin Data Acquisition
csmar432/finai-research
根据REFINEDDESIGN.md中的变量定义，自动获取所需数据并生成可执行的回归分析脚本（Python/Stata）。
Generate RFC and IMPL documents from a user-provided feature/fix description.
Install Rfc Impl Generator
$ npx skills add SepineTam/mcp-for-stata --skill rfc-impl-generator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install SepineTam/mcp-for-stata rfc-impl-generator --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/rfc-impl-generator .claude/skills/rfc-impl-generator && 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 "rfc-impl-generator" agent skill from https://github.com/SepineTam/mcp-for-stata/tree/master/.claude/skills/rfc-impl-generator into .claude/skills/rfc-impl-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rfc-impl-generator", 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/rfc-impl-generatorType 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 rfc-impl-generator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install SepineTam/mcp-for-stata rfc-impl-generator --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/rfc-impl-generator .agents/skills/rfc-impl-generator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "rfc-impl-generator" agent skill from https://github.com/SepineTam/mcp-for-stata/tree/master/.claude/skills/rfc-impl-generator into .agents/skills/rfc-impl-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rfc-impl-generator", 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 rfc-impl-generator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install SepineTam/mcp-for-stata rfc-impl-generator --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/rfc-impl-generator .cursor/skills/rfc-impl-generator && 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 "rfc-impl-generator" agent skill from https://github.com/SepineTam/mcp-for-stata/tree/master/.claude/skills/rfc-impl-generator into .cursor/skills/rfc-impl-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rfc-impl-generator", 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/rfc-impl-generator--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 rfc-impl-generator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install SepineTam/mcp-for-stata rfc-impl-generator --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/rfc-impl-generator .gemini/skills/rfc-impl-generator && 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 "rfc-impl-generator" agent skill from https://github.com/SepineTam/mcp-for-stata/tree/master/.claude/skills/rfc-impl-generator into .gemini/skills/rfc-impl-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rfc-impl-generator", 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 rfc-impl-generatorInstalls 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 rfc-impl-generator -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/rfc-impl-generator .github/skills/rfc-impl-generator && 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 "rfc-impl-generator" agent skill from https://github.com/SepineTam/mcp-for-stata/tree/master/.claude/skills/rfc-impl-generator into .github/skills/rfc-impl-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rfc-impl-generator", 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 rfc-impl-generator -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 rfc-impl-generator --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/rfc-impl-generator .opencode/skills/rfc-impl-generator && 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 "rfc-impl-generator" agent skill from https://github.com/SepineTam/mcp-for-stata/tree/master/.claude/skills/rfc-impl-generator into .opencode/skills/rfc-impl-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rfc-impl-generator", 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
rfc-impl-generator- GitHub stars
- 264
- Token cost
- ~1.1k tokens
- SKILL.md length
- 561 words
- Files
- 6 (incl. references)
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Generate RFC and IMPL documents from a user-provided feature/fix description.
- Works in 5 steps: Receive the User's Description → Assess Information Completeness → Ask Clarifying Questions (if needed) → …
- The user says something like I want to add a feature with codex
- SKILL.md covers When to Use, Workflow and Reference Files
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Rfc Impl Generator is an agent skill from SepineTam/mcp-for-stata. Generate RFC and IMPL documents from a user-provided feature/fix description. Use when the user says something like "I want to add a feature with codex", "Implement this", "Write an RFC for...", or provides a short idea that needs to be formalized into the ai-driven/rfc + ai-driven/impl pipeline.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/impl-example.md`, `references/impl-template.md` and `references/rfc-example.md`).
It sits in Research & Science, covering Econometrics and empirical research. 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
- The user says something like I want to add a feature with codex
- Write an RFC for...
- Provides a short idea that needs to be formalized into the ai-driven/rfc + ai-driven/impl pipeline
Example prompts
- “I want to add a feature with codex”
- “Implement this”
- “Write an RFC for...”
- “/rfc-impl-generator”
Requirements
- Pre-approved tools (allowed-tools): Read, Grep, Write, Edit, AskUserQuestion
Workflow steps
5 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 these tools, so the agent can use them without asking each time:
ReadGrepWriteEditAskUserQuestion
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
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
Rfc Impl Generator loads about 1.1k tokens when it runs, and up to ~4.2k if it reads all its reference files. Until then it costs about 79 tokens; SKILL.md has 561 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from SepineTam/mcp-for-stata at commit d339615, republished under its AGPL-3.0 licence (© SepineTam). 561 words, ~1,094 tokens.
