Tech Stack Eval

What it does

When your agent uses it

• Needs to choose between technologies
• Says which framework should I use
• Should we migrate from X to Y
• What database should I use

Example prompts

• “which framework should I use”
• “compare X vs Y”
• “should we migrate from X to Y”
• “/tech-stack-eval”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

1. 1Clarify the decision — What exactly is being decided and what are the real requirements? Push back if the user picks tech before defining…
2. 2Identify candidates — List 2-4 realistic options. Exclude clearly wrong choices early.
3. 3Define weighted evaluation criteria — Select 6-8 criteria from the master list below. Assign weights based on the user's priorities (total…
4. 4Score each candidate — Rate 1-5 on each criterion with one-line justification per score.
5. 5Assess ecosystem health — Evaluate GitHub activity, npm/PyPI adoption, community strength, corporate backing, and trajectory (growing…
6. 6Calculate TCO — Project 5-year total cost including compute, storage, bandwidth, licensing, engineering time (setup + ongoing), and…
7. 7Analyze migration path — If migrating, estimate effort, risks, timeline, and recommend phased approach (strangler fig pattern).
8. 8Deliver recommendation — Clear winner with rationale and confidence level. No "it depends" without a follow-up question to resolve the…

What it can do on your machine

Read from SKILL.md and the folder at commit 4ad31b4. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • heroku
  • aws

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use aws, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Tech Stack Eval loads about 2k tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 706 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~57

When it runs · the whole SKILL.md, loaded when a task matches

~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from shawnpang/startup-founder-skills at commit 4ad31b4, republished under its MIT licence (© shawnpang). 706 words, ~2,005 tokens.

name

tech-stack-eval

description

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".

related

architecture-design, cicd-setup

reads

startup-context

# Tech Stack Evaluation: [Decision Title]

## Decision Context — what we are choosing and why it matters
## Candidates — table: technology, version, license, one-liner
## Evaluation Criteria — table: criterion, weight, why it matters
## Scoring Matrix — table: criterion (weight), scores per option, weighted total
## Ecosystem Health — table: GitHub stars, weekly downloads, last release, open issues, major users
## TCO Estimate — table: cost category by option over 12 months or 5 years
## Security & Compliance — vulnerability history, compliance readiness (SOC 2, GDPR)
## Recommendation — clear winner, rationale, confidence level, caveats
## Migration Path (if applicable) — phased plan with timeline and rollback strategy

## Scoring Matrix
| Criterion (weight)       | React | Vue  |
|--------------------------|-------|------|
| Developer Productivity (40%) | 4/5   | 4/5  |
| Ecosystem (30%)          | 5/5   | 4/5  |
| Performance (30%)        | 4/5   | 5/5  |
| **Weighted Total**       | **4.3** | **4.3** |

Confidence: Medium (55%). Scores are nearly identical. Recommendation: React,
but only because your team has 2 years of React experience (not captured in
the matrix). If the team were greenfield, Vue's developer experience gives it
a slight edge. This is close enough to warrant team preference as the tiebreaker.

## TCO Estimate (12 months)
| Category             | Heroku    | AWS               |
|----------------------|-----------|-------------------|
| Compute              | $1,200/mo | $480/mo (ECS)     |
| Database             | $800/mo   | $350/mo (RDS)     |
| Add-ons              | $400/mo   | $120/mo           |
| Engineering (setup)  | $0        | $12,000 one-time  |
| Engineering (ongoing)| 2 hrs/mo  | 8 hrs/mo          |
| **Annual Total**     | **$28,800** | **$18,000**     |

Break-even at month 14. At Series A with a team of 6, wait until Heroku hits
$4,000/mo — engineering hours are better spent on product right now.

© shawnpang, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/tech-stack-eval of shawnpang/startup-founder-skills.

Open the folder on GitHubat commit 4ad31b4