Kit Preamble — account-brief

---

name: account-brief description: Pre-meeting B2B account research. Produces a structured account brief (company overview, recent news, tech stack, decision structure hypothesis, hypothesized pain points, approach strategy). Use before /discovery-prep. argument-hint: [output file path, default docs/account_brief.md] disable-model-invocation: false allowed-tools: Read, Glob, Grep, Write, Edit, WebSearch, WebFetch, Task

Kit Preamble — account-brief

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/account_brief.md).
2. Check if the file already exists at that path.
3. Ask the user for the target company name (required). Optionally accept: website URL, known contacts, prior context, hypothesized opportunity angle.

If the file does NOT exist (New Brief):

4a) Invoke the account-researcher agent via the Task tool with the inputs from step 3. 5a) The agent will: - Read templates/account_brief.md for structure - Run parallel web research (company basics, recent news, tech stack, competitive landscape) - Hypothesize decision structure and pain points (clearly labeled as hypothesis) - Save the brief to the output path 6a) Present the brief to the user. Highlight: top 3 things to know, weakest sections, unresolved questions.

If the file DOES exist (Update Brief):

4b) Read the existing brief and present a brief summary. 5b) Ask the user what triggered the update (new meeting, news, contact). 6b) Invoke the account-researcher agent in update mode — it will do targeted research on the changed area only. 7b) Highlight what changed.

Common (both modes):

7. Inform the user they can run /discovery-prep next to generate Discovery questions tailored to this account.

Error Handling

• If no company name is provided: ask the user — do not proceed.
• If web research returns sparse results (private company, non-English market): produce the best brief possible and explicitly flag the gaps in "Unresolved Questions".
• If the output path is not writable: report the error and ask for an alternative path.

Quality Criteria

NEVER:

• Fabricate executive names, titles, or org charts — mark unverified entries as hypothesis
• State pain points unsupported by research
• Cite news older than 18 months without flagging the date
• Praise the customer uncritically — note threats and competitive pressures

INSTEAD:

• Cite sources inline for every external claim
• Distinguish "confirmed" from "inferred" from "speculative"
• Lead with the 3 things the salesperson most needs to know
• For Korean companies, also search Korean-language sources (네이버 뉴스, 잡코리아 채용공고)

Guidelines

• This is a research-heavy skill — expect 2–5 minutes of web search.
• The brief is meant to be skimmed in 5–10 minutes before a meeting. Keep it tight.
• After saving, suggest next step: /discovery-prep to generate the Discovery question plan.