菜单
Loads structured project context at session start from README, docs, plans, git state, and memory MCPs. Use when orienting on a known project, resuming after a gap, or when the user says "prime context" or "/context-prime".
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
| name | context-prime |
| description | Loads structured project context at session start from README, docs, plans, git state, and memory MCPs. Use when orienting on a known project, resuming after a gap, or when the user says "prime context" or "/context-prime". |
On-demand loading: Read this skill only when starting or resuming work on a known project. Do not load for unrelated tasks.
Use this skill at the start of a session on a known project to quickly load structured context. Invoke when starting work, resuming after a gap, or when you need a fast orientation of the project state.
When this skill is invoked, execute the following steps to build and emit a structured context summary:
Read these files if they exist (in order):
README.md — project overview, tech stack, quick startpackage.json / pyproject.toml / Cargo.toml / go.mod — name, version, dependencies.cursor/plans/workflow_state.md — current workflow phase and active tasksAGENTS.md — agent conventions for this projectExtract:
dev, test, build, lint)Scan these paths for relevant context:
docs/ — architecture, decisions, API contracts (read top-level index or most recent files).cursor/plans/ — any .plan.md or .md files (read titles and summaries)CHANGELOG.md or HISTORY.md — last 10 entries for recent changesRun to find files modified in the last 7 days:
git log --since="7 days ago" --name-only --format="" | sort -u | head -20
Or use Glob to find recent files and read key ones for context.
git status --short
git log --oneline -10
git branch --show-current
Extract:
If user-cursor10x-mcp is available, query for recent project context (e.g. getComprehensiveContext). If user-devcontext is available, query for active session state (e.g. initialize_conversation_context). Extract:
Output in this format:
## Project Context: <PROJECT_NAME>
**Purpose:** <one-line description>
**Stack:** <languages, frameworks, databases>
**Key commands:**
- Dev: `<command>`
- Test: `<command>`
- Build: `<command>`
- Lint: `<command>`
---
**Current branch:** <branch>
**Workflow phase:** <phase from workflow_state.md or "unknown">
**Active tasks:**
- <task 1>
- <task 2>
---
**Recent changes (last 7 days):**
- <file 1>: <what changed>
- <file 2>: <what changed>
**Uncommitted changes:**
- <file>: <M/A/D status>
---
**Architecture highlights:**
<2-3 sentences from docs/ or README>
**Open decisions / known issues:**
<from plans/ or recent commits>
---
**Suggested focus areas for this session:**
1. <area 1>
2. <area 2>
/context-prime command pattern, adapted for Cursor skills format.Orchestrate continual learning by delegating transcript mining and AGENTS.md updates to the knowledge-synthesizer subagent. Use when asked to mine prior chats, maintain AGENTS.md, update learned preferences, or run the continual-learning loop.
Security-focused review of code diffs and PRs with surface classification and Semgrep on changed files. Use when reviewing pull requests, branch diffs, or validating security regressions before merge.
Live Notion session log (L4b) — create, incremental updates during work, finalize on CLOSE. Works on any Cursor project workspace.
Bootstrap a new project with Cursor-ready configuration: AGENTS.md, per-project .cursor/rules/project-conventions.mdc, and optional memory_bank/ scaffold. Use at project initialization, when starting a new repo, or when the user says "set up Cursor for this project" / "bootstrap this project" / "init project config".
Phase-1 repo reconnaissance as a standalone skill: stack detection, relevant files, validation commands from repo evidence, workflow hints, and risk flags. Use inside /scout, /ks-conductor pre-flight, or any read-only discovery before planning or implementation.
Validates phase outputs before advancing the SDLC. Defines expected artifacts per phase (intake, scout, plan, critic, build, test, review, document, close) and produces a clear PASS / CONDITIONAL / BLOCK verdict with gaps. Use at orchestrator or command phase boundaries, before expensive work, or when the user asks to verify a gate or "are we ready to proceed".