Idea Generation
voidful/academic-skills
學術研究的 Idea 產生技能——從發散到收斂，系統化地產出高品質研究構想。當使用者想腦力激盪研究方向、找新 research idea、或問「我接下來可以做什麼研究」時，一定要使用此技能。觸發詞包括：brainstorm、想 idea、研究方向、下一步做什麼、有什麼可以研究的、找 gap、research proposal。適用於任何階段的學術研究構想生成。
Interactive interview that formalizes a fuzzy research idea into a structured spec (RQ, hypotheses, identification, data needs, empirical strategy).
Install Interview Me
$ npx skills add pedrohcgs/claude-code-my-workflow --skill interview-me -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install pedrohcgs/claude-code-my-workflow interview-me --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/pedrohcgs/claude-code-my-workflow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/interview-me .claude/skills/interview-me && 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 "interview-me" agent skill from https://github.com/pedrohcgs/claude-code-my-workflow/tree/main/.claude/skills/interview-me into .claude/skills/interview-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interview-me", 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/pedrohcgs/claude-code-my-workflow/tree/main/.claude/skills/interview-meType 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 pedrohcgs/claude-code-my-workflow --skill interview-me -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install pedrohcgs/claude-code-my-workflow interview-me --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pedrohcgs/claude-code-my-workflow.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/interview-me .agents/skills/interview-me && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "interview-me" agent skill from https://github.com/pedrohcgs/claude-code-my-workflow/tree/main/.claude/skills/interview-me into .agents/skills/interview-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interview-me", 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 pedrohcgs/claude-code-my-workflow --skill interview-me -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install pedrohcgs/claude-code-my-workflow interview-me --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pedrohcgs/claude-code-my-workflow.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/interview-me .cursor/skills/interview-me && 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 "interview-me" agent skill from https://github.com/pedrohcgs/claude-code-my-workflow/tree/main/.claude/skills/interview-me into .cursor/skills/interview-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interview-me", 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/pedrohcgs/claude-code-my-workflow.git --path .claude/skills/interview-me--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 pedrohcgs/claude-code-my-workflow --skill interview-me -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install pedrohcgs/claude-code-my-workflow interview-me --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pedrohcgs/claude-code-my-workflow.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/interview-me .gemini/skills/interview-me && 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 "interview-me" agent skill from https://github.com/pedrohcgs/claude-code-my-workflow/tree/main/.claude/skills/interview-me into .gemini/skills/interview-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interview-me", 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 pedrohcgs/claude-code-my-workflow interview-meInstalls 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 pedrohcgs/claude-code-my-workflow --skill interview-me -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/pedrohcgs/claude-code-my-workflow.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/interview-me .github/skills/interview-me && 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 "interview-me" agent skill from https://github.com/pedrohcgs/claude-code-my-workflow/tree/main/.claude/skills/interview-me into .github/skills/interview-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interview-me", 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 pedrohcgs/claude-code-my-workflow --skill interview-me -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install pedrohcgs/claude-code-my-workflow interview-me --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pedrohcgs/claude-code-my-workflow.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/interview-me .opencode/skills/interview-me && 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 "interview-me" agent skill from https://github.com/pedrohcgs/claude-code-my-workflow/tree/main/.claude/skills/interview-me into .opencode/skills/interview-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interview-me", 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
interview-me- GitHub stars
- 1.6k
- Token cost
- ~1.8k tokens
- SKILL.md length
- 707 words
- Files
- 1
- Skills in repo
- 59
- Repo updated
- First seen
- Licence
- MIT
At a glance
Interactive interview that formalizes a fuzzy research idea into a structured spec (RQ, hypotheses, identification, data needs, empirical strategy).
- Works in 6 steps: The Big Picture (1-2 questions) → Theoretical Motivation (1-2 questions) → Data and Setting (1-2 questions) → …
- User says interview me
- SKILL.md covers How This Works, Interview Structure, After the Interview and Post-Flight Verification…, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Interview Me is an agent skill from pedrohcgs/claude-code-my-workflow. Interactive interview that formalizes a fuzzy research idea into a structured spec (RQ, hypotheses, identification, data needs, empirical strategy). Use when user says "interview me", "help me think through this idea", "I have a half-baked idea", "formalize this into a project", "walk me through framing a study". Multi-turn Q&A; saves spec to disk. NOT for lit review (/lit-review) or ideation from scratch (/research-ideation).
