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

Todos Review

by hanamizuki in hanamizuki/solopreneur

Deep-review a single todo or backlog item to decide whether it is worth building: problem clarity, solution quality, and implementation priority.

MITAuto-check passedAgent Workflows

Install Todos Review

skills CLI
$ npx skills add hanamizuki/solopreneur --skill todos-review -a claude-code

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

GitHub CLI
$ gh skill install hanamizuki/solopreneur todos-review --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/hanamizuki/solopreneur.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/solopreneur/todos-review .claude/skills/todos-review && 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
todos-review
GitHub stars
152
Token cost
~2.2k tokens
SKILL.md length
799 words
Files
1
Skills in repo
31
Repo updated
First seen
Licence
MIT

At a glance

Deep-review a single todo or backlog item to decide whether it is worth building: problem clarity, solution quality, and implementation priority.

  • Works in 8 steps: Read the Todo → Verify Current State (Explore Agent) → 5: Short-Circuit for Completed Todos → …
  • The user says review this todo
  • SKILL.md covers Config Discovery, Input, Review Process and Key Principles
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Todos Review is an agent skill from hanamizuki/solopreneur. Deep-review a single todo or backlog item to decide whether it is worth building: problem clarity, solution quality, and implementation priority. Dispatches platform-specific expert agents for readiness checks. Use when the user says "review this todo", "review todo", provides a todo file path, or wants a go/no-go recommendation before implementing a backlog item. This skill answers "should we build this at all" — for "is this the right way to build it", use /plan-review on the spec or implementation plan instead.

Its SKILL.md is about 2.2k 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 Planning and Feature launches and release readiness. The repository describes itself as: Skills and agents for solopreneurs — ship, review, debug, and think through problems with AI. The licence is MIT.

When your agent uses it

  • The user says review this todo
  • Provides a todo file path
  • Wants a go/no-go recommendation before implementing a backlog item

Example prompts

  • “review this todo”
  • “review todo”
  • “should we build this at all”
  • “/todos-review”

Requirements

  • Python 3

Workflow steps

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

  1. Read the Todo
  2. Verify Current State (Explore Agent)
  3. 5: Short-Circuit for Completed Todos
  4. Detect Tech Stack and Route to Expert Agent
  5. Best Practice Check (Expert Subagent)
  6. Check Dependencies and Spec Conflicts
  7. Structured Evaluation
  8. Output

What it can do on your machine

Read from SKILL.md and the folder at commit f43f001. 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

    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

Todos Review loads about 2.2k tokens when it runs. Until then it costs about 134 tokens; SKILL.md has 799 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~134
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

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 hanamizuki/solopreneur at commit f43f001, republished under its MIT licence (© hanamizuki). 799 words, ~2,244 tokens.

Download SKILL.mdSave it as .claude/skills/todos-review/SKILL.md (or your agent's skills folder).
name
todos-review
description
Deep-review a single todo or backlog item to decide whether it is worth building: problem clarity, solution quality, and implementation priority. Dispatches platform-specific expert agents for readiness checks. Use when the user says "review this todo", "review todo", provides a todo file path, or wants a go/no-go recommendation before implementing a backlog item. This skill answers "should we build this at all" — for "is this the right way to build it", use `/plan-review` on the spec or implementation plan instead.

Todos Review

Review a todo or backlog item to evaluate problem clarity, solution quality, and implementation priority. Prevents over-engineering, catches missing cross-platform work, and surfaces better alternatives before any code is written.

Config Discovery

Resolve todo directory paths using the same config discovery as other todos-* skills:

  1. Use read_solopreneur_config todos via the cascade helper (see /todos-cleanup Config Discovery for the full setup including helper definitions)
  2. If absent, scan project for todo directories, confirm with user, save to config

See /todos-cleanup for the full discovery flow — use the same logic and config format.

Input

The todo file path comes from:

  1. The command argument: /todos-review todos/backlog/foo.md
  2. The current conversation context (user may have just pasted the path)
  3. If unclear, ask the user for the file path

Review Process

Run these steps in order. Steps 3–5 can be parallelized.

