New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Interview-Driven Spec Writer

by poshan0126 in poshan0126/dotclaude

Interviews you about scope, behavior, edge cases and verification, then writes a self-contained SPEC.md that a fresh session can implement without this conversation.

MITAuto-check passedAgent Workflows

Install Interview-Driven Spec Writer

skills CLI
$ npx skills add poshan0126/dotclaude --skill spec -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install poshan0126/dotclaude spec --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/poshan0126/dotclaude.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/spec .claude/skills/spec && rm -rf skills-src

Use ~/.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/

Facts

Skill name
spec
GitHub stars
871
Token cost
~804 tokens
SKILL.md length
344 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Interviews you about scope, behavior, edge cases and verification, then writes a self-contained SPEC.md that a fresh session can implement without this conversation.

  • Works in 3 steps: Explore enough to ask good questions → Interview with AskUserQuestion → Write SPEC.md
  • Before building anything non-trivial from a fuzzy feature idea
  • SKILL.md covers Step 1: Explore enough to ask…, Step 2: Interview with…, Step 3: Write SPEC.md and Rules
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The agent first skims the codebase for the modules a feature will touch, existing patterns, the test setup and similar features, strictly read-only. It then interviews you in focused rounds with the question tool, asking only what the code cannot answer and proposing defaults where the code implies one. Topics are scope and outcome, behavior including edge cases, explicit out-of-scope items, constraints and how the result will be verified.

The spec is written to SPEC.md at the project root, not in .claude, naming real files and interfaces, and you see the draft and confirm before it is saved. You are then told to run implementation in a fresh session after clearing, so it starts from clean context with the spec as its brief. The rules say never skip the interview, always state a verification step, and keep to one feature per spec.

When your agent uses it

  • Before building anything non-trivial from a fuzzy feature idea
  • Turning a vague request into a brief for a separate implementation session
  • Pinning down edge cases and verification for a feature before coding

Example prompts

  • “Interview me about a CSV export feature for the reports page, then write the spec.”
  • “Spec out role-based access for the admin area before we start building.”

Requirements

  • A repository open in the session
  • Pre-approved tools (allowed-tools): Read, Grep, Glob, Write, Bash(git ls-files *), Bash(git log *)

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Explore enough to ask good questions
  2. Interview with AskUserQuestion
  3. Write SPEC.md

What it can do on your machine

Read from SKILL.md and the folder at commit 94b84b9. 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:

    • Read
    • Grep
    • Glob
    • Write
    • Bash(git ls-files *)
    • Bash(git log *)

    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-Driven Spec Writer loads about 804 tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 344 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~804

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 poshan0126/dotclaude at commit 94b84b9, republished under its MIT licence (© poshan0126). 344 words, ~804 tokens.

Download SKILL.mdSave it as .claude/skills/spec/SKILL.md (or your agent's skills folder).
name
spec
description
Turn a fuzzy feature idea into a self-contained SPEC.md by interviewing you first. Claude asks about scope, behavior, edge cases, and verification, then writes a spec a fresh implementation session can execute. Use before building anything non-trivial.
allowed-tools
Read, Grep, Glob, Write, Bash(git ls-files *), Bash(git log *)
argument-hint
[optional: one-line feature description]
disable-model-invocation
true

Separate deciding WHAT to build from building it. Interview the user, ground the answers in the actual codebase, then write a self-contained SPEC.md a fresh session can execute without you in the room. $ARGUMENTS is an optional starting description.

Run this in a session that already has the repo open, so the questions are informed by real code.

Step 1: Explore enough to ask good questions

Skim the codebase for what the feature will touch: the relevant modules, existing patterns to match, the test setup, and any similar feature to model after. Read only — you're gathering context to interview well, not building.

Step 2: Interview with AskUserQuestion

Ask only what you can't answer from the code, in focused rounds (use AskUserQuestion; batch related questions). Cover:

  • Scope & outcome — what does "done" look like from the user's side, and what's the smallest version worth shipping?
  • Behavior — the happy path, then the edge cases (empty, error, concurrent, permission-denied) that actually matter here.
  • Boundaries — what is explicitly OUT of scope for this iteration.
  • Constraints — compatibility, performance, data/migration concerns, security-sensitive surfaces.
  • Verification — how will we confirm it works end to end (a command, a test, an observable behavior)?