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Requirements gathering, Hypothesis generation and Brainstorming. The repository describes itself as: A ready-to-fork Claude Code template for academics using LaTeX/Beamer + R. Multi-agent review, quality gates, adversarial QA, and replication protocols. The licence is MIT.
When your agent uses it
- User says interview me
- Help me think through this idea
- I have a half-baked idea
- Formalize this into a project
Example prompts
- “interview me”
- “help me think through this idea”
- “I have a half-baked idea”
- “/interview-me”
Requirements
- Pre-approved tools (allowed-tools): Read, Write, Agent, Task
Workflow steps
6 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 ae72617. 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:
ReadWriteAgentTask
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
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
Interview Me loads about 1.8k tokens when it runs. Until then it costs about 112 tokens; SKILL.md has 707 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 pedrohcgs/claude-code-my-workflow at commit ae72617, republished under its MIT licence (© pedrohcgs). 707 words, ~1,787 tokens.
Download SKILL.mdSave it as
.claude/skills/interview-me/SKILL.md (or your agent's skills folder).- name
- interview-me
- description
- Interactive interview that formalizes a fuzzy research idea into a structured spec (RQ, hypotheses, identification, data needs, empirical strategy). Use when user says "interview me", "help me think through this idea", "I have a half-baked idea", "formalize this into a project", "walk me through framing a study". Multi-turn Q&A; saves spec to disk. NOT for lit review (`/lit-review`) or ideation from scratch (`/research-ideation`).
- allowed-tools
- Read, Write, Agent, Task
- argument-hint
- [brief topic or 'start fresh'] [--no-verify]
Research Interview
Conduct a structured interview to help formalize a research idea into a concrete specification.
Input: $ARGUMENTS — a brief topic description or "start fresh" for an open-ended exploration.
How This Works
This is a conversational skill. Instead of producing a report immediately, you conduct an interview by asking questions one at a time, probing deeper based on answers, and building toward a structured research specification.
Do NOT use AskUserQuestion. Ask questions directly in your text responses, one or two at a time. Wait for the user to respond before continuing.
Interview Structure
Phase 1: The Big Picture (1-2 questions)
- "What phenomenon or puzzle are you trying to understand?"
- "Why does this matter? Who should care about the answer?"
- After the user answers, optionally ask: "Do you have a sense of what kind of paper this would be — reduced-form / structural / theory+empirics / descriptive / formal-theory / survey-experiment / unsure?" (See
.claude/agents/methods-referee.mdfor the type definitions and.claude/references/discipline-cards.mdfor field-default frequencies.) Record the answer in the saved spec under the**Paper type:**header field; "unsure" is fine and is recorded as**Paper type:** unsure.
Phase 2: Theoretical Motivation (1-2 questions)
- "What's your intuition for why X happens / what drives Y?"
- "What would standard theory predict? Do you expect something different?"
Phase 3: Data and Setting (1-2 questions)
- "What data do you have access to, or what data would you ideally want?"
- "Is there a specific context, time period, or institutional setting you're focused on?"
Phase 4: Identification (1-2 questions)
- "Is there a natural experiment, policy change, or source of variation you can exploit?"
- "What's the biggest threat to a causal interpretation?"
Phase 5: Expected Results (1-2 questions)
- "What would you expect to find? What would surprise you?"
- "What would the results imply for policy or theory?"
Phase 6: Contribution (1 question)
- "How does this differ from what's already been done? What's the gap you're filling?"
After the Interview
Once you have enough information (typically 5-8 exchanges), produce a Research Specification Document:
# Research Specification: [Title]
**Date:** [YYYY-MM-DD]
**Researcher:** [from conversation context]
**Paper type:** [reduced-form | structural | theory+empirics | descriptive | formal-theory | survey-experiment | unsure]
## Research Question
[Clear, specific question in one sentence]
## Motivation
[2-3 paragraphs: why this matters, theoretical context, policy relevance]
## Hypothesis
[Testable prediction with expected direction]
## Empirical Strategy
- **Method:** [e.g., regression discontinuity around an eligibility cutoff]
- **Treatment:** [What varies]
- **Control:** [Comparison group]
- **Key identifying assumption:** [What must hold]
- **Robustness checks:** [Placebo tests, bandwidth sensitivity, etc.]
