CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

interview

Interview the author with a panel of six interviewer personas (Terkel, Bell, Klein, Stern, Gross, Abumrad), one question at a time, turning answers about beliefs into concrete stories and saving a verbatim transcript as the source for drafting. Use when the author picks a topic or mirror cluster to write about, says "interview me," or has an idea but no draft.

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

An exemplary instruction-only skill body: tight, concrete, and well-structured. It gives executable specifics (path patterns, prefixes, scripts, budgets, stopping criteria) without over-explaining, and delegates persona detail to real one-level-deep reference files. No dimension shows more than nit-level room for improvement.

DimensionReasoningScore

Conciseness

The ~100-line body is lean and assumes Claude's competence: no explanation of what interviewing is, a table instead of prose for persona routing, and every rule carries its own one-line justification that shapes judgment (e.g., "Two questions get half of each"). Nothing reads as padding, matching the level-5 anchor rather than the level-4 'minor instances of over-explanation'.

5 / 5

Actionability

For an instruction-only skill the guidance is fully executable: a transcript path pattern (`transcripts/YYYY-MM-DD-<slug>.md`), a persona-prefix example (`**Terkel:**`), a verbatim closing-move script to quote, a twelve-question ceiling, named cross-skill handoffs (`research`, `voice`, `drafting`), and per-persona follow-up triggers delegated to the persona files. The guidance is concrete and specific throughout, so the absence of code is not penalized.

5 / 5

Workflow Clarity

The process is clearly sequenced — brief first if needed, one question at a time, route follow-ups by persona triggers, stop on the three-item checklist ("concrete story or artifact", "unguarded position", "hook material"), transcript written as you go, closing move, then hand off. The stopping checklist and the completion condition ("The interview isn't done until at least one concrete story or artifact is on the record") act as explicit validation checkpoints, satisfying the level-5 anchor; this is not a destructive or batch operation, so no validation cap applies.

5 / 5

Progressive Disclosure

The body is a well-organized overview and the six persona files (verified present in references/personas/) are exactly one level deep, linked by name in a routing table and a per-seat purpose list. Detail that would bloat the body (persona voice, question patterns) correctly lives in the bundle files, matching the level-5 anchor of well-signaled, one-level-deep references.

5 / 5

Total

20

/

20

Passed

Description

92%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, concrete actions covering the full workflow, and an explicit 'Use when...' clause with quotable trigger phrases. The only weakness is trigger-term coverage — 'mirror cluster' is insider jargon and a few natural synonyms are missing.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "a panel of six interviewer personas", "one question at a time", "turning answers about beliefs into concrete stories", "saving a verbatim transcript" — covering conduct, technique, and output comprehensively for the skill's scope. It exceeds the level-4 anchor ('several specific actions; minor gaps') because no meaningful capability of the skill is left out of the description.

5 / 5

Completeness

Explicitly answers both questions: the what ("Interview the author with a panel of six interviewer personas... saving a verbatim transcript") and the when ("Use when the author picks a topic or mirror cluster to write about, says 'interview me,' or has an idea but no draft") with concrete trigger phrases. The when-clause is already explicit and specific, so the level-4 anchor ('when could be more explicit') does not fit.

5 / 5

Trigger Term Quality

Includes natural phrases a user would actually say — "says 'interview me'" and "has an idea but no draft" — plus the action keyword "interview". It falls short of the level-5 anchor because "mirror cluster" is internal jargon users would not naturally say, and common variations like "ask me questions" or "help me figure out what to write" are absent.

4 / 5

Distinctiveness Conflict Risk

The named six-persona panel and verbatim-transcript output define a clear niche, and triggers like "interview me" and "has an idea but no draft" are unambiguous. Overlap risk with adjacent writing skills (drafting, research) is minimal because the description scopes it to interviewing the author as source-material collection.

5 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 6 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 6 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository

shortrib-labs/content-loop

Path

plugins/drafting/skills/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.