菜单
Audit and repair the context layer. Use when asked to clean up context, before a quarterly review, or when the knowledge graph feels stale. Finds missing frontmatter, broken references, orphan files, and stale content, then fixes them file by file.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Turn something heard in the field into durable context, at the right confidence level. Use when the user relays an objection, a competitor mention, a win or loss reason, a signal, or any claim from a call, and asks to remember it. Enforces the repetition rule and the confidence ladder.
How this GTM repository works. Load when orienting in this repo, deciding where a change belongs, or explaining the layer conventions to someone. Covers the layers, the dependency direction, the PR workflow, the confidence ladder, and where each kind of change goes.
Write today's entry in the cadence log. Use at the end of a working day, or when the user recaps what happened. Captures what moved, what is stuck, and anything worth remembering, then routes stuck items to carryover and repeated observations toward context.
Scaffold a new GTM motion end to end across all three layers. Use whenever creating a new motion, campaign, play, or automation in this repo, so the narrative (context), the implementation (infra), and the regression suite (evals) ship together and never drift apart. Enforces the outreach hypothesis rule.
Plan the coming week in the cadence layer. Use every Monday, or whenever asked what this week should focus on. Pulls from plan/ and open initiatives/, carries over unresolved items, and writes cadence/weekly/YYYY-Www.md. Escalates anything that has slipped three weeks into a decision instead of a task.
Digest the outputs archive into durable context. Use for the weekly GTM review, or whenever asked what happened recently and what we learned. Reads recent outputs entries, summarizes results, and proposes context updates as a PR. This is the repo's memory flywheel.
| name | context-hygiene |
| description | Audit and repair the context layer. Use when asked to clean up context, before a quarterly review, or when the knowledge graph feels stale. Finds missing frontmatter, broken references, orphan files, and stale content, then fixes them file by file. |
The context layer is only useful if agents can trust it. Run this audit periodically or when onboarding a new team member.
Mechanical lint. Run npm run lint:context. Fix every error (missing
title/description, broken references: entries, broken wikilinks or
relative links). Errors block CI; do these first.
Orphans. The linter warns about files nothing references. For each orphan, decide: link it from the file that should own the relationship, or delete it if it no longer earns its place. Do not leave orphans standing.
Staleness. The linter warns about files untouched for more than 90
days. For each, check it against reality: recent won/lost deals in
context/client/, current pricing, live positioning. Update the file or
add a dated note explaining why it is still accurate.
Contradictions. Read global/ and icp/ together and flag claims that
conflict (two different ICPs, outdated competitor claims in
alternative/). Surface contradictions to the team in the PR description
rather than silently picking a side.
Ship it. One PR titled context: hygiene pass YYYY-MM-DD, with a
summary table: files fixed, orphans resolved, stale files refreshed,
contradictions flagged.
TODO(owner): marker.