Tech Stack Eval

When the user needs to choose between technologies, frameworks, or tools — or says "which framework should I use", "compare X vs Y", "should we migrate from X to Y", "what database should I use", "calculate TCO".

393 stars 46 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add shawnpang/startup-founder-skills --skill tech-stack-eval
Manual install
git clone --depth 1 https://github.com/shawnpang/startup-founder-skills.git /tmp/startup-founder-skills
mkdir -p ~/.claude/skills
cp -r /tmp/startup-founder-skills/skills/tech-stack-eval ~/.claude/skills/tech-stack-eval

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Tech Stack Evaluation

## When to Use

- Comparing frontend/backend frameworks or libraries for new projects
- Evaluating cloud providers (AWS vs Azure vs GCP) for specific workloads
- Planning technology migrations with risk and effort assessment
- Calculating TCO including hidden costs; making build vs. buy decisions
- Assessing open-source library viability and ecosystem health

Do NOT use when: the decision is trivial (use team preference), the technology is already mandated, or this is an emergency production issue.

## Context Required

From `startup-context`: product type, team skills, tech stack, stage, scale, budget. Also ask:
- What problem are you solving? (push back on solution-first thinking)
- Non-negotiable requirements (performance, compliance, team familiarity)
- Team experience with each option and timeline pressure (tight deadlines favor familiar tools)
- Growth expectations that affect scalability requirements

## Workflow

1. **Clarify the decision** — What exactly is being decided and what are the real requirements? Push back if the user picks tech before defining the problem.
2. **Identify candidates** — List 2-4 realistic options. Exclude clearly wrong choices early.
3. **Define weighted evaluation criteria** — Select 6-8 criteria from the master list below. Assign weights based on the user's priorities (total = 100%).
4. **Score each candidate** — Rate 1-5 on each criterion with one-line justification per score.
Read the full skill on GitHub

Details

Skill name
tech-stack-eval
Path
skills/tech-stack-eval/SKILL.md
License
MIT
Repo updated
16 March 2026

FAQ

What does the Tech Stack Eval skill do?

When the user needs to choose between technologies, frameworks, or tools — or says "which framework should I use", "compare X vs Y", "should we migrate from X to Y", "what database should I use", "calculate TCO".

How do I install the Tech Stack Eval skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add shawnpang/startup-founder-skills --skill tech-stack-eval. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Tech Stack Eval popular?

It lives in shawnpang/startup-founder-skills, which has 393 GitHub stars and 46 forks.

Related skills

Accelerator Application

393

shawnpang/startup-founder-skills

When the user wants to apply to startup accelerators, incubators, or fellowship programs. Also use when the user mentions "YC application", "Techstars", "accelerator", or "apply to programs".

Software Development46

Architecture Design

393

shawnpang/startup-founder-skills

When the user needs to design or evaluate system architecture — service boundaries, data models, API contracts, infrastructure topology, database selection, or dependency analysis. Also activate for "design the system", "how should I architect this", "monolith vs microservices", or architecture decision records.

Software Development46

Board Update

393

shawnpang/startup-founder-skills

When the user needs to write a monthly or quarterly investor update, prepare a board deck, or communicate company progress to stakeholders.

Finance & Crypto46

China AI Compliance Audit

139

jnMetaCode/shellward

按中国法规(网安法 / PIPL / 等保2.0 / 数据出境 / AI生成内容标识)审计一个 AI 项目的代码仓库,产出每条都带 文件:行 取证、经独立复核、经脚本校验的合规报告。当用户问「这个项目上线合不合规」「调用了 OpenAI/Claude 算不算数据出境」「要不要做 AI 标识」「帮我做合规自查/等保/PIPL 检查」时使用。Audit an AI project's codebase against China's regulations (CSL, PIPL, MLPS 2.0, cross-border data transfer, AI content labeling) with file:line evidence, independent verification and a deterministic validator.

AI, LLMs & AgentsIn 1 list24

Caveman Stats

155

kubestellar/console

Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.

AI, LLMs & AgentsIn 1 list139

Hol Guard

197

nextlevelbuilder/skillx

Use when setting up HOL Guard, protecting local AI harnesses, reviewing Guard approvals or receipts, or scanning agent plugins, skills, MCP servers, and marketplace packages before use.

AI, LLMs & Agents47

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.