Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Pm User Research · echovic | DecimalAI

researchby echovic

Pm User Research

echovic/pm-user-research

Source echovic/boss-skill ↗License MIT

用户研究方法，通过用户画像和用户旅程图，深入理解目标用户的特征、需求和行为

SkillScore74Maintained

Automatic

Product Management pack

Last verified 8/19/2026

What it changes

Passed 17 of 23 test cases with the skill, and 15 of 23 without it.

Without skill65%

With skill74%

Checks it passed that the model alone missed

Structures pain point scenarios with 场景描述, 当前解决方案, 痛点, and 情绪
Includes the six stages: 认知阶段, 考虑阶段, 购买/注册阶段, 首次使用阶段, 持续使用阶段, and 推荐阶段

2 fixed15 passed either way6 still failing0 broke

Pass-rate lift: +9 pp
Tokens: +71%
Agent turns: 0%
Response time: +3%

Model gemini-3.6-flashMeasured 8/19/2026v117 of 23 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/echovic-pm-user-research/SKILL.md https://app.decimal.ai/s/echovic-pm-user-research/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add echovic-pm-user-research, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/echovic-pm-user-research/ and pins it in .decimal/skills.lock

decimalai skills add echovic-pm-user-research

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/echovic-pm-user-research/SKILL.md https://app.decimal.ai/s/echovic-pm-user-research/SKILL.md

Raw file: /s/echovic-pm-user-research/SKILL.md ↗ · machine-readable summary at /s/echovic-pm-user-research.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 2

Prompt

在设计二手交易平台的买家用户画像时，团队写下了'希望能买到便宜的好东西'作为痛点。请纠正这种宽泛的需求描述，按照痛点场景模板展开具体的细节描述。

What was checked, without and with the skill
Checked	Without skill	With skill
Structures pain point scenarios with 场景描述, 当前解决方案, 痛点, and 情绪	Missed	Passed

case-13 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md229 linessingle file

用户研究方法论

适用场景

在产品设计前，需要深入理解目标用户是谁、他们的特征是什么、他们在什么场景下使用产品、他们的行为路径是什么。

核心方法

1. 用户画像 (User Persona)

用户画像是对目标用户的具象化描述，帮助团队建立对用户的共同理解。

用户画像模板

用户画像 1：[给用户起个名字，如"技术小白张三"]

基本特征：
- 年龄：[年龄段]
- 职业：[职业]
- 收入：[收入水平]
- 教育：[教育背景]
- 地域：[所在地区]
行为特征：
- 使用习惯：[如何使用类似产品]
- 技术水平：[对技术的熟悉程度]
- 使用频率：[多久使用一次]
- 使用时长：[每次使用多久]
- 设备偏好：[PC/移动端/平板]
心理特征：
- 性格特点：[如保守/激进、理性/感性]
- 价值观：[看重什么]
- 动机：[为什么使用产品]
- 顾虑：[担心什么]
核心需求：
- 最想解决的问题：[核心痛点]
- 期望的结果：[想要达成什么]
- 愿意付出的代价：[时间/金钱/学习成本]

Track record

Benchmark

17 / 23

test cases passed, vs 15 / 23 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

echovic / boss-skill

skill/skills/pm/user-research/SKILL.md

View on GitHub ↗

License MITImported 10/2/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.