product-analysis

An agent skill by daymade, from daymade/claude-code-skills. Tags: analysis, brainstorming, multi-agent, optimization, product-strategy.

What it does

Multi-path parallel product analysis with cross-model test-time compute scaling. Spawns parallel agents (Claude Code agent teams + Codex CLI) to explore product from multiple perspectives, then synthesizes findings into actionable optimization plans. Can invoke competitors-analysis for competitive benchmarking. Use when "product audit", "self-review", "发布前审查", "产品分析", "analyze our product", "UX audit", or "信息架构审计".

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add daymade/claude-code-skills --skill product-analysis

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/daymade/claude-code-skills
cp -r claude-code-skills/product-analysis ~/.claude/skills/product-analysis

Safety box score

Grade D, elevated risk: 47 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is an analysis orchestrator, but it launches shell commands and Codex CLI in parallel, with Codex explicitly allowed to run autonomously in the project directory. The main risks are command execution, repository data being sent to OpenAI-backed tooling, and instructions that bypass normal approval prompts while inspecting config files that may include secrets.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	3 (high)	It directly runs shell checks like `which codex`/`ls ...` and instructs Codex CLI to execute in `--full-auto` mode, which is autonomous command execution.
Network access	2 (moderate)	It uses Codex CLI with an OpenAI account (`Requires OpenAI API key configured`) and sends analysis prompts derived from the repository to a remote model.
Filesystem reach	1 (low)	The workflow reads project files and runs Codex in the project's working directory; it does not explicitly target paths outside the workspace.
Secrets & credentials	2 (moderate)	The analysis targets config files including `.env`/`.env.example` and asks for config consistency, so it may surface or inspect sensitive environment material.
Privilege & persistence	0 (none)	No sudo, service registration, global installs, or shell-startup/OS setting changes are requested.
Instruction hijack surface	3 (high)	The docs explicitly encourage approval bypass with `--full-auto` (`Skip all approval prompts`) and even mention the legacy `--dangerously-bypass-approvals-and-sandbox` flag.
Irreversible actions	0 (none)	It automates analysis and synthesis but does not push, post, deploy, pay, delete, or otherwise take external-world actions.
Transparency	0 (none)	All provided files are readable markdown; there are no binaries, encoded blobs, or hidden runtime-decoded scripts.

Before installing

Read `references/codex_patterns.md` and decide whether you accept `--full-auto` / sandbox-bypass behavior.
Check whether the repo contains real `.env` or other secret-bearing config before running the skill.
Run it first on a throwaway clone or unprivileged account, with the OpenAI/Codex credential you intend to use.
Verify which files the skill may inspect in your workspace and whether that is acceptable for your data policy.

Rated 2026-10-20 by an automated review of 4 files from the skill's repository.

Source

Repository: daymade/claude-code-skills (all skills from this repository)
Path: product-analysis/SKILL.md
Branch: main
Updated: 2026-09-20

arena — Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.
pricing — When the user wants help with pricing decisions, packaging, or monetization strategy.
principle-guard-the-context-window — Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning.
reflect — Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill.
coordinating-multi-space-devops-agent — Coordinate the AWS DevOps Agent across multiple AgentSpaces from one Claude Code session — route questions to the right space (prod vs staging vs knowledge).
interpreting-culture-index — Interprets Culture Index (CI) surveys, behavioral profiles, and personality assessment data.