CtrlK
BlogDocsLog inGet started
Tessl Logo

vibe-techdesign

Write an MVP technical design from agreed requirements, including architecture choices and relevant tradeoffs.

56

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./templates/.agents/skills/vibe-techdesign/SKILL.md

The canonical home for this skill is vibe-techdesign in KhazP/vibe-coding-prompt-template

SKILL.md
Quality
Evals
Security

Quality

Content

76%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an exceptionally lean, opinionated set of instructions with well-managed references and real bundle files backing them. Its main weakness is workflow presentation: the process lives in an unsegmented prose block with only implicit validation, and concrete deliverable structure is referenced but never exemplified.

Suggestions

Make the workflow sequence explicit with numbered steps (gather requirements → inspect stack → decide architecture → draft the design doc → emit Handoff Context) and add explicit validation checkpoints such as re-verifying integration contracts against the inspected code before finalizing.

Add section headings (e.g. '## Process', '## Output', '## References') so the dense prose block is navigable at a glance, completing the otherwise strong progressive-disclosure structure.

DimensionReasoningScore

Conciseness

The body is ~30 lines of dense imperative guidance with zero padding — no concept explanations, no library background — and every sentence carries a non-obvious instruction (e.g., "a known answer does not need another confirmation echo", "Continue to the next authorized workflow stage rather than stopping solely because a document exists").

5 / 5

Actionability

As an instruction-only skill it has concrete anchors — the output path `docs/TechDesign-[AppName]-MVP.md`, the checklist of architecture facets ("component/service boundaries, data ownership, integration contracts, deployment target"), and the Handoff Context field list — but the core design process itself remains high-level direction with no example structure or worked instance, leaving minor gaps versus fully executable guidance.

4 / 5

Workflow Clarity

A rough sequence exists in prose order (read requirements → inspect stack → describe architecture → record tradeoffs → emit Handoff Context → continue) but it is never made explicit: no numbered steps, no headings, and validation is only implied ("how the result will be checked", "Verify changing vendor details") rather than given as checkpoints.

3 / 5

Progressive Disclosure

Both referenced files (references/question-bank.md and references/cli-output.md) exist, are exactly one level deep, and are well signaled with descriptive link text and clear purpose ("This is a parser contract, not an optional prose template"); however the body itself has no section headers, leaving a minor organization gap against anchor 5.

4 / 5

Total

16

/

20

Passed

Description

53%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description states a clear, specific 'what' with a defensible niche, but it completely lacks a 'when to use' trigger clause and natural synonyms, capping completeness and trigger-term quality at 3. It reads as one sentence of scope rather than a full discoverability surface.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when the user asks for a technical design, architecture plan, or design doc after requirements have been agreed.'

Include natural synonyms and variations users would say — 'design doc', 'tech spec', 'architecture plan', 'spec' — alongside 'MVP technical design' to broaden trigger-term coverage.

Enumerate the concrete actions the skill performs (e.g. 'inspect the existing stack, compare architecture options, record tradeoffs, produce a design document') to lift specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

"Write an MVP technical design from agreed requirements, including architecture choices and relevant tradeoffs" names the domain and deliverable plus two content components, but stops short of the several distinct concrete actions of anchor 4 — the whole skill is condensed to one writing action.

3 / 5

Completeness

The 'what' is clear (write an MVP technical design with architecture choices and tradeoffs) but there is no 'when' clause at all — no 'Use when...' or equivalent trigger guidance — which the guidelines explicitly cap at 3.

3 / 5

Trigger Term Quality

Terms like "MVP", "technical design", "architecture", and "tradeoffs" are ones users would naturally say, but common variations and synonyms ("design doc", "spec", "tech spec", "architecture document") are absent, matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

"MVP technical design from agreed requirements" carves a fairly distinct niche; it could overlap with general design-doc or spec-writing skills but the MVP-scope and requirements-input framing keeps conflict risk minor, fitting anchor 4.

4 / 5

Total

13

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
KhazP/vibe-coding-prompt-template
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.