CtrlK
BlogDocsLog inGet started
Tessl Logo

vibe-prd

Write or revise an MVP product requirements document with scope and observable acceptance criteria.

57

Quality

66%

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-prd/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

80%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.

A disciplined, token-efficient instruction skill with excellent progressive disclosure: an imperative overview, concrete coverage and handoff checklists, and two conditional, purpose-labeled references. Its weaknesses are the implicit, prose-based workflow ordering and the absence of any worked example or template that would make the output format fully concrete.

Suggestions

Make the sequence explicit as a short ordered list (gather known context → resolve open scope questions → draft PRD → emit Handoff Context → optionally continue to design) so the workflow order is unambiguous.

Add a validation checkpoint such as re-reading each acceptance criterion to confirm it is observable, and confirming every assumption is labeled before finishing.

Include a minimal PRD skeleton or one example of an observable acceptance criterion to make the output shape concrete rather than inferred.

DimensionReasoningScore

Conciseness

The body is lean and imperative with zero padding — it never explains what a PRD is and every sentence carries project-specific guidance Claude cannot infer ('Use the manifest's configured PRD path or docs/PRD-[AppName]-MVP.md', 'Do not present planned acceptance checks as executed evidence'). Every token earns its place, matching the 'lean and efficient; assumes Claude's competence' anchor.

5 / 5

Actionability

Concrete, instruction-only guidance: an explicit coverage checklist ('target user and problem, the core journey, MVP scope, out-of-scope work, meaningful failure states, constraints, and observable acceptance criteria'), an exact output path pattern, and an enumerated Handoff Context field list. It stops short of level 5 because no PRD skeleton or example acceptance criterion is given, leaving the document's concrete shape and the 'observable' standard to inference.

4 / 5

Workflow Clarity

A sequence exists (gather known context, ask only unresolved requirements, draft the PRD, emit Handoff Context, optionally continue into technical design) but it is embedded in prose paragraphs rather than explicit ordered steps, and there are no validation checkpoints (e.g., verifying criteria are observable or assumptions are labeled). This matches 'steps listed but validation gaps; checkpoints missing or implicit', and the operation is not destructive/batch so no hard cap applies.

3 / 5

Progressive Disclosure

The body is a concise overview with two well-signaled, one-level-deep references that both exist in the bundle, each with a clear purpose and even usage conditions ('For a guided interview with unresolved requirements' and 'This is a parser contract, not an optional prose template'). This matches the 'clear overview with well-signaled one-level-deep references' anchor.

5 / 5

Total

17

/

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.

A concise, third-person description with a clear 'what', but it omits any 'when to use' trigger guidance and the natural synonyms (especially 'PRD') users would most often say. Adding a 'Use when...' clause with those terms would lift completeness and trigger-term quality substantially.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to write, draft, or revise a PRD, MVP requirements, or product spec.'

Include the common abbreviation and synonyms ('PRD', 'product spec', 'requirements doc') as trigger terms users naturally say.

Mention the adjacent capabilities the body covers (unresolved-requirement questions, handoff into technical design) so the description's coverage is more comprehensive.

DimensionReasoningScore

Specificity

The description names the domain ('MVP product requirements document') and two concrete actions ('Write or revise') plus attributes ('scope and observable acceptance criteria'), matching the anchor for 1-2 concrete actions without comprehensive coverage. It is above level 2 because the actions are specific rather than generic, but below level 4 because only two verbs are listed with no coverage of the skill's other capabilities (interviewing, handoff, design continuation).

3 / 5

Completeness

The 'what' is clear (write or revise an MVP PRD with scope and observable acceptance criteria), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not level 2 because the 'what' is concrete, not vague.

3 / 5

Trigger Term Quality

'MVP' and 'product requirements document' are natural keywords a user would say, but common variations are missing — the ubiquitous 'PRD' abbreviation, 'spec', 'requirements', and 'product doc'. This fits the anchor 'some relevant keywords but missing common variations or synonyms' rather than level 4, whose example shows a broader spread of natural terms.

3 / 5

Distinctiveness Conflict Risk

'MVP product requirements document with observable acceptance criteria' carves a clear niche that is unlikely to trigger for unrelated skills, fitting 'mostly distinct; minor overlap risk'. It falls short of level 5 because the missing trigger clause leaves residual ambiguity against adjacent writing/planning skills (e.g., technical-design or general docs skills).

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.