CtrlK
BlogDocsLog inGet started
Tessl Logo

interview-me

Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user explicitly invokes ("interview me", "grill me", "are we sure?", "stress-test my thinking"), or when you catch yourself silently filling in ambiguous requirements before any plan, spec, or code exists.

74

Quality

91%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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-structured, actionable instruction skill with clear sequencing, concrete templates, explicit stop criteria, and a verification checklist. The only real weakness is mild redundancy across the Red Flags, Common Rationalizations, and Verification sections, which a tighter pass could consolidate.

Suggestions

Consolidate the overlapping guidance about "whatever you think" / hollow yes across Step 5, Common Rationalizations, and Red Flags into one authoritative location and cross-reference it to reduce token cost.

Consider moving the full worked example or the Common Rationalizations table into a reference file and linking to it from SKILL.md, leaving the core process leaner in the overview.

Tighten the Verification checklist so its items map one-to-one to the Red Flags rather than restating them, eliminating the duplicated anti-pattern enumeration.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's competence — the rationalizations table, red flags, and templates are skill-specific rather than padded general knowledge — though the "whatever you think" pattern recurs across Step 5, Common Rationalizations, and Red Flags, and the worked example is long.

4 / 5

Actionability

Provides copy-paste-ready templates (HYPOTHESIS/CONFIDENCE, Q/GUESS, the six-line restate) and an exact probe question ("If you didn't have to justify this to anyone, what would you actually want?"), with a full worked transcript; the absence of code is not penalized for this instruction-only skill.

5 / 5

Workflow Clarity

Steps 1–5 are clearly sequenced with an explicit validation gate (the 95% "predict the next three reactions" test), a feedback/floor loop for stalled interviews, and a closing verification checklist — no destructive or batch operation cap applies.

5 / 5

Progressive Disclosure

No bundle files exist and the skill is self-contained with well-organized sections (Overview, When to Use, Loading Constraints, Process, Output, Example, Interaction, Rationalizations, Red Flags, Verification); the 5-anchor's "well-signaled one-level-deep references" does not apply since there are no references, and some reinforcing content spans Red Flags, Verification, and Common Rationalizations.

4 / 5

Total

18

/

20

Passed

Description

95%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: third-person voice, explicit what-and-when with concrete trigger synonyms, and a clearly bounded niche. Minor specificity gap only because a single interview process naturally yields fewer discrete action verbs than a multi-operation file skill.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions — "one-question-at-a-time interview", "until ~95% confidence", restate underlying intent — but as a single-process skill it does not enumerate a broad set of distinct operations like the 5-anchor examples.

4 / 5

Completeness

Explicitly answers both what ("Extracts what the user actually wants... through one-question-at-a-time interview until ~95% confidence") and when ("Use when an ask is underspecified... when the user explicitly invokes... or when you catch yourself silently filling in ambiguous requirements") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural user invocations with synonyms — "interview me", "grill me", "are we sure?", "stress-test my thinking" — plus the underspecified-ask pattern "build me X", covering the phrases a user would actually say.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — pre-decision intent extraction "before any plan, spec, or code exists" — with distinct trigger phrases that would not fire for downstream skills like spec-driven-development or doubt-driven-development.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
addyosmani/agent-skills
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.