Kit Preamble — discovery-prep

---

name: discovery-prep description: Generates a Discovery meeting plan from an account brief — SPIN questions, MEDDIC checklist, hypothesized pain points with verification questions, objection prep, time-boxed agenda. Run after /account-brief, before the meeting. argument-hint: [output file path, default docs/discovery_plan.md] disable-model-invocation: false allowed-tools: Read, Glob, Grep, Write, Edit, Task

Kit Preamble — discovery-prep

Kit Update Check

Run silently at the start:

python3 scripts/kit_update_check.py 2>/dev/null

If exit code is 1 (update available), show the output to the user once. Do not block the workflow.

Project Context Detection

Run these checks silently at the start. Use results to adapt behavior:

• [ -f issues.md ] — if true, this project uses the sprint system. Respect issue numbering and STATUS.md.
• [ -f docs/sprint_state.md ] — if true and Status shows running, a sprint is active. Be aware of parallel work in worktrees.
• [ -f docs/prd_digest.md ] — if true, read it for quick project context before starting.

Behavioral Rules

• Verify gh auth status before any GitHub operation.
• Never commit secrets, API keys, or credentials. Use environment variables.
• Prefer parallel Read/Glob/Grep tool calls when reading multiple independent files.
• When uncertain about intent, ask the user rather than guessing.
• Respect existing project conventions (package manager, test framework, code style).

Contributor Mode

At the start of this skill, check if contributor mode is enabled:

python3 scripts/kit_config.py get contributor_mode

If the result is true:

1. At the end of each major workflow step, self-rate your experience with the kit 0–10.
2. If rating < 10 and there is an actionable improvement, file a field report:

   python3 scripts/contributor_report.py --skill <name> --step "<step>" --rating <N> --notes "<friction or suggestion>"
   

3. Maximum 3 reports per session. Skip if a report for the same step already exists.
4. Do NOT stop the workflow to file reports — do it inline.
5. Only report kit/skill issues (unclear instructions, missing checkpoints, bad ergonomics). Do NOT report user-app bugs or network errors. Steps:

1. Determine the output path ($ARGUMENTS or docs/discovery_plan.md).
2. Check if docs/account_brief.md exists. Required. If absent, stop and tell the user to run /account-brief first.
3. Check if the output file already exists. 3.5) Resolve shared file paths via walk-up (supports multi-account repo structure):

   LESSONS_PATH="$(bash scripts/find_shared.sh sales_lessons.md 2>/dev/null || true)"
   

   • If non-empty, pass the absolute path to the agent as the sales_lessons input.
   • If empty (not found within repo), proceed without lessons context.

If the file does NOT exist (New Plan):

4a) Invoke the discovery-coach agent via the Task tool, passing the account brief path and the resolved LESSONS_PATH (or None if unresolved). 5a) The agent will: - Read docs/account_brief.md and templates/discovery_plan.md - Optionally read any prior meeting_notes_*.md for accumulated context - Optionally read the resolved sales_lessons.md path (passed in from step 3.5) for cross-account patterns to apply - Generate meeting goals (Must / Nice / no-go) - Convert hypothesized pain points into verification questions - Generate SPIN questions — HARD CAP 6 total (Situation 1–2, Problem 2, Implication 1–2, Need-Payoff 1) - Build MEDDIC checklist (blank, for salesperson to fill in meeting) - Anticipate objections + draft responses - Propose time-boxed meeting flow - Save the plan to the output path 6a) Present the plan to the user. Highlight: must-have meeting goal, top 3 questions, top 3 objections to prep.

If the file DOES exist (Update Plan):

4b) Read the existing plan and present a brief summary. 5b) Ask what changed: new account intel? prior meeting revealed something? new objections to prep? 6b) Invoke discovery-coach in update mode — it will update only affected sections. 7b) Highlight what changed.

Common (both modes):

7. Remind the user:
   • Skim the plan 30 minutes before the meeting
   • After the meeting, write meeting notes using templates/meeting_notes.md as the format
   • Then run /meeting-capture <notes_path> to generate the PRD draft

Error Handling

• If docs/account_brief.md is missing: stop and tell the user to run /account-brief first.
• If the brief is thin (private company, sparse data): warn the user and produce a more cautious plan with extra Situation questions.
• If the output path is not writable: report and ask for alternative.

Quality Criteria

NEVER:

• Generate generic SPIN templates that ignore the account brief
• Exceed 6 total questions — hard cap
• Use leading questions ("Wouldn't it be great if...")
• Pack the agenda so tightly there's no room for the customer to talk
• Recommend premature pricing or contract discussion in a Discovery meeting
• Skip Implication questions — they are SPIN's hardest and most important stage

INSTEAD:

• Pull specific phrases from account_brief.md into question wording
• Pair every hypothesized pain with a question that could disconfirm it
• Limit to 6 total questions — quality over quantity
• Apply relevant sales_lessons.md patterns when available (within the 6-question cap)
• For each objection, name a concrete reference artifact (case study, white paper, ROI calculator)

Guidelines

• After saving, suggest next step: write meeting notes after the meeting, then run /meeting-capture.
• If the salesperson is new to SPIN/MEDDIC, offer a one-paragraph primer in the response (not in the saved file).