Where the code implies an answer, propose it as the default in the question rather than asking cold.

Step 3: Write SPEC.md

Write SPEC.md at the project root (NOT in .claude/). Make it self-contained — a fresh session with no memory of this conversation should be able to execute it:

markdown
# Spec: <feature>

## Goal
<what and why, 2-3 sentences>

## Scope
- In: <what this iteration delivers>
- Out: <explicitly deferred>

## Behavior
- <happy path>
- <edge cases and how each should behave>

## Touch points
- <exact files / modules / interfaces involved, as file:path — named, not vague>

## Constraints
- <compat, performance, security, data/migration>

## Verification
- <the exact end-to-end check: command to run, test to pass, or behavior to observe>

## Open questions
- <anything still undecided — none is ideal>

Show the draft and confirm before writing. Then tell the user to run the implementation in a fresh session (/clear first) so it starts with a clean context and the spec as its brief.

Rules

  • Interview before writing — do not skip Step 2 and guess the spec.
  • Name real files and interfaces from the codebase; a spec full of placeholders isn't self-contained.
  • Every spec states its verification step. If you can't name one, say so and ask the user how they'll check.
  • One feature per spec. If the idea is really three features, say so and spec the one that was asked.

© poshan0126, 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 skills/spec of poshan0126/dotclaude.

Open the folder on GitHubat commit 94b84b9

Compare with similar skills

Interview-Driven Spec Writer 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.

Interview-Driven Spec Writer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Interview-Driven Spec Writer this skillposhan0126/dotclaude871—~804Automated safety check: PassMIT
GSD Phase Discussionopen-gsd/gsd-core10k1 repos~1.5kAutomated safety check: WarnMIT
Brainstorming Before BuildingjnMetaCode/superpowers-zh8.3k—~1.8kAutomated safety check: PassMIT
MoAI SPEC Workflowmodu-ai/moai-adk1.2k—~5.1kAutomated safety check: PassApache-2.0
Spec-Driven DevelopmentLichAmnesia/lich-skills234—~3.5kAutomated safety check: PassMIT
CE BrainstormEveryInc/compound-engineering-plugin25k—~1.9kAutomated safety check: PassMIT

Similar skills

  • GSD Phase Discussion

    open-gsd/gsd-core

    Asks adaptive questions about a project phase and records the decisions in a CONTEXT.md that later research and planning agents can act on without asking again.

    10k GitHub starsUsed in 1 repo~1.5k tokens
    Agent WorkflowsAuto-check: warnings

  • Brainstorming Before Building

    jnMetaCode/superpowers-zh

    Turns a rough idea into an approved design before any code is written, sorting the request into spike, bounded or architectural and enforcing an approval gate.

    8.3k GitHub stars~1.8k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed

  • MoAI SPEC Workflow

    modu-ai/moai-adk

    Manages SPEC documents for MoAI-ADK development, with GEARS or EARS requirement notation, acceptance criteria and a link into the Plan-Run-Sync workflow.

    1.2k GitHub stars~5.1k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Spec-Driven Development

    LichAmnesia/lich-skills

    Runs a gated Spec, Plan, Build, Test, Review, Ship workflow so non-trivial changes are specified, verified and reviewed before they ship, with a named artifact per phase.

    234 GitHub stars~3.5k tokensUpdated 4 mo ago
    Agent WorkflowsAuto-check passed

  • CE Brainstorm

    EveryInc/compound-engineering-plugin

    Turns a vague or ambitious feature idea into a requirements-only plan through dialogue with you, sized to the work, before any code is written.

    25k GitHub stars~1.9k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Extracting Requirements

    prime-radiant-inc/iterative-development

    Reads human-written spec documents and produces per-epic requirement files with proof obligations plus behavior scenarios with stable IDs, using parallel chunked extraction.

    181 GitHub stars~2.7k tokensUpdated 4 mo ago
    Agent WorkflowsAuto-check passed

More from poshan0126/dotclaude

All 14 skills in this repo

  • Session Catchup and Handoff

    poshan0126/dotclaude

    Rebuilds working context after /clear by reading a handoff note and the branch's git state, or writes that handoff note before a session ends.

