← Back to Skills Marketplace
vincentjiang06

Headphone Review

by VincentJiang06 · GitHub ↗ · v1.0.5 · MIT-0
cross-platform ✓ Security Clean
115
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install headphone-review
Description
Use this skill when the user wants a buyer-facing long review of a headphone, IEM, earbud, or TWS model by name. Use AskUserQuestion in option mode first for...
README (SKILL.md)

Headphone Review

Use this skill when the user names a headphone, IEM, earbud, or TWS model and wants a buyer-facing long review: what it sounds like, who it fits, who should skip it, and where reviewers agree or disagree.

When web lookup is needed, also use $web-access or the environment's browsing tools.

Trigger Hints

  • Model-name requests such as WH-1000XM5, IE 900, Blessing 3, Susvara
  • Questions like 这耳机适合谁, 什么声音, 值不值得买, fit, sound signature, should I buy
  • Requests to aggregate multilingual reviews into one conclusion

Do not use this skill for pure repair, firmware, pairing, or EQ-only tasks unless the user also wants a buying summary.

Workflow

  1. Ask the missing preference questions first with AskUserQuestion in option mode, not as free-form text. Language options: 中文, English Description mode options: 客观(偏理性、直接), 情绪化抽象(偏氛围、意象) Read rules/intake.md.

  2. Gather multilingual evidence and reduce it into facts, consensus, and uncertainty. Read rules/research.md.

  3. Write the review in pure Markdown with the chosen language and description mode. Read rules/output.md and rules/humanize.md.

  4. If you are validating sample outputs, score them against the eval rules. Read rules/eval.md.

Done When

The review clearly answers:

  1. what it sounds like
  2. strengths and weaknesses
  3. who should buy it
  4. who should avoid it
  5. where reviewers disagree and why
  6. confidence level and evidence boundary
Usage Guidance
This skill appears coherent and safe to install: it only contains runtime instructions for asking the user two options (language and description mode), researching public reviews via the agent's browsing tools, and producing a structured Markdown review. Things to consider before enabling: (1) the skill will perform web lookups — verify your agent's browsing tool and privacy settings if you care about what web requests are made; (2) the output is intentionally not supposed to include a Sources section (rules forbid adding source lists), so you may get synthesized conclusions without an explicit bibliography — expect limited traceability of individual claims; (3) the skill enforces stylistic and content constraints (hard bans on certain templates and punctuation) which may affect tone and phrasing; (4) since it gathers third-party reviews, verify factual points (specs, revisions) against official pages if accuracy is critical. No secrets or elevated privileges are required.
Capability Analysis
Type: OpenClaw Skill Name: headphone-review Version: 1.0.5 The skill bundle is a well-structured tool for generating detailed headphone reviews. It utilizes a modular approach with specific rule files (rules/research.md, rules/humanize.md, etc.) to guide the agent through data collection, stylistic formatting, and quality evaluation. There is no evidence of malicious intent, data exfiltration, or unauthorized execution; the instructions are strictly focused on the stated purpose of product reviewing and improving prose quality.
Capability Assessment
Purpose & Capability
Name/description match the actual instructions: gather multilingual reviews, ask the user language/style options, synthesize a Markdown review. No unrelated binaries, env vars, or config paths are requested.
Instruction Scope
SKILL.md stays on-task: it requires asking two intake questions, collecting multiple review sources (including official/spec pages), and producing a structured Markdown review with a disagreement section. It does not instruct reading unrelated files, accessing credentials, or sending data to unknown endpoints. It does rely on the environment's web-access/browsing tools for research, which is appropriate for the stated purpose.
Install Mechanism
No install spec or code files to be downloaded or executed—this is an instruction-only skill, the lowest-risk category for installation.
Credentials
The skill requests no environment variables, credentials, or config paths. It references a $web-access browsing tool (expected for research) but does not declare or require any secrets.
Persistence & Privilege
always:false and default model invocation are set (normal). The skill does not request permanent presence, nor does it modify other skills or system-wide settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install headphone-review
  3. After installation, invoke the skill by name or use /headphone-review
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.5
Enforce option-style AskUserQuestion at the entry layer for language and description mode.
v1.0.4
Add 1.0.4 humanization rules and tighter article structure.
Metadata
Slug headphone-review
Version 1.0.5
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is Headphone Review?

Use this skill when the user wants a buyer-facing long review of a headphone, IEM, earbud, or TWS model by name. Use AskUserQuestion in option mode first for... It is an AI Agent Skill for Claude Code / OpenClaw, with 115 downloads so far.

How do I install Headphone Review?

Run "/install headphone-review" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Headphone Review free?

Yes, Headphone Review is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Headphone Review support?

Headphone Review is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Headphone Review?

It is built and maintained by VincentJiang06 (@vincentjiang06); the current version is v1.0.5.

💬 Comments