Agent skill

Spec Planner

by letehaha in letehaha/moneymatter

Deep-dive specification planner. An agent skill from letehaha/moneymatter.

AGPL-3.0Auto-check: notesDevelopment

Install Spec Planner

skills CLI
$ npx skills add letehaha/moneymatter --skill spec-planner -a claude-code

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

GitHub CLI
$ gh skill install letehaha/moneymatter spec-planner --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/letehaha/moneymatter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/spec-planner .claude/skills/spec-planner && 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-planner
GitHub stars
160
Token cost
~1.8k tokens
SKILL.md length
918 words
Files
2 (incl. references)
Skills in repo
10
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Deep-dive specification planner. An agent skill from letehaha/moneymatter.

  • Works in 4 steps: Context Gathering → Deep-Dive Interviewing → Clarification Rounds → …
  • You want to plan new functionality
  • SKILL.md covers When to Use This Skill, Core Philosophy, Interview Process and Interview Rules, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Spec Planner is an agent skill from letehaha/moneymatter. Deep-dive specification planner. Interviews you thoroughly about new features, refactoring, or any work requiring planning. Use when you want to plan new functionality, refactor existing code, design architecture, or create detailed specifications. Triggers on "plan", "spec", "design", "architect", or when you mention wanting to think through implementation details.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/interview-questions.md`).

It sits in Development, covering Refactoring. The repository describes itself as: A personal budget tracking application. Track your balances and transactions with bank connections or manual entry, categorize and analyze expenses and income, and many more. The licence is AGPL-3.0.

When your agent uses it

  • You want to plan new functionality
  • Refactor existing code
  • Design architecture
  • Create detailed specifications

Example prompts

  • “design”
  • “architect”
  • “/spec-planner”

Requirements

  • Pre-approved tools (allowed-tools): Read, Write, Edit, Grep, Glob, Bash, AskUserQuestion

Workflow steps

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

  1. Context Gathering
  2. Deep-Dive Interviewing
  3. Clarification Rounds
  4. Spec Writing

What it can do on your machine

Read from SKILL.md and the folder at commit de5319f. 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
    • Write
    • Edit
    • Grep
    • Glob
    • Bash
    • AskUserQuestion

    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

Spec Planner loads about 1.8k tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 95 tokens; SKILL.md has 918 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~95
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.4k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Edit, Grep, Glob, Bash, AskUserQuestion

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 letehaha/moneymatter at commit de5319f, republished under its AGPL-3.0 licence (© letehaha). 918 words, ~1,794 tokens.

Download SKILL.mdSave it as .claude/skills/spec-planner/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
spec-planner
description
Deep-dive specification planner. Interviews you thoroughly about new features, refactoring, or any work requiring planning. Use when you want to plan new functionality, refactor existing code, design architecture, or create detailed specifications. Triggers on "plan", "spec", "design", "architect", or when you mention wanting to think through implementation details.
allowed-tools
Read, Write, Edit, Grep, Glob, Bash, AskUserQuestion

Spec Planner

An in-depth interviewing and specification writing skill that helps you think through features, refactoring, and architectural decisions before implementation.

When to Use This Skill

Activate when user:

  • Wants to plan a new feature or functionality
  • Needs to refactor existing code and wants to think it through
  • Says "plan", "let's plan", "help me plan", "spec out", "design"
  • Wants to discuss implementation details before coding
  • Mentions wanting to think through tradeoffs or concerns
  • References a SPEC.md file or asks to create one

Do NOT activate for:

  • Simple bug fixes that don't need planning
  • Documentation requests (use prd-creator for PRDs)
  • Direct code implementation requests without planning context

Core Philosophy

Interview First, Write Second: Your primary job is to extract information from the user's head through thoughtful questioning. The spec document is a byproduct of thorough understanding.

No Obvious Questions: Never ask questions the user could answer by reading basic documentation. Focus on edge cases, tradeoffs, UX nuances, and non-obvious implementation concerns.

Continuous Until Complete: Keep interviewing until you've covered all aspects. Don't stop after one round of questions.