Step 1: Read the Todo

Read the full todo file. Extract:

  • Core problem: What user pain or technical debt is this solving?
  • Proposed solution: What changes are being proposed?
  • Current state described: What does the todo say about the current code?
Step 2: Verify Current State (Explore Agent)

Spawn an Explore subagent to read the relevant source files mentioned in the todo:

  • Is the current state described in the todo accurate, or has the code changed?
  • Has any part of this todo already been implemented? Assess completion as a percentage
  • Are there existing patterns the proposed solution might be ignoring?
  • Note where implementation diverges from the spec

Report discrepancies between the todo description and actual code.

Step 2.5: Short-Circuit for Completed Todos

If Step 2 reveals the todo is >80% implemented, skip Steps 3–6 and jump to "Output: Completion Review". A full architectural review is wasted effort on code that's already written — the user needs a gap analysis, not a design critique.

Step 3: Detect Tech Stack and Route to Expert Agent

Infer the tech stack from the codebase:

Detected filesPlatformSubagent
.xcodeproj / .swiftiOS/SwiftUIios-dev
build.gradle / .ktAndroid/Kotlinandroid-dev
LangGraph / agent workflowLLM/AI Agentai-engineer
*.cypher / Neo4j driverNeo4jneo4j-dev
package.json / .tsx / .jsxWeb / Next.jsgeneral-purpose
pyproject.toml / FastAPIPythongeneral-purpose
docs/gtm/ / BRAND.md / marketing copyMarketingmarketer
*.css / *.scss / design system filesDesigndesigner

Cross-platform todo (e.g., iOS + Android) → spawn two experts in parallel. If no platform detected → skip expert review.

Agent availability: each stack agent lives in its own sub-plugin (ios-dev, android-dev, ai-engineer, neo4j-dev). When dispatching in Step 4:

  • Success → proceed as normal.

  • Unknown-subagent-type error → do the review inline with generic expertise and prepend the stack's output with the template below, substituting <plugin> with the agent / plugin name for that stack (ios-dev, android-dev, ai-engineer, or neo4j-dev; the agent and plugin share the same name):

    ⚠️ Plugin <plugin> not installed. Review done with generic expertise. Install it for deeper, skill-index-backed review.

  • Any other Agent error → surface to the user; do not silently fall back.

Show full SKILL.md (324 more words)Show less
Step 4: Best Practice Check (Expert Subagent)

Spawn the matched subagent(s). Each agent already has access to its platform's skill index — no reference files needed. Prompt:

You are an expert reviewer, not an implementer. Do not write code or modify files.

Review the proposed solution in this todo against platform best practices:
1. Does the approach follow best practices for this platform? If not, what should change?
2. Are there existing codebase patterns the solution should follow? (search to verify)
3. Are there potential pitfalls or easily-missed implementation details?

Todo content:
[paste full todo]

Relevant files:
[list file paths mentioned in the todo]

Consult your skill index for relevant best practices, then provide analysis.
Report only — no code.

Skip condition: If the todo is trivially simple (< 10 lines of change, no architectural decisions), skip expert review to save time.

Step 5: Check Dependencies and Spec Conflicts
  • Search $BACKLOG and $DOING for related open todos that might block or be blocked
  • Search docs/spec/ for specs this todo might contradict
  • Check $DONE to see if a similar feature was attempted before
Step 6: Structured Evaluation

Evaluate across these dimensions:

A. Problem Clarity — Is the problem clearly defined? Real user pain or hypothetical?

B. Solution Simplicity — Is this the simplest path? Could fewer moving parts work? Could a product/UX change eliminate the need for code?

C. The "Don't Do It" Option — Explicitly consider not implementing. What's the cost of doing nothing?

D. Cross-Platform Consistency — If iOS or Android is involved, does the todo account for both platforms?

E. Destructiveness — Low / Medium / High

  • Low: UI-only changes, no data structure changes
  • Medium: Logic changes, new fields with defaults
  • High: Breaking data changes, migration required, removes functionality

F. Value — Low / Medium / High

  • Who benefits? How many users? Is it blocking other work?

G. Effort — S / M / L

  • S: < 1 day (~50 lines, one platform)
  • M: 1–3 days (both platforms, moderate logic)
  • L: > 3 days (migration, multi-screen, new data model)
Step 7: Output

Choose the output format based on Step 2's findings.

