interview-spec

Deep-dive interview to flesh out a spec or design document

Quality

47%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.opencode/skills/interview-spec/SKILL.md

Quality

Content

65%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 content is a well-organized, concise interview playbook with strong topic coverage and a clear flow. Its main weaknesses are the absence of worked examples or templates and the lack of a validation/confirmation checkpoint before the destructive write-back of the user's document.

Suggestions

Add one concrete example question with sample AskUserQuestion options showing real tradeoffs, to move actionability from suggestive to executable.

Insert an explicit validation checkpoint before writing back, e.g. 'Confirm with the user before overwriting the original document; offer to diff or save a copy first.'

Define an explicit completion signal the user can recognize (e.g. a short checklist of satisfied critical areas) rather than only 'signal when you believe the interview is complete'.

Dimension	Reasoning	Score
Conciseness	The body is tight and assumes Claude's competence; it does not re-explain what a spec or design document is and uses dense bullet lists of concrete focus areas, with only minor padding in the topic enumerations.	4 / 5
Actionability	It gives concrete strategy and specific topic checklists (e.g. 'Use the AskUserQuestion tool', 'Ask 2-4 questions at a time'), but offers no executable template, example question, or worked option set, leaving guidance suggestive rather than copy-paste ready.	3 / 5
Workflow Clarity	The numbered task list and interview flow provide a clear sequence, but there is no validation checkpoint that the gathered answers are sufficient before rewriting, and the destructive step of overwriting the user's original document lacks a confirm-before-write loop.	3 / 5
Progressive Disclosure	No bundle files exist and none are needed; the body is well-organized with clear section headers (Task, Guidelines, Topics, Flow, Output) and stays within a single self-contained file, which matches the simple-skill exception for progressive disclosure.	5 / 5
	Total	15 / 20 Passed

Description

30%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 is a single short sentence that captures the core purpose but lacks trigger guidance and concrete action detail. It is readable but underspecified relative to the good examples. Adding a "Use when..." clause with natural trigger phrases would substantially improve it.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user wants to flesh out, refine, or pressure-test a spec or design document before implementation.'

Enumerate concrete actions (e.g. 'identifies gaps and ambiguities, asks targeted clarifying questions, rewrites the completed spec') to lift specificity from 2 toward 4.

Include natural user trigger phrases such as 'refine a spec', 'fill in design gaps', 'clarify requirements', or 'review a design doc'.

Dimension	Reasoning	Score
Specificity	The phrase "Deep-dive interview" names the domain but the only concrete action is to "flesh out a spec or design document"; actions are minimal and generic with no enumeration of specific behaviors.	2 / 5
Completeness	It states a vague "what" (interview to flesh out a spec/design doc) but provides no "Use when..." clause or equivalent explicit trigger guidance, capping completeness at 3 per the guidelines and landing at 2 given the weak what.	2 / 5
Trigger Term Quality	It offers only generic phrasing ("interview", "spec or design document") and lacks the natural trigger phrases a user would actually say, such as "refine a spec", "fill gaps in a design", or "clarify requirements".	2 / 5
Distinctiveness Conflict Risk	The interview/spec-flushing niche is fairly distinct from most skills, but "interview" and "spec/design document" are broad enough to risk overlap with general planning or design skills.	3 / 5
	Total	9 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: LibPDF-js/core
Path: .opencode/skills/interview-spec/SKILL.md
Commit: 0fa22e0

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.