Interview Process

Phase 1: Context Gathering
  1. If user references a file (like @SPEC.md or any existing spec), read it first
  2. Explore relevant existing code to understand current architecture
  3. Identify what the user is trying to achieve at a high level
Phase 2: Deep-Dive Interviewing

Use AskUserQuestion tool repeatedly to probe deeply. Structure your questions across these dimensions:

Consult references/interview-questions.md for the full question bank. Cover these dimensions:

  • Technical Implementation: Edge cases, failure conditions, async vs sync, rollback, validation, migrations, API contracts
  • UI/UX: Loading states, error display, unexpected actions, confirmation dialogs, navigation, accessibility
  • Data & State: Source of truth, staleness, caching, persistence, cascading deletes, consistency
  • Security & Privacy: Access control, rate limiting, audit logging, sensitive data
  • Integration & Dependencies: External services, failure handling, API limitations, feature interactions
  • Tradeoffs & Alternatives: Approach justification, compromises, MVP scope, risk assessment
  • Future Considerations: Evolution path, related features, changeability, extensibility vs simplicity
Phase 3: Clarification Rounds

After initial deep-dive:

  1. Summarize your understanding back to the user
  2. Identify any contradictions or gaps
  3. Ask follow-up questions based on their answers
  4. Continue until you have no more ambiguities
Phase 4: Spec Writing

Only after thorough interviewing, write the specification:

  1. Location: Store specs in docs/prds/ using kebab-case naming (e.g., transaction-bulk-edit.md)

  2. Structure:

    • Overview (2-3 sentences max)
    • Problem Statement
    • Goals & Non-Goals (explicitly list what's OUT of scope)
    • Technical Design (architecture, data flow, key decisions)
    • Edge Cases & Error Handling
    • UI/UX Specifications (if applicable)
    • Security Considerations
    • Open Questions (anything still unresolved)
    • Implementation Notes (gotchas, dependencies, suggested order)
  3. Keep it Actionable: Write for an engineer who needs to implement this. Be specific, not vague.

Interview Rules

  1. Batch Questions Wisely: Use AskUserQuestion to present 3-4 related questions at once, not one at a time (avoids fatigue) but not too many (avoids overwhelm).

  2. Build on Answers: Each round of questions should be informed by previous answers. Don't use a generic checklist.

  3. Challenge Assumptions: If the user says "it should just work like X", probe what "just work" means in edge cases.

  4. Suggest Alternatives: When appropriate, present options with tradeoffs rather than just asking open-ended questions.

  5. Know When to Stop: Stop interviewing when:

    • You can explain the feature back to them with full confidence
    • All edge cases have clear handling strategies
    • The user confirms the summary is accurate and complete
  6. Don't Assume: Never fill in gaps with assumptions. If something is unclear, ask.

Show full SKILL.md (344 more words)Show less

Example Question Patterns

Instead of: "What should the button do?" Ask: "When the user clicks submit and the network request fails mid-way, should we: (a) show an error and let them retry, (b) automatically retry N times silently, or (c) save as draft and notify them later?"

Instead of: "How should errors work?" Ask: "If the external API returns a 429 rate limit error during bulk import of 100 items where 47 have already succeeded, should we: (a) fail the entire operation and rollback, (b) pause and retry after the rate limit window, or (c) mark partial success and let user resume?"

Instead of: "What's the UI?" Ask: "When showing the list of 500+ items, should we: (a) paginate with explicit page numbers, (b) infinite scroll with virtualization, or (c) load-more button? Consider that users mentioned they often need to jump to specific items."

Output Expectations

  • The final spec should be detailed enough that another engineer could implement it without asking clarifying questions
  • Include concrete examples where helpful
  • List explicit decisions made during the interview
  • Note any accepted limitations or future improvements deferred

Examples

Example 1: New feature spec

User says: "I want to plan a recurring transactions feature" Actions:

  1. Read existing transaction-related code for context
  2. Interview user across all dimensions (3-4 rounds)
  3. Write spec to docs/prds/recurring-transactions.md Result: Detailed spec covering technical design, edge cases, UI/UX, and implementation notes
Example 2: Refactoring spec

User says: "Let's plan the migration from REST to tRPC" Actions:

  1. Explore current API structure and patterns
  2. Interview about scope, rollout strategy, backwards compatibility
  3. Write spec with phased migration plan Result: Actionable spec with clear phases, dependencies, and risk assessment

Troubleshooting

User gives vague answers

Cause: Questions are too open-ended or user hasn't thought through details yet Solution: Offer concrete options with tradeoffs instead of open-ended questions. Use the "Instead of X, ask Y" patterns.

Interview goes too long

Cause: Too many dimensions explored at once Solution: Prioritize dimensions most relevant to the feature. Skip Security/Privacy for internal-only features, skip UI/UX for pure backend work.

© letehaha, 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 1 other file (references) in .claude/skills/spec-planner of letehaha/moneymatter.

  • SKILL.md
  • references/interview-questions.md

Open the folder on GitHubat commit de5319f

Compare with similar skills

Spec Planner 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.

