/interview

name: interview
description: "Use when onboarding a new product/project. Progressive interview to understand purpose, vision, north star, and competitive landscape."
metadata:
  instruction_budget: "110"
  framework_dependency: "mycelium"
  framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin install mycelium@haabe-mycelium."

Interview Skill

First: are Mycelium's hooks running here? (v0.286.0)

Run `find .claude/state/hooks-alive "${TMPDIR:-/tmp}/mycelium-hooks-alive-$(id -u)" -mmin -60 2>/dev/null`. If it prints a path (since v0.318.0 the hooks also stamp the temp folder in a project with no Mycelium state yet, where they do nothing else), say nothing about it and go on. If it prints nothing, Mycelium's hooks did not run in this session: its gates and the rules it gives the agent at session start are off, and nothing else will say so. Tell the user in one line before anything else: "Mycelium's hooks are not running in this session, so its gates are off. On Codex CLI, open `/hooks`, trust Mycelium's hooks and start a new session; on Claude Code, check the plugin is enabled in `/plugin`." Then carry on with this skill.

Progressive onboarding through structured discovery conversation.

Preflight: Read target canvas file(s) before any Write/Edit

**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.

**Edit vs Write — different cost profiles** (verified 2026-05-14):

• **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).
• **`Write`** (full replacement): do a **full Read** first. Write obliterates the file; you should see what you're about to replace. The `limit:1` shortcut is *not* appropriate here.

**ID-bearing entries — scan the ID space before assigning** (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:

grep -o "<prefix>-[0-9][0-9]*" .claude/canvas/<file>.yml | sort -u -t- -k2 -n | tail -3

Replace `<prefix>` with the canvas's ID prefix (`comp` for landscape, `opp` for opportunities, `sol` for solutions, `ht` for human-tasks, etc.). Then pick the next free integer, **matching the zero-padding already used in that file**. The sort is NUMERIC (`-t- -k2 -n`) rather than lexical, and that is not pedantry: a plain `sort -u` orders `ht-1` after `ht-080`, so on a canvas with inconsistent padding it reports the wrong maximum and the next ID collides. Verified on the dogfood repo 2026-08-13, where lexical sort returned `ht-1` as the highest human-task ID against an actual `ht-080`. `grep -o` is also deliberate: it matches IDs wherever they appear, including cross-references and prose, so an ID that was promised somewhere but not yet defined is not handed out twice. `validate_canvas.py` has a per-file duplicate-ID check (it reports `duplicate id '<id>'`) that catches the failure on CI, but a duplicate can persist in the working tree for days if CI isn't run between edit and discovery; that happened on 2026-05-15, when a duplicate ID was created in `landscape.yml`.

Original failure mode: anti-pattern #7 instance #5, 2026-05-09 — agent conflated Bash `head` with the Read tool, lost ~14k tokens to a Write-fail → remedial-full-Read → re-Write loop. The `limit:1` discipline (graduated 2026-05-14, v0.23.18) prevents the second-order cost where the agent *correctly* follows the rule but full-Reads every time. The ID-scan discipline (graduated 2026-05-15, v0.23.19) prevents the related class where the agent reads enough of the file to satisfy the Edit check but not enough to see existing ID assignments — kin to anti-pattern #8 (Stale State Read).

If this skill writes to multiple canvas files, register each one first (limit:1 for Edit-only paths; full Read for Write paths) AND ID-scan any prefix you intend to assign.

See `${CLAUDE_PLUGIN_ROOT}/engine/agent-operating-contract.md` *Canvas writes — Read before Write* for the canonical rule.

When to Use

• Starting a new product or project.
• Joining an existing product that lacks documented context.
• Context has changed significantly and needs refreshing.

Workflow

Phase 0: Canvas state detection (ALWAYS FIRST)

Read `.claude/canvas/purpose.yml` and `.claude/diamonds/active.yml` at session start. Determine state:

• **An interview was started and not finished** (`.claude/state/interview-in-progress.md` exists): **resume it, do not restart it.** Show the answers already saved in one short list, ask the next unanswered question, and continue the Universal Brief Flow from there. This check comes FIRST, before the two below: a half-finished interview can sit beside diamonds opened later, and the project still has no purpose.
• **Canvas empty** (template-only fields, no diamonds in `active_diamonds`): proceed to **Universal Brief Flow** below.
• **Canvas populated** (purpose statement set OR diamonds present): proceed to **Continuing-Project Routing** below.

This replaces the prior intent check (`(a) try for 10 min / (b) onboard real project`) and the prior time-budget routing (`<8h / 8-48h / 48+h`). Both were predict-the-future questions asked before any value was delivered. The brief is now universal for empty-canvas entry; depth and time-cost are chosen post-brief, when the user has the data to choose. Scope (solo or team, hobby or produc