CtrlK
BlogDocsLog inGet started
Tessl Logo

interview

Phase 1 of building a Claude Managed Agent — interview the founder about the one job the agent should do, then produce a build sheet (CMA primitives table + v1/v2 deferrals + eval plan) WITHOUT needing their API key yet. Use when the user says "help me scope an agent", "I have an idea for an agent", "what should this agent be", or when the orchestrator routes phase=interview. Drives the six intake slots (job, trigger, inputs, actions, definition-of-done, recurrence) via AskUserQuestion, maps them to primitives with interview_planner.py, assembles build-sheet.json with build_sheet_builder.py, and validates limits with primitives_validator.py. Connectors are mockable in v0 (schema-true custom tools); real MCP servers become v1 deferrals. Distinct from stage-launch (which turns the sheet into payloads).

76

Quality

96%

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

The canonical home for this skill is interview in alirezarezvani/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 body is a lean, highly actionable, well-sequenced workflow with a real validation checkpoint. Its main weakness is progressive disclosure: it references reference and script files that are not present in the bundle.

Suggestions

Provide the referenced files (references/examples-bank.md, references/interview-to-config.md, and the scripts/interview_planner.py, build_sheet_builder.py, primitives_validator.py) so the signaled navigation resolves to real artifacts.

If any referenced file is not yet authored, either inline the essential content or mark the reference as a stub so Claude is not left following dead links.

Consider consolidating the examples-bank reference into the body if it is small, to reduce reliance on a missing file for the warm-open step.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it never explains what an agent or an interview is — and uses compact tables and inline commands so every token earns its place.

5 / 5

Actionability

Three fully executable bash commands with concrete arguments (interview_planner.py, build_sheet_builder.py, primitives_validator.py) and a forcing-question library with explicit recommendations and citations provide copy-paste-ready guidance.

5 / 5

Workflow Clarity

A five-step numbered workflow includes an explicit validation checkpoint (step 4: 'FAIL blocks progress; fix and re-run. WARN is advisory') with a feedback loop, matching the score-5 anchor.

5 / 5

Progressive Disclosure

The body signals one-level-deep references (examples-bank.md, interview-to-config.md) and scripts cleanly, but the referenced references/ and scripts/ bundle directories are absent, so the navigation points to files that do not exist.

3 / 5

Total

18

/

20

Passed

Description

100%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 excellent: it concretely names the actions and supporting scripts, gives explicit natural trigger phrases, and explicitly disambiguates the skill from a sibling stage. Voice is third person throughout with no over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'interview the founder about the one job', 'produce a build sheet (CMA primitives table + v1/v2 deferrals + eval plan)', 'Drives the six intake slots... via AskUserQuestion', and names the exact scripts (interview_planner.py, build_sheet_builder.py, primitives_validator.py) — comprehensive coverage.

5 / 5

Completeness

Explicitly answers both 'what' (interview founder, produce a build sheet with primitives/deferrals/eval plan) and 'when' (a 'Use when...' clause with concrete trigger phrases), matching the score-5 anchor.

5 / 5

Trigger Term Quality

Provides natural user phrases users would actually say — 'help me scope an agent', 'I have an idea for an agent', 'what should this agent be' — plus the orchestrator's phase=interview routing, giving comprehensive coverage of natural terms.

5 / 5

Distinctiveness Conflict Risk

States a clear niche and explicitly distinguishes it — 'Distinct from stage-launch (which turns the sheet into payloads)' — so it is unlikely to trigger for the wrong skill.

5 / 5

Total

20

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 2 suspicious

Warning

referenced_paths_exist

Referenced path issues: 6 missing

Warning

Total

13

/

16

Passed

Repository
alirezarezvani/claude-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.