Spec Planner compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Spec Planner this skillletehaha/moneymatter160—~1.8kAutomated safety check: NotesAGPL-3.0
Guidelinesakash-network/node1.1k22 repos~577Automated safety check: PassMIT
Component Refactoringlangflow-ai/langflow156k—~3.5kAutomated safety check: PassMIT
Migrate Core Code to Submodulestinyhumansai/openhuman42k—~2.6kAutomated safety check: PassGPL-3.0
Systematic Code Refactoringluongnv89/claude-howto42k—~3kAutomated safety check: PassMIT
Codexskills-directory/skill-codex1.5k3 repos~1.8kAutomated safety check: PassMIT

Similar skills

  • Guidelines

    akash-network/node

    Behavioral guidelines to reduce common LLM coding mistakes. An agent skill from akash-network/node.

    1.1k GitHub starsUsed in 22 repos~577 tokens
    DevelopmentAuto-check passed
  • Component Refactoring

    langflow-ai/langflow

    Refactor high-complexity React components in Langflow frontend.

    156k GitHub stars~3.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Migrate Core Code to Submodules

    tinyhumansai/openhuman

    Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.

    42k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed
  • Systematic Code Refactoring

    luongnv89/claude-howto

    Guides refactoring in phases based on Martin Fowler's method: research, test coverage check, planning and small tested steps, with your approval at each phase.

    42k GitHub stars~3k tokensUpdated 8 days ago
    DevelopmentAuto-check passed
  • Codex

    skills-directory/skill-codex

    A skill your agent uses when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing

    1.5k GitHub starsUsed in 3 repos~1.8k tokens
    DevelopmentAuto-check passed
  • Ponytail

    DavidObando/gsharp

    Forces the laziest solution that actually works, simplest, shortest, most minimal.

    565 GitHub starsUsed in 8 repos~1.7k tokens
    DevelopmentAuto-check passed

More from letehaha/moneymatter

All 10 skills in this repo
  • Add MCP Tool

    letehaha/moneymatter

    Add a new tool to the MoneyMatter MCP server. An agent skill from letehaha/moneymatter.

    160 GitHub stars~1.9k tokensUpdated today
    Auto-check: notes
  • Find Slop

    letehaha/moneymatter

    Hunt "AI slop" in this codebase — duplication, reinvented wheels, over-engineering, defensive cruft, dead code, comment slop, performance antipatterns.

    160 GitHub stars~3k tokensUpdated today
    Auto-check passed
  • Frontend Rules

    letehaha/moneymatter

    Frontend conventions and component usage rules. An agent skill from letehaha/moneymatter.

    160 GitHub stars~3.8k tokensUpdated today
    Auto-check passed
  • I18n Before Release

    letehaha/moneymatter

    Occasional i18n catch-up: strip unused en keys, then fill any uk translations that slipped through via i18n-editor subagents.

    160 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • E2E Test Creator

    letehaha/moneymatter

    Creates backend e2e tests for new or existing endpoints. An agent skill from letehaha/moneymatter.

    160 GitHub stars~2.4k tokensUpdated today
    Auto-check: warnings
  • Prd Creator

    letehaha/moneymatter

    Smart PRD generator. An agent skill from letehaha/moneymatter.

    160 GitHub stars~1.1k tokensUpdated today
    Auto-check: notes

Categories

Questions about Spec Planner

What does Spec Planner do?

Deep-dive specification planner. An agent skill from letehaha/moneymatter. Spec Planner is an agent skill from letehaha/moneymatter. Deep-dive specification planner.

When should I use Spec Planner?

Spec Planner fits situations like: you want to plan new functionality; refactor existing code; design architecture; create detailed specifications.

How do I install Spec Planner in Claude Code?

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

How do I install Spec Planner in Codex?

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

Can I use Spec Planner 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 letehaha/moneymatter --skill spec-planner -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-planner, .gemini/skills/spec-planner, .github/skills/spec-planner and .opencode/skills/spec-planner in your project.

What does Spec Planner need to run?

SKILL.md names no scripts, command-line tools or credentials: Spec Planner is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit, Grep, Glob, Bash, AskUserQuestion.

Does Spec Planner 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 Spec Planner safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Spec Planner use?

Spec Planner 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 Spec Planner use?

About 1.8k tokens (SKILL.md is roughly 7.2k 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 611 tokens, read only when the agent opens those files.

What are the alternatives to Spec Planner?

Skills that share tags, products or a category with Spec Planner: Guidelines (akash-network/node, 1.1k stars), Component Refactoring (langflow-ai/langflow, 156k stars), Migrate Core Code to Submodules (tinyhumansai/openhuman, 42k stars) and Systematic Code Refactoring (luongnv89/claude-howto, 42k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Spec Planner?

letehaha (a GitHub user) maintains it in letehaha/moneymatter, which has 160 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 7, 2026.

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