CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

deep-interview

Analyze, deepen, and validate an existing doc or topic through a structured interview. Use when refining PRDs, Linear tickets, notes, or draft specs before planning or execution.

Quality

73%

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 ./Skills/product-strategy/deep-interview/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

52%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 well-organized, token-efficient contract with explicit validation and fail-fast checkpoints, but the guidance stays at the directive level — no concrete interview mechanics, output templates, or worked examples. The Progressive Disclosure section points at files that do not exist in the bundle, breaking navigation to the deferred content.

Suggestions

Add concrete execution mechanics: one example interview question, a short template for the gap list and approval-ready summary, and what counts as a 'focused surface' so steps like 'Inspect 2-3 focused surfaces' are executable rather than directive.

Fix the dangling references: cite paths that exist in the bundle (references/contract.yaml, references/evals.yaml, references/task-profile.json) or actually ship the cited Infrastructure/references files, and drop the one-level-deep pointer to the non-existent deferred-skill-context directory.

Trim redundancy by merging the overlapping Philosophy/Avoid/Gotchas/Anti-Patterns bullets (e.g., deferred-file loading is stated twice) and removing the verbatim repetition of the frontmatter description in the body opening.

DimensionReasoningScore

Conciseness

The body is lean, bullet-based, and assumes competence without explaining known concepts. Not 5 because of redundancy: the frontmatter description is repeated verbatim in the opening, and Philosophy/Avoid/Gotchas/Anti-Patterns overlap (e.g., deferred-reference guidance appears in both Gotchas and Anti-Patterns).

4 / 5

Actionability

The workflow steps are high-level directives ("Inspect 2-3 focused surfaces before expanding scope", "Take the smallest action that advances the confirmed goal") with no concrete mechanics: no example interview question, no template for the gap list or approval-ready summary, and no illustration of what an output looks like. Not 3 because even pseudocode-level specifics or a worked example are absent, leaving only abstract direction.

2 / 5

Workflow Clarity

The five-step sequence is clearly ordered with explicit checkpoints: "Stop at the first failed gate or blocker and report exact evidence" plus a validate→fix→rerun feedback loop ("Rerun the relevant validation after fixes before claiming completion"). Not 5 because the steps themselves are abstract, so error recovery cannot be followed mechanically; not 3 because validation checkpoints and feedback loops are explicitly present, not implicit.

4 / 5

Progressive Disclosure

References are clearly signaled ("Use `Infrastructure/references/software-literature-expert-lens-pack.md`...") but dangling: none of the cited paths exist in the bundle, whose references/ directory contains only contract.yaml, evals.yaml, and task-profile.json — none of which the body links to. Not 3 because navigation to the deferred material is broken rather than merely under-signaled; not 1 because the body itself is short and well-sectioned rather than a monolithic wall.

2 / 5

Total

12

/

20

Passed

Description

83%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 strong description that explicitly covers what the skill does and when to use it, with natural trigger nouns (PRDs, Linear tickets, notes, draft specs) in third person. Minor room to grow via more concrete output statements and additional trigger synonyms.

DimensionReasoningScore

Specificity

Names three concrete actions ("Analyze, deepen, and validate") applied to a defined artifact set ("an existing doc or topic"), in third person. Not 5 because the actions are high-level verbs without concrete deliverables (e.g., 'produces a gap list' or 'asks targeted questions'), and not 3 because multiple specific actions plus a named domain exceed the 1-2 action anchor.

4 / 5

Completeness

Explicitly answers both what ("Analyze, deepen, and validate an existing doc or topic through a structured interview") and when ("Use when refining PRDs, Linear tickets, notes, or draft specs before planning or execution") with concrete trigger phrases. Not 4 because the 'when' clause is already specific and trigger-laden, not merely present.

5 / 5

Trigger Term Quality

"refining PRDs, Linear tickets, notes, or draft specs" are natural nouns users would actually say, plus "before planning or execution" gives timing context. Not 5 because common variations like 'requirements doc', 'review my draft', or 'spec review' are missing.

4 / 5

Distinctiveness Conflict Risk

The pre-planning structured-interview framing over PRDs/tickets/notes/specs is a fairly clear niche with distinct triggers. Not 5 because it could still overlap with general draft-review, critique, or planning skills that also act on drafts and specs.

4 / 5

Total

17

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

jscraik/Agent-Skills

Path

Skills/product-strategy/deep-interview/SKILL.md

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.