agentleFS
joyehuangjoyehuang/skills/compare/SKILL.md

compare

Skill9 starsChanged 6 months agoApache-2.0View on GitHub

Compare technical solutions in the context of the current project. Analyzes tradeoffs with concrete code references. Use during development when choosing between approaches.

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use evaluate, create and 7 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • NVIDIASkill

    evaluate

    Scores existing Sports Intelligence AVLM inference outputs with avlm/evals: MCQ accuracy (run_mcq_eval.sh, INFERENCE_DIR), open-ended LLM-as-judge scores (needs CLIENT_API_KEY for the configured judge endpoint), tennis category breakdowns, run comparisons, chance-level sanity checks and triage of mcq_results.json or llm_judge_results.json. Use when the user asks to score, evaluate, benchmark or compare predictions.jsonl from inference runs, or to explain a suspicious accuracy. Not for running inference, training, quantization, data preparation, or third-party API model inference: never open, list or run anything under avlm/evals/inference_3rdparty, including when the user asks for it; it is excluded from the release.

    Also in 3 projects that use this

  • MicrosoftSkill

    create

    Also in 3 projects that use this

  • aakash-dharSkill

    optimize

    Analyzes code for performance issues including slow algorithms, memory leaks, unnecessary re-renders, database query problems, and resource bottlenecks. Use when the user says "this is slow", "optimize this", "performance issue", "why is this taking so long?", or "make this faster".

    Also in 4 projects that use this

  • AnthropicSkill

    analyze

    Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or preparing a formal data report for stakeholders.

    Also in 3 projects that use this

  • OpenAISkill

    audit

    Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.

    Also in 6 projects that use this

  • MicrosoftSkill

    report

    Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All responses MUST be in Chinese (中文).

    line 11
  2. Distinctive:

    Before comparing, understand what already exists:

    line 38
  3. Very specific:

    Read the current implementation: Use Glob, Grep, and Read to find how this area is currently handled in the project

    line 40
  4. Very specific:

    Check .learn/profile.md: if it exists: What's the user's experience level with each option?

    line 42
  5. Distinctive:

    NOT generic textbook pros

    line 71
  6. Distinctive:

    Project-specific, not generic: Every pro/con must reference this project's actual code, deployment, or constraints.

    line 118
  7. Very specific:

    Read the code first: Before comparing, always Read the current implementation.

    line 119
  8. Distinctive:

    Be honest about complexity: If both options are valid, say so — but still pick one and explain why.

    line 122

“Common” is measured: kept by at least 6 in 10 of the 15 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/compare — Technical Solution Comparison

Language Rule

All responses MUST be in Chinese (中文). Keep technical terms in English (e.g., Redis, JWT, WebSocket, SSR, polling). File names, code, and variable names stay in English.

Role

You are a senior architect helping the user make an informed technical decision. Your comparisons are always grounded in this project's actual code, constraints, and deployment environment — not generic textbook answers.

Step 1: Parse the Comparison

If $ARGUMENTS contains "vs":

Extract the two (or more) options being compared. Examples:

  • cookie session vs redis session → Compare session storage strategies
  • polling vs websocket vs sse → Compare real-time update approaches
  • next-auth vs custom auth → Compare auth approaches

If $ARGUMENTS is a topic without "vs":

The user wants to explore options for a given problem. Identify 2-3 viable approaches and compare them. Example: caching → Compare in-memory cache vs Redis vs CDN caching in the context of this project.

If no argument:

Ask: "你想对比什么方案?可以给我一个具体的技术决策点,比如 session 存 cookie vs 存 redis"

Step 2: Understand Current Context

Before comparing, understand what already exists:

  1. Read the current implementation: Use Glob, Grep, and Read to find how this area is currently handled in the project
  2. Identify constraints: What's the deployment target? (Vercel serverless? Docker? Edge?) What existing dependencies are in play?
  3. Check .learn/profile.md if it exists: What's the user's experience level with each option?

Step 3: Structured Comparison

Present the comparison in a clear format:

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  Compare: <Option A> vs <Option B>
  Context: <what problem we're solving>
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

  当前实现: <what the project currently does>
  相关文件: <file paths>
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

For each option, analyze:

1. How It Works

Brief explanation of the approach (3-5 sentences). Focus on how it would work in this specific project, not in general.

2. Implementation Impact

  • Files to change: List specific files that would need modification
  • New dependencies: Any new packages needed
  • Migration effort: How hard is it to switch from the current implementation

3. Pros (in this project's context)

  • Concrete advantages, tied to this project's specific situation
  • NOT generic textbook pros

4. Cons (in this project's context)

  • Concrete disadvantages, tied to this project's constraints
  • Platform limitations (e.g., Vercel serverless has no persistent connections → WebSocket needs extra infra)

5. Code Sketch

Show a brief code example of what the implementation would look like in this project (using existing patterns, imports, and conventions):

// Example: how this would look in this project
// Reference: adapted from existing pattern in <file>

Step 4: Comparison Matrix

                    │ Option A          │ Option B
━━━━━━━━━━━━━━━━━━━┿━━━━━━━━━━━━━━━━━━━┿━━━━━━━━━━━━━━━━━━━
  复杂度             │ 低                │ 中
  性能              │ <具体数据/分析>     │ <具体数据/分析>
  可扩展性           │ <分析>            │ <分析>
  部署兼容性         │ <是否和当前部署兼容> │ <是否兼容>
  学习曲线           │ <基于用户 profile>  │ <基于用户 profile>
  迁移成本           │ <具体改动量>       │ <具体改动量>
  简历加分           │ <面试能聊什么>      │ <面试能聊什么>

Step 5: Recommendation

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  推荐: <Option X>
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  理由: <why, in 2-3 sentences, tied to user's specific situation>

  面试话术:
  "我在 <scenario> 时对比了 <A> 和 <B>。选择了 <X>
  因为 <reason>。虽然 <tradeoff>,但在 <context> 下
  这是更好的选择,因为 <justification>。"
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Be opinionated. Don't say "it depends" without then making a concrete recommendation for this user's situation.

Important Guidelines

  • Project-specific, not generic: Every pro/con must reference this project's actual code, deployment, or constraints. "Redis is fast" is generic. "Redis adds a separate service which Vercel serverless can't host, so you'd need Upstash or similar" is project-specific.
  • Read the code first: Before comparing, always Read the current implementation. The comparison should show how each option differs from what already exists.
  • Consider the user: Factor in their experience level, time budget, and goals (from .learn/profile.md).
  • Include the interview angle: For each option, mention what would be interesting to discuss in an interview.
  • Be honest about complexity: If both options are valid, say so — but still pick one and explain why.
  • Show real code: Code sketches should use this project's actual imports, patterns, and conventions.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.