Download SKILL.mdSave it as
.claude/skills/rfc-impl-generator/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- rfc-impl-generator
- description
- Generate RFC and IMPL documents from a user-provided feature/fix description. Use when the user says something like "I want to add a feature with codex", "Implement this", "Write an RFC for...", or provides a short idea that needs to be formalized into the ai-driven/rfc + ai-driven/impl pipeline.
- allowed-tools
- Read, Grep, Write, Edit, AskUserQuestion
RFC/IMPL Document Generator
Convert a user's feature or fix idea into a paired RFC (design document for humans) and IMPL (implementation prompt for AI) in the ai-driven/ directory.
When to Use
- User says "I want to add X feature"
- User describes a bug fix or improvement
- User says "write an RFC for..."
- User gives a short idea that needs formalization before coding
Workflow
Step 1. Receive the User's Description
The user provides a short description of what they want. This could be a sentence, a paragraph, or a reference to a GitHub issue.
Step 2. Assess Information Completeness
Determine if the description is sufficient to write a meaningful RFC and IMPL. Ask yourself:
- Do I understand what problem this solves?
- Do I understand what the user expects to happen after the change?
- Do I understand when/where the user would use this?
- Do I know the scope (what's in, what's out)?
If any of these are unclear, proceed to Step 3. If all are clear, jump to Step 4.
Step 3. Ask Clarifying Questions (if needed)
Use AskUserQuestion to gather missing information. Focus on expected outcomes and user experience, NOT technical implementation details.
Good questions (ask these):
- "What should the user see or experience after this change?"
- "When would someone use this? Can you walk through a concrete scenario?"
- "What problem does this solve for you?"
- "How important is this compared to other features you're considering?"
Bad questions (avoid these):
- "Should this be a new parameter or a config option?"
- "Do you want to use threading or multiprocessing?"
- "What data structure should we use?"
- "Should we cache this in Redis or a file?"
Rules for asking:
- Ask 1-2 questions at a time
- After each answer, re-assess if you have enough information
- If still unclear, ask follow-up questions
- Stop once you can write a coherent RFC and IMPL
Step 4. Generate the Documents
Once you have sufficient information, generate both documents.
Show full SKILL.md (242 more words)Show less
4.1 Determine the filename
Use the naming convention from .claude/rules/ai-driven-coding.md:
- If there's a GitHub issue:
{issue-number}-{short-name}.md - If no issue:
{prefix}-{short-name}.md(prefix = feat-, fix-, refactor-, perf-, docs-)
short-name should be 2-4 English words, kebab-case.
Before writing, ask the user to confirm the filename if you're unsure about the issue number or prefix.
4.2 Write the RFC
Create ai-driven/rfc/{filename}. Read references/rfc-template.md for the exact structure and copy it as the starting scaffold.
RFC rules:
- Written in the user's natural language
- No concrete code (no diffs, no real implementation)
- No "future work" sections
- Focus on "what" and "why", not "how"
4.3 Write the IMPL
Create ai-driven/impl/{filename}. Read references/impl-template.md for the exact structure and copy it as the starting scaffold.
IMPL rules:
- Written in English (AI-facing)
- Pseudocode only, no real runnable code
- Use "suggested", "recommended", "consider" — leave room for AI judgment
- Must end with a Checking List
Step 5. Present to User
After generating both files:
- Show the user the two file paths
- Summarize what was written in 2-3 sentences
- Ask if they want to review or modify anything before handing off to a Coding Agent
Reference Files
| Name | Location | Description |
|---|---|---|
| RFC Template | references/rfc-template.md | Empty RFC scaffold to copy for new design docs |
| IMPL Template | references/impl-template.md | Empty IMPL scaffold to copy for new AI prompts |
| RFC Example | references/rfc-example.md | Filled RFC for issue #60 (exit-clear-unix) |
| IMPL Example | references/impl-example.md | Filled IMPL for issue #60 |
| Workflow Example | references/workflow-example.md | Full walkthrough from vague idea to RFC+IMPL pair |
© 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 5 other files (references) in .claude/skills/rfc-impl-generator of SepineTam/mcp-for-stata.