    871 GitHub stars~811 tokensUpdated 1 mo ago
    Auto-check passed

  • Context Budget Check

    poshan0126/dotclaude

    Estimates the per-turn token cost of a project's .claude folder and CLAUDE.md, split into always-loaded, path-scoped and invoked-only files, and flags what runs over budget.

    871 GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check passed

  • Codebase Onboarding Tour

    poshan0126/dotclaude

    Builds a quick mental model of an unfamiliar codebase by dispatching read-only Explore subagents and merging their findings into one brief.

    871 GitHub stars~858 tokensUpdated 1 mo ago
    Auto-check passed

  • Parallel Specialist PR Review

    poshan0126/dotclaude

    Reviews a pull request, staged changes or a file by sending the diff to specialist reviewer agents in parallel, then merges their findings into one compact report.

    871 GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check passed

  • dotclaude Project Setup

    poshan0126/dotclaude

    Scans a codebase, interviews you, and installs only the justified Claude Code rules, hooks, agents and skills, tailored to the project's stack.

    871 GitHub stars~3.6k tokensUpdated 1 mo ago
    Auto-check passed

  • Ship Changes

    poshan0126/dotclaude

    Walks through commit, push and pull request creation for the current changes, asking you to confirm the files, message, push and PR text at each step.

    871 GitHub stars~953 tokensUpdated 1 mo ago
    Auto-check: notes

Works with

Categories

Questions about Interview-Driven Spec Writer

What does Interview-Driven Spec Writer do?

Interviews you about scope, behavior, edge cases and verification, then writes a self-contained SPEC.md that a fresh session can implement without this conversation. The agent first skims the codebase for the modules a feature will touch, existing patterns, the test setup and similar features, strictly read-only. It then interviews you in focused rounds with the question tool, asking only what the code cannot answer and proposing defaults where the code implies one.

When should I use Interview-Driven Spec Writer?

Interview-Driven Spec Writer fits situations like: before building anything non-trivial from a fuzzy feature idea; turning a vague request into a brief for a separate implementation session; pinning down edge cases and verification for a feature before coding.

How do I install Interview-Driven Spec Writer in Claude Code?

Run `npx skills add poshan0126/dotclaude --skill spec -a claude-code`. Or copy the skill folder (skills/spec in poshan0126/dotclaude) into .claude/skills/spec in your project. Claude Code loads it when a task matches its description.

How do I install Interview-Driven Spec Writer in Codex?

Run `npx skills add poshan0126/dotclaude --skill spec -a codex`. Or copy the skill folder (skills/spec in poshan0126/dotclaude) into .agents/skills/spec in your project. Codex loads it when a task matches its description.

Can I use Interview-Driven Spec Writer 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 poshan0126/dotclaude --skill spec -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/spec, .gemini/skills/spec, .github/skills/spec and .opencode/skills/spec in your project.

What does Interview-Driven Spec Writer need to run?

SKILL.md names no scripts, command-line tools or credentials: Interview-Driven Spec Writer is instructions for the agent only. Our summary lists: A repository open in the session. Its frontmatter pre-approves these tools: Read, Grep, Glob, Write, Bash(git ls-files *), Bash(git log *).

Does Interview-Driven Spec Writer 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-Driven Spec Writer 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-Driven Spec Writer use?

Interview-Driven Spec Writer 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-Driven Spec Writer use?

About 804 tokens (SKILL.md is roughly 3.2k 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-Driven Spec Writer?

Skills that share tags, products or a category with Interview-Driven Spec Writer: GSD Phase Discussion (open-gsd/gsd-core, 10k stars), Brainstorming Before Building (jnMetaCode/superpowers-zh, 8.3k stars), MoAI SPEC Workflow (modu-ai/moai-adk, 1.2k stars) and Spec-Driven Development (LichAmnesia/lich-skills, 234 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Interview-Driven Spec Writer?

poshan0126 (a GitHub user) maintains it in poshan0126/dotclaude, which has 871 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on August 27, 2026.

Source: poshan0126/dotclaude on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.