## Data
- **Primary dataset:** [Name, source, coverage]
- **Key variables:** [Treatment, outcome, controls]
- **Sample:** [Unit of observation, time period, N]
## Expected Results
[What the researcher expects to find and why]
## Contribution
[How this advances the literature — 2-3 sentences]
## Open Questions
[Issues raised during the interview that need further thought]Save to: quality_reports/specs/research_spec_[sanitized_topic].md — the directory /grant-proposal, /data-management-plan, /power-analysis, and /preregister read from.
Post-Flight Verification (mandatory, CoVe — applies when the spec cites prior work)
The research spec's Motivation and Contribution sections typically reference prior papers by author + year. Those citations are hallucination-prone. Before saving the spec, run the Post-Flight Verification protocol from .claude/rules/post-flight-verification.md if the spec contains any citations.
Show full SKILL.md (323 more words)Show less
Steps (skip if the spec cites zero papers)
- Extract claims: every paper-citation in the Motivation / Contribution sections ("Smith 2019 shows X"), any dataset-structure claims ("the CPS has field
educ_attain"), any negative-literature assertions ("nobody has studied Y"). - Generate verification questions: specific, answerable questions per claim. "Does Smith (2019, JEL) Section 3 report finding X? Is the venue correct?"
- Spawn
claim-verifiervia theAgenttool withsubagent_type=claim-verifier, in a fresh context — a namedAgentcall, not a conversation fork, which would inherit the draft. Hand it the claims + questions + source pointers (DOIs, arXiv links,master_supporting_docs/PDFs if the user provided any during the interview). Do NOT include the drafted spec. - Reconcile: PASS → attach green block to the spec. PARTIAL → mark unverifiable citations with uncertainty flags. FAIL → rewrite the affected paragraph using the verifier's evidence before saving the spec.
Skip conditions
- Spec contains zero paper citations (pure-methodology specs with no lit references).
--no-verifyflag.- The user explicitly said during the interview "I'll verify the literature myself."
Decision records (when tradeoffs surface)
If during the interview the researcher explicitly chose among alternatives — identification strategy (DiD vs IV vs RDD), data source (admin vs survey), outcome measure, sample scope, etc. — also write an ADR-style decision record for each choice. Use templates/decision-record.md and save to quality_reports/decisions/YYYY-MM-DD_[short-topic].md. Required fields: Status / Problem / Options considered / Decision + rationale / Consequences / Rejected alternatives.
Skip the ADR if the interview produced a single uncontested direction — ADRs are for decisions with live alternatives, not for announcing the default path.
Interview Style
- Be curious, not prescriptive. Your job is to draw out the researcher's thinking, not impose your own ideas.
- Probe weak spots gently. If the identification strategy sounds fragile, ask "What would a skeptic say about...?" rather than "This won't work because..."
- Build on answers. Each question should follow from the previous response.
- Know when to stop. If the researcher has a clear vision after 4-5 exchanges, move to the specification. Don't over-interview.
© pedrohcgs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/interview-me of pedrohcgs/claude-code-my-workflow.
Open the folder on GitHubat commit ae72617
Compare with similar skills
Interview Me 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 |
|---|---|---|---|---|---|---|
| Interview Me this skillpedrohcgs/claude-code-my-workflow | 1.6k | — | ~1.8k | Automated safety check: Pass | MIT | |
| Idea Generationvoidful/academic-skills | 133 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Research Ideationmaxwell2732/paper-replicate-agent-demo | 137 | 2 repos | ~914 | Automated safety check: Pass | None | |
| Light Idea GenerationLight0305/Light-skills | 641 | 1 repos | ~4.6k | Automated safety check: Pass | MIT | |
| Idea Memo WriterWILLOSCAR/research-units-pipeline-skills | 513 | — | ~441 | Automated safety check: Pass | None | |
| Scholar Brainstormjoshzyj/open-scholar-skill | 168 | — | ~4.2k | Automated safety check: Pass | Custom licence |
Similar skills
Research Ideation
maxwell2732/paper-replicate-agent-demo
Generate structured research questions, testable hypotheses, and empirical strategies from a topic or dataset
Light Idea Generation
Light0305/Light-skills
Light 科研主线第 3 步·提 idea:从模糊方向/数据/文献结构化发散(激发算子系统生成,不是泛泛头脑风暴) → 产值得做且做得成的分层候选 idea(moonshot 冲刺/solid 稳妥/safe 保底),每个必答为什么值得做·创新点· 比现有强在哪·解决什么具体问题·能投什么层次,且提出时就自带撞车前置自查(最像的前作+delta,吃上游 literature-search…
Idea Memo Writer
WILLOSCAR/research-units-pipeline-skills
Synthesize the shortlist into a discussion-ready research idea brainstorm memo, writing output/REPORT.md, output/APPENDIX.md, and output/REPORT.json.