- SKILL.md
- references/impl-example.md
- references/impl-template.md
- references/rfc-example.md
- references/rfc-template.md
- references/workflow-example.md
Open the folder on GitHubat commit d339615
Compare with similar skills
Rfc Impl Generator 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 |
|---|---|---|---|---|---|---|
| Rfc Impl Generator this skillSepineTam/mcp-for-stata | 264 | — | ~1.1k | Automated safety check: Pass | AGPL-3.0 | |
| Fin Data Acquisitioncsmar432/finai-research | 109 | — | ~2k | Automated safety check: Pass | MIT | |
| Fin Generate Ideacsmar432/finai-research | 109 | — | ~2.5k | Automated safety check: Pass | MIT | |
| Fin Idea Discoverycsmar432/finai-research | 109 | — | ~2.7k | Automated safety check: Pass | MIT | |
| Fin Novelty Checkcsmar432/finai-research | 109 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Stata Replicationpedrohcgs/claude-code-my-workflow | 1.7k | — | ~2.1k | Automated safety check: Notes | MIT |
Similar skills
Fin Generate Idea
csmar432/finai-research
针对经济金融研究方向的创意生成与评估。生成8-12个可发表的研究idea，过滤后在数据可行的情况下进行小规模实证验证，输出排序后的研究想法报告。
Fin Idea Discovery
csmar432/finai-research
经济金融研究的完整想法发现流程。从研究方向出发，经过文献综述、想法生成、新颖性验证、实证方法设计和数据获取，输出经过数据实证验证的可执行研究方案。
Fin Novelty Check
csmar432/finai-research
验证经济金融研究想法的新颖性。在JF、JFE、RFS、JME等顶刊及arXiv中搜索近三年文献，输出结构化新颖性报告和定位策略。
Stata Replication
pedrohcgs/claude-code-my-workflow
End-to-end Stata replication pipeline — scaffolds numbered .do files in scripts/stata/, executes them via the stata-mcp MCP server, captures logs and outputs to output/, and produces…
Aer Statspai
brycewang-stanford/Auto-Empirical-Research-Skills
A skill your agent uses when aer-identification has fixed the design, after methodology choice and before aer-robustness or aer-tables-figures, to run an AER-track analysis with StatsPAI — the…
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.
MCP Smoke Test
SepineTam/mcp-for-stata
Run a local smoke test for the Stata-MCP server. An agent skill from SepineTam/mcp-for-stata.
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.
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 Rfc Impl Generator
What does Rfc Impl Generator do?
Generate RFC and IMPL documents from a user-provided feature/fix description. Rfc Impl Generator is an agent skill from SepineTam/mcp-for-stata. Generate RFC and IMPL documents from a user-provided feature/fix description.
When should I use Rfc Impl Generator?
Rfc Impl Generator fits situations like: the user says something like I want to add a feature with codex; write an RFC for..; provides a short idea that needs to be formalized into the ai-driven/rfc + ai-driven/impl pipeline.
How do I install Rfc Impl Generator in Claude Code?
Run `npx skills add SepineTam/mcp-for-stata --skill rfc-impl-generator -a claude-code`. Or copy the skill folder (.claude/skills/rfc-impl-generator in SepineTam/mcp-for-stata) into .claude/skills/rfc-impl-generator in your project. Claude Code loads it when a task matches its description.
How do I install Rfc Impl Generator in Codex?
Run `npx skills add SepineTam/mcp-for-stata --skill rfc-impl-generator -a codex`. Or copy the skill folder (.claude/skills/rfc-impl-generator in SepineTam/mcp-for-stata) into .agents/skills/rfc-impl-generator in your project. Codex loads it when a task matches its description.
Can I use Rfc Impl Generator 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 rfc-impl-generator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/rfc-impl-generator, .gemini/skills/rfc-impl-generator, .github/skills/rfc-impl-generator and .opencode/skills/rfc-impl-generator in your project.
What does Rfc Impl Generator need to run?
SKILL.md names no scripts, command-line tools or credentials: Rfc Impl Generator is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Grep, Write, Edit, AskUserQuestion.
Does Rfc Impl Generator 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 Rfc Impl Generator 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 Rfc Impl Generator use?
Rfc Impl Generator 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 Rfc Impl Generator use?
About 1.1k tokens (SKILL.md is roughly 4.4k 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 3.1k tokens, read only when the agent opens those files.
What are the alternatives to Rfc Impl Generator?
Skills that share tags, products or a category with Rfc Impl Generator: Fin Data Acquisition (csmar432/finai-research, 109 stars), Fin Generate Idea (csmar432/finai-research, 109 stars), Fin Idea Discovery (csmar432/finai-research, 109 stars) and Fin Novelty Check (csmar432/finai-research, 109 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Rfc Impl Generator?
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.