一键导入
context-preservation
Generate structured context summaries for session continuity across compaction
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。
菜单
Generate structured context summaries for session continuity across compaction
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
Analyze system health, surface patterns, manage improvement suggestions. Self-improvement flywheel for the hook/agent/dispatch system.
Multi-model deep research with comparative assessment (OpenAI + Perplexity + Gemini). Queries 3 deep research providers in parallel and produces a comparative synthesis.
Generate an interactive decision configurator from research or plan analysis. Presents options as explorable cards with trade-offs, costs, and filtering. Integrates with Planner to collect DEC-ID decisions.
Write structured feature specifications with problem statements, user journeys, use cases, functional requirements, and success metrics. Use when describing a problem space, developing a PRD, defining acceptance criteria, prioritizing requirements, or documenting product decisions.
Analyze a project's MASTER_PLAN.md to assess coherence, evolution trajectory, and intent alignment. Modes: default (full analysis), compare (delta between reckonings), operationalize (convert findings to actionable work via /decide), steer (strategic brainstorming grounded in findings).
Trace systemic brittleness from symptom to root cause. Data-flow analysis of hooks, state, and dispatch paths to find where signals break, race, or carry garbage. Produces single-gate fixes, not fallback chains.
| name | context-preservation |
| description | Generate structured context summaries for session continuity across compaction |
Generate structured context summaries when compaction is imminent or requested, ensuring session continuity without information loss.
### 1. Current Objective & Status
- **Goal**: [Robust, multi-sentence description of what we are building. Include critical details, context, and the "Definition of Done". Do not summarize into a single vague line.]
- **Status**: [Completed | In Progress | Blocked]
- **Immediate Next Step**: [The very next command or code edit required. Be specific.]
### 2. Active Context
- **Active Files**:
- `[Absolute Path]`
- `[Absolute Path]`
- **Recent Changes**: [Specific descriptions of what *just* changed in the code, referencing specific functions or logic.]
- **Variables/State**: [Key variable names, data structures, or temporary states currently in focus.]
### 3. Constraints & Decisions (CRITICAL)
- **Preferences**: [User preferences stated in this session, e.g., "no external deps", "use snake_case"]
- **Discarded Approaches**: [What did we try that failed? Do not repeat these mistakes.]
- **Architectural Rules**: [Patterns we agreed on, e.g., "Service Layer pattern", "DTOs required"]
### 4. Continuity Handoff
- "When resuming, the first thing to do is..."
Completed (all objectives achieved), In Progress (work ongoing), Blocked (explicit blocker)/Users/turla/Code/project/src/auth.ts)WRONG:
RIGHT:
WRONG:
file.ts./src/auth.tsRIGHT:
/Users/turla/Code/myproject/src/auth/oauth-handler.tsWRONG:
RIGHT:
validateTokenExpiry() function to /Users/turla/Code/myproject/src/auth/token-storage.ts (lines 42-67) that checks JWT expiration. Modified refreshToken() to call this before attempting refresh."WRONG:
RIGHT:
npm test -- --testPathPattern=oauth-handler to verify the new validateTokenExpiry() function works with expired tokens"/)