SKILLEMALL.ai
GitHub ↗ RU Sign in

FF software-manager-skill

软件产品经理/软件开发经理知识技能。当用户需要产品经理级别的专业支持时触发，包括： 需求分析、PRD撰写、产品设计、产品路线图规划、竞品分析、数据分析； 或用户询问产品经理职责、如何成为产品经理、产品经理技能要求； 或需要产品架构图、流程图、时序图、甘特图等 Mermaid 图表； 或需要从0到1输出PRD文档并自动生成可交互H5原型图； 或需要将PRD文档导出为Markdown(.md)或Word(.docx)格式。 注意：本 skill 采用主动式产品咨询流程。流程：确认需求 → 提问澄清 → 网络搜索 + RAG搜索 → 产品规划 → 方案对比 → 技术选型 → 需求确认 → PRD文档 + Mermaid图表 → 导出格式 → H5原型图（可选）。

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: yhongm v2.2.0 MIT-0 28 files body ≈ 10 404 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 32/100 · Will not run — References files that are not bundled: references/icon-libraries/icon-sources.txt, references/h5-prototype/

ProcedureWordAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
F
21/100
safety, quality, tests
Safety 60%
0
Quality 40%
52
Run on models
none yet
Process rating
F
32/100
Will not run
References files that are not bundled: references/icon-libraries/icon-sources.txt, references/h5-prototype/
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Obfuscation
If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  3. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  4. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 11

  • high Obfuscation uni-zero-width references/tailwind-core/animation.txt:1
    Zero-width / invisible characters (possible hidden text) (13 occurrences)
    Animation - TailwindCSS中文文档 | TailwindCSS中文网Tailwind CSS home page…ing CatalystA modern application UI kit for ReactThemeTailwind CSS on GitHubSea…
  • high Obfuscation uni-zero-width references/tailwind-core/configuration.txt:1
    Zero-width / invisible characters (possible hidden text) (12 occurrences)
    Configuration - TailwindCSS中文文档 | TailwindCSS中文网Tailwind CSS home page…ing CatalystA modern application UI kit for ReactThemeTailwind CSS on GitHu…
  • high Obfuscation uni-zero-width references/tailwind-core/content-configuration.txt:1
    Zero-width / invisible characters (possible hidden text) (5 occurrences)
    Content Configuration - TailwindCSS中文文档 | TailwindCSS中文网Tailwind CSS home page…ing CatalystA modern application UI kit for ReactThemeTailwind CSS …
  • high Obfuscation uni-zero-width references/tailwind-core/dark-mode.txt:1
    Zero-width / invisible characters (possible hidden text) (6 occurrences)
    Dark Mode - TailwindCSS中文文档 | TailwindCSS中文网Tailwind CSS home page…ing CatalystA modern application UI kit for ReactThemeTailwind CSS on GitHubSea…
  • high Obfuscation uni-zero-width references/tailwind-core/Functions-and-directives.txt:1
    Zero-width / invisible characters (possible hidden text) (8 occurrences)
    Functions & Directives - TailwindCSS中文文档 | TailwindCSS中文网Tailwind CSS home page…ing CatalystA modern application UI kit for ReactThemeTailwind…
  • high Obfuscation uni-zero-width references/tailwind-core/hover-focus-and-other-states.txt:1
    Zero-width / invisible characters (possible hidden text) (6 occurrences)
    Handling Hover, Focus, and Other States - TailwindCSS中文文档 | TailwindCSS中文网Tailwind CSS home page…ing CatalystA modern application UI kit for React…
  • high Obfuscation uni-zero-width references/tailwind-core/responsive-design.txt:1
    Zero-width / invisible characters (possible hidden text) (8 occurrences)
    Responsive Design - TailwindCSS中文文档 | TailwindCSS中文网Tailwind CSS home page…ing CatalystA modern application UI kit for ReactThemeTailwind CSS on G…
  • high Obfuscation uni-zero-width references/tailwind-core/theme.txt:1
    Zero-width / invisible characters (possible hidden text) (9 occurrences)
    Theme Configuration - TailwindCSS中文文档 | TailwindCSS中文网Tailwind CSS home page…ing CatalystA modern application UI kit for ReactThemeTailwind CSS on…
  • high Obfuscation uni-zero-width references/tailwind-core/utility-first.txt:1
    Zero-width / invisible characters (possible hidden text) (3 occurrences)
    Utility-First Fundamentals - TailwindCSS中文文档 | TailwindCSS中文网Tailwind CSS home page…ing CatalystA modern application UI kit for ReactThemeTailwind…
Medium and low: 2
  • low Secrets in code secret-high-entropy-token references/tailwind-core/customization.txt:1
    High-entropy token-like string (may be an id, hash or a credential)
    404 - TailwindCSS中文文档 | TailwindCSS中文网Tailwind CSS home page…ing CatalystA modern application UI kit for ReactThemeTailwind CSS on GitH…his page could not be found.
  • low Dangerous commands cmd-privilege scripts/mermaid_render_multi.js:287
    Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)
    const args = ['--no-sandbox', '--disable-setuid-sandbox', '--disable-dev-shm-usage'];
    detectorcode literal

Files scanned: 28. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 10404 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/icon-libraries/icon-sources.txt
  • warning missing-ref reference to a missing file: references/h5-prototype/
  • note frontmatter-key unknown frontmatter key "trigger"
  • note frontmatter-key unknown frontmatter key "hermes"
  • note frontmatter-key unknown frontmatter key "required_commands"
  • note frontmatter-key unknown frontmatter key "required_npm_packages"
  • note frontmatter-key unknown frontmatter key "required_python_packages"
  • note frontmatter-key unknown frontmatter key "required_environment"
  • note frontmatter-key unknown frontmatter key "notes_on_dependencies"

Process rating: all ten parameters 32/100

Will not run. References files that are not bundled: references/icon-libraries/icon-sources.txt, references/h5-prototype/
  • 0Tools and files. 2 referenced file(s) missing: references/icon-libraries/icon-sources.txt, references/h5-prototype/
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 40Execution cost. Instruction body is 10404 tokens: crowds the task out of the window
  • 100Steps. 74 steps
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. No mutating operations
  • low 21 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (5 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -228 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +3Description length 332: enough signal without eating the budget
  • +4Structure: 62 headings
  • +3Step-by-step instructions: 74 items
  • +4Has examples (29 code blocks)
  • +4Reference files are cited in the instructions (8 of 13)
  • +3All 2 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 52.

External checks

ClawHub: clean
This is a coherent product-management helper with disclosed web research, local reference use, and optional export scripts; I found no hidden credential use, persistence, purchases, or destructive behavior.
LLM: benign (medium) · VirusTotal: · 29 May 2026