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).

Quality

98%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

96%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 lean, highly actionable, and sequenced with a real validation feedback loop. The only gap is progressive disclosure: two inline reference links point to markdown files that are not bundled, so the navigation they promise does not resolve.

Suggestions

Bundle the two referenced files (examples-bank.md and interview-to-config.md) under references/, or remove/replace the dangling links so every reference in the body resolves to a real bundled file.

Add a one-line pointer near the top clarifying that scripts/ holds the three executable tools, since the Tools section already lists them but a reader scanning the workflow hits the bash commands first.

If references are intentionally external to this skill, mark them as out-of-bundle (e.g., 'see the CMA reference set') rather than presenting them as relative paths that imply local files.

Dimension	Reasoning	Score
Conciseness	The body is lean — a short intake table, terse numbered workflow, and three code blocks — and assumes Claude's competence, never explaining what an agent, MCP, or rubric is; every section earns its place.	5 / 5
Actionability	Provides three copy-paste-ready bash commands with concrete arguments and a real example job, plus the referenced scripts exist in the bundle and are executable, covering the common cases fully.	5 / 5
Workflow Clarity	A clear five-step sequence with an explicit validation checkpoint in step 4 ('FAIL blocks progress; fix and re-run. WARN is advisory') constituting a validate->fix->retry feedback loop.	5 / 5
Progressive Disclosure	Well-organized overview with clearly signaled one-level-deep references (../../references/examples-bank.md, ../../references/interview-to-config.md) and a Tools list, but those referenced files are not present in the bundle — the references/ directory does not exist — so navigation is partially broken.	4 / 5
	Total	19 / 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 specific, trigger-rich, and self-distinguishing, cleanly answering both what the skill does and when to invoke it. It names the concrete scripts, outputs, and intake slots, and even disambiguates from the sibling stage-launch skill.

Dimension	Reasoning	Score
Specificity	Names a concrete domain and multiple specific actions — 'interview the founder', 'produce a build sheet (CMA primitives table + v1/v2 deferrals + eval plan)', 'maps them to primitives with interview_planner.py', 'assembles build-sheet.json', 'validates limits with primitives_validator.py' — covering the intake slots, scripts, and outputs comprehensively.	5 / 5
Completeness	Explicitly answers both 'what' (interview founder, produce a build sheet with primitives/deferrals/eval plan) and 'when' with concrete trigger phrases via the 'Use when the user says...' clause.	5 / 5
Trigger Term Quality	Includes verbatim natural user utterances — 'help me scope an agent', 'I have an idea for an agent', 'what should this agent be' — plus the orchestrator routing trigger phase=interview, giving comprehensive natural-term coverage.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Phase 1 CMA interview/build-sheet) and explicitly distinguishes itself from a sibling — 'Distinct from stage-launch (which turns the sheet into payloads)' — minimizing overlap risk.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 suspicious	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: agent-launcher/skills/interview/SKILL.md
Commit: 19392f7

Reviewed: ~10 hours 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.