Output: Completion Review (>80% implemented)
markdown
## Todo Review: [filename] — Mostly Implemented

### Completion Status
| Item | Status | Notes |
|------|--------|-------|
| ... | Done/Partial/Missing | ... |

### Spec vs Implementation Gaps
[Differences between todo description and actual code — may be bugs or outdated spec]

### Remaining Work
[Checklist of incomplete items, prioritized]

### Recommendation
[Move to done / convert to checklist / update spec to match implementation]
Output: Full Review (<80% implemented)
markdown
## Todo Review: [filename]

### Core Problem
One sentence describing what this todo is really solving.

### Current State Check
[Is the todo's description of current code accurate? What's changed?]

### Solution Assessment
[Is the approach simplest? Are there better alternatives? Is "don't do it" viable?]

### Cross-Platform Consistency
[If applicable: are both iOS/Android covered?]

### Dependencies / Conflicts
[Blocked by other todos? Contradicts existing specs?]

### Ratings
| Dimension | Rating |
|-----------|--------|
| Destructiveness | Low/Medium/High + explanation |
| Value | Low/Medium/High + explanation |
| Effort | S/M/L + explanation |
| Readiness | Auto / Needs Discussion + explanation |

**Readiness criteria** — mark `Auto` only when **all** conditions are met:
1. Todo is a bug fix (not a new feature, refactor, or exploratory task)
2. Effort = S
3. Destructiveness = Low
4. Has clear acceptance criteria (how to verify the fix)
5. Mentions specific files or code paths
6. Solution has no ambiguity (only one reasonable interpretation)

If any condition fails, mark `Needs Discussion` and state which conditions failed.

### Implementation Benefits
[List only applicable items:]
- Bug fix: [what user-visible issue is resolved]
- UX improvement: [what experience improves]
- Performance: [what gets faster]
- Stability / test coverage: [what regressions are prevented]
- Cross-platform parity: [iOS/Android alignment]
- Tech debt cleanup: [what code smell is removed]

### Recommendation
[Do / don't do / modify approach — with the simplest implementation path]

Key Principles

  • Prefer deletion over addition. If a todo adds logic for an edge case, first ask whether the edge case can be eliminated.
  • Flag stale todos. If the code has changed and the todo's premise is outdated, call it out immediately.
  • One problem, one todo. If a todo solves 3 things, note it should be split.
  • Don't rubber-stamp. The purpose is to catch mistakes before implementation. Be direct about problems.

© hanamizuki, 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/solopreneur/todos-review of hanamizuki/solopreneur.

Open the folder on GitHubat commit f43f001

Compare with similar skills

Todos Review 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.

Todos Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Todos Review this skillhanamizuki/solopreneur152—~2.2kAutomated safety check: PassMIT
Refactor Design Reportpenwyp/ClaudePreference136—~1.4kAutomated safety check: PassMIT
Visual Dashboarddanielvm-git/bigpowers260—~478Automated safety check: PassMIT
SpikeDeL-TaiseiOzaki/claude-code-orchestra199—~6.9kAutomated safety check: PassMIT
Utility Pm Workflow Orchestratorproduct-on-purpose/pm-skills716—~2.5kAutomated safety check: PassApache-2.0
Agent Workflowmenkesu/awesome-pm-skills434—~5.2kAutomated safety check: PassCustom licence

Similar skills

  • Refactor Design Report

    penwyp/ClaudePreference

    Produce a professional, code-grounded refactor or implementation design report from identified technical problems, product gaps, review findings, architecture concerns, or frontend-backend contract…

    136 GitHub stars~1.4k tokensUpdated 4 mo ago
    Product & Project ManagementAuto-check passed

  • Visual Dashboard

    danielvm-git/bigpowers

    Start a browser-based dashboard that visualizes architecture, implementation plans, and project status.

    260 GitHub stars~478 tokensUpdated 19 days ago
    Product & Project ManagementAuto-check passed

  • Spike

    DeL-TaiseiOzaki/claude-code-orchestra

    Time-boxed technical investigation/feasibility study with Codex-first multi-agent collaboration (Codex + Opus 4.6 + Agent Teams).