Scholar Brainstorm
joshzyj/open-scholar-skill
Generate research questions from existing materials — codebooks, survey questionnaires, datasets, or published papers/abstracts.
Research Ideation
meleantonio/awesome-econ-ai-stuff
Generate research questions from economic phenomena. An agent skill from meleantonio/awesome-econ-ai-stuff.
More from pedrohcgs/claude-code-my-workflow
All 59 skills in this repoDevils Advocate
pedrohcgs/claude-code-my-workflow
Adversarial 5-7 question challenge to a deck's pedagogical choices — ordering, prerequisites, cognitive load, motivation.
Vaccinate
pedrohcgs/claude-code-my-workflow
Qualify a check before it is allowed to clear anything — prove it can detect the failure it is meant to catch.
Compile Latex
pedrohcgs/claude-code-my-workflow
Compile a Beamer LaTeX slide deck with XeLaTeX (3 passes + bibtex).
Context Status
pedrohcgs/claude-code-my-workflow
Show current context status and session health. An agent skill from pedrohcgs/claude-code-my-workflow.
Disclosure Check
pedrohcgs/claude-code-my-workflow
Pre-screen analysis outputs (tables, figures, logs) built on restricted or confidential data for statistical-disclosure-limitation problems before any release.
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…
Related
Categories
Questions about Interview Me
What does Interview Me do?
Interactive interview that formalizes a fuzzy research idea into a structured spec (RQ, hypotheses, identification, data needs, empirical strategy). Interview Me is an agent skill from pedrohcgs/claude-code-my-workflow. Interactive interview that formalizes a fuzzy research idea into a structured spec (RQ, hypotheses, identification, data needs, empirical strategy).
When should I use Interview Me?
Interview Me fits situations like: user says interview me; help me think through this idea; I have a half-baked idea; formalize this into a project.
How do I install Interview Me in Claude Code?
Run `npx skills add pedrohcgs/claude-code-my-workflow --skill interview-me -a claude-code`. Or copy the skill folder (.claude/skills/interview-me in pedrohcgs/claude-code-my-workflow) into .claude/skills/interview-me in your project. Claude Code loads it when a task matches its description.
How do I install Interview Me in Codex?
Run `npx skills add pedrohcgs/claude-code-my-workflow --skill interview-me -a codex`. Or copy the skill folder (.claude/skills/interview-me in pedrohcgs/claude-code-my-workflow) into .agents/skills/interview-me in your project. Codex loads it when a task matches its description.
Can I use Interview Me 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 pedrohcgs/claude-code-my-workflow --skill interview-me -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/interview-me, .gemini/skills/interview-me, .github/skills/interview-me and .opencode/skills/interview-me in your project.
What does Interview Me need to run?
SKILL.md names no scripts, command-line tools or credentials: Interview Me is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Agent, Task.
Does Interview Me 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 Interview Me 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 Interview Me use?
Interview Me is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Interview Me use?
About 1.8k tokens (SKILL.md is roughly 7.1k 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 Interview Me?
Skills that share tags, products or a category with Interview Me: Idea Generation (voidful/academic-skills, 133 stars), Research Ideation (maxwell2732/paper-replicate-agent-demo, 137 stars), Light Idea Generation (Light0305/Light-skills, 641 stars) and Idea Memo Writer (WILLOSCAR/research-units-pipeline-skills, 513 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Interview Me?
pedrohcgs (a GitHub user) maintains it in pedrohcgs/claude-code-my-workflow, which has 1,645 GitHub stars. The repository holds 59 skills in this directory. The repository was last updated on September 27, 2026.
Source: pedrohcgs/claude-code-my-workflow on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.