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".
65
57%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/tech-stack-eval/SKILL.mdQuality
Discovery
37%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is essentially a list of trigger phrases with no explanation of what the skill actually does. While the trigger terms are strong and natural, the complete absence of capability descriptions (what actions it performs, what outputs it produces) makes it impossible for Claude to understand the skill's value proposition. It reads as a 'when' clause without a corresponding 'what' clause.
Suggestions
Add concrete capability descriptions before the trigger phrases, e.g., 'Generates structured technology comparison matrices, calculates total cost of ownership, and produces migration risk assessments with pros/cons analysis.'
Restructure to follow the pattern: '[What it does]. Use when [triggers].' — e.g., 'Compares technologies, frameworks, and tools using weighted criteria, TCO analysis, and migration feasibility assessment. Use when the user asks...'
Specify the outputs or deliverables the skill produces (e.g., comparison tables, recommendation summaries, TCO breakdowns) to distinguish it from generic advisory skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions describing what the skill actually does. It only lists trigger phrases without specifying capabilities like 'generates comparison matrices', 'calculates TCO', or 'produces migration risk assessments'. | 1 / 3 |
Completeness | The description only addresses 'when' (trigger conditions) but completely omits 'what' — there is no explanation of what the skill actually does or produces. The rubric states a missing 'Use when...' clause caps completeness at 2, and analogously, missing the 'what' portion is equally problematic. | 1 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'which framework should I use', 'compare X vs Y', 'should we migrate from X to Y', 'what database should I use', 'calculate TCO'. These are realistic, varied user phrases. | 3 / 3 |
Distinctiveness Conflict Risk | The trigger terms like 'compare X vs Y' and 'which framework' provide some specificity to a technology comparison niche, but without describing concrete outputs or actions, it could overlap with general advice-giving or research skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable skill with a well-defined workflow and excellent concrete examples that demonstrate exactly what good output looks like. Its main weakness is length — at ~150 lines with multiple inline reference tables, it could benefit from splitting detailed frameworks into separate files. The content is mostly efficient but includes some explanations of concepts Claude already knows.
Suggestions
Move the detailed reference tables (Master Evaluation Criteria definitions, Ecosystem Health Scoring, TCO Calculation Framework, Migration Risk Assessment, Confidence Levels) into a separate REFERENCE.md file and link to it, keeping only brief summaries inline.
Trim criterion descriptions in the master list — Claude knows what 'performance' and 'scalability' mean; just list the criteria names with the specific lens to apply (e.g., 'Performance — score for the specific workload, not benchmarks').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive and mostly efficient, but includes some content that could be tightened — e.g., the 'Do NOT use when' section states obvious things, the master criteria list explains concepts Claude already understands (like what 'performance' or 'scalability' mean), and the confidence levels table is somewhat redundant. However, it avoids egregious padding. | 2 / 3 |
Actionability | The skill provides highly concrete, executable guidance: a clear 8-step workflow, specific output format with table structures, weighted scoring methodology, TCO calculation categories, and two detailed examples with realistic numbers showing exactly what good output looks like. The examples are copy-paste ready templates. | 3 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced with logical progression from clarification through recommendation. It includes validation-like checkpoints (push back on solution-first thinking, set confidence levels, recommend PoC for low-confidence decisions). The migration section includes the strangler fig pattern with rollback capability and a concrete anti-pattern warning about half-migrated systems. | 3 / 3 |
Progressive Disclosure | The skill references related skills (architecture-design, cicd-setup) and startup-context, which is good. However, the content is quite long and monolithic — the master evaluation criteria, ecosystem health scoring, TCO framework, migration risk assessment, and confidence levels could be split into referenced files. The inline tables and frameworks make this a dense single file when some content could be progressively disclosed. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- shawnpang/startup-founder-skills
- Commit
4ad31b4
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.