    199 GitHub stars~6.9k tokensUpdated 20 days ago
    Agent WorkflowsAuto-check passed

  • Utility Pm Workflow Orchestrator

    product-on-purpose/pm-skills

    Run an ordered sequence of pm-skills against one input, pausing for go/no-go and stopping on a failed or empty step.

    716 GitHub stars~2.5k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

  • Agent Workflow

    menkesu/awesome-pm-skills

    Sets up how you and your team build and work with AI agents, and produces an Agent Workflow Charter (agent lanes, plan-mode loop, autonomy ladder with promotion criteria, rules file, review policy…

    434 GitHub stars~5.2k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed

  • Prod Activation Plan

    evolution-foundation/evo-nexus

    Create a phased activation plan using the EvoNexus standard structure — single index file + folder-per-phase + file-per-item, each item detailed with owner, dependencies, decisions pending…

    545 GitHub stars~2.9k tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed

More from hanamizuki/solopreneur

All 31 skills in this repo

  • Preview

    hanamizuki/solopreneur

    Create an interactive HTML preview of any proposal, plan, idea, doc, brief, or spec and land it in the browsable local Preview Library by default (opens under file:// with a catalog sidebar and…

    152 GitHub stars~5.2k tokensUpdated 14 days ago
    Auto-check passed

  • iOS Patterns

    hanamizuki/solopreneur

    A skill your agent uses when building iOS/macOS apps with SwiftUI — covers localization (String Catalogs), date/time formatting, JSON date decoding, Previews, state management, sheet/navigation…

    152 GitHub stars~2.3k tokensUpdated 14 days ago
    Auto-check: notes

  • Linkedin Growth

    hanamizuki/solopreneur

    LinkedIn organic growth consultant — diagnoses profiles, discusses goals, and co-creates a personalized 90-day growth plan.

    152 GitHub stars~3.7k tokensUpdated 14 days ago
    Auto-check passed

  • Perspective

    hanamizuki/solopreneur

    Switch perspectives to think through problems using the mental models of ten iconic thinkers: Elon Musk, Richard Feynman, Charlie Munger, Naval Ravikant, Steve Jobs, Nassim Taleb, Ilya Sutskever…

    152 GitHub stars~971 tokensUpdated 14 days ago
    Auto-check passed

  • Slide Design

    hanamizuki/solopreneur

    Create brand-aware presentations using frontend-slides or reveal.js.

    152 GitHub stars~3.9k tokensUpdated 14 days ago
    Auto-check passed

  • X Growth

    hanamizuki/solopreneur

    X/Twitter growth consultant — diagnoses profiles, discusses goals, and co-creates a personalized growth plan.

    152 GitHub stars~3.8k tokensUpdated 14 days ago
    Auto-check passed

Categories

Questions about Todos Review

What does Todos Review do?

Deep-review a single todo or backlog item to decide whether it is worth building: problem clarity, solution quality, and implementation priority. Todos Review is an agent skill from hanamizuki/solopreneur. Deep-review a single todo or backlog item to decide whether it is worth building: problem clarity, solution quality, and implementation priority.

When should I use Todos Review?

Todos Review fits situations like: the user says review this todo; provides a todo file path; wants a go/no-go recommendation before implementing a backlog item.

How do I install Todos Review in Claude Code?

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

How do I install Todos Review in Codex?

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

Can I use Todos Review 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 hanamizuki/solopreneur --skill todos-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/todos-review, .gemini/skills/todos-review, .github/skills/todos-review and .opencode/skills/todos-review in your project.

What does Todos Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Todos Review is instructions for the agent only. Our summary lists: Python 3.

Does Todos Review 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 Todos Review 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 Todos Review use?

Todos Review 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 Todos Review use?

About 2.2k tokens (SKILL.md is roughly 9k 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 Todos Review?

Skills that share tags, products or a category with Todos Review: Refactor Design Report (penwyp/ClaudePreference, 136 stars), Visual Dashboard (danielvm-git/bigpowers, 260 stars), Spike (DeL-TaiseiOzaki/claude-code-orchestra, 199 stars) and Utility Pm Workflow Orchestrator (product-on-purpose/pm-skills, 716 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Todos Review?

hanamizuki (a GitHub user) maintains it in hanamizuki/solopreneur, which has 152 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on September 26, 2026.

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