← 返回 Skills 市场
Weekly Review Builder
作者
sunbinnju-star
· GitHub ↗
· v1.0.0
· MIT-0
116
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install weekly-review-builder
功能描述
Build a weekly review that refreshes project phase, bottleneck, and next steps. Use on: weekly schedule, after several daily loops, before resetting project...
使用说明 (SKILL.md)
Weekly Review Builder
Compress one week's activity into an updated, honest project state. Prevent long-term drift.
Input
Required:
project_card— full project card with current state, goals, phaseweekly_daily_logs— array of 5-7 daily loop logs from this weekweekly_decisions— decisions made during the weekweekly_outputs— tangible outputs produced this weekstale_tasks— tasks that were planned but not completed
Optional:
blocked_tasks— tasks that failed due to blockers
Output Schema
updated_current_phase: string # refreshed project phase
updated_current_bottleneck: string # the one most critical blocker now
next_week_goal: string # single clear goal for next week
next_3_actions: string[] # top 3 actions for next week
risk_check: string # honest assessment of current risks
one_page_project_summary: string # compressed project status (≤300 words)
review_confidence: "high" | "medium" | "low"
review_writeback: object # structured record for project memory
stale_tasks_resolved: string[] # tasks cleared this week
stale_tasks_remaining: string[] # tasks still pending
Rules
- Must remove outdated actions. If a planned task wasn't touched, mark it stale and either drop or reschedule it.
- Must identify the single current bottleneck. Not 3, not 5 — one.
- Must distinguish progress from activity. Meetings attended ≠ progress. Code shipped ≠ impact. Be precise.
- Must be honest if no real progress was made. Say so. A stagnant review is better than a flattering one.
- Evidence-based only. Do not update phase or bottleneck without supporting evidence from logs.
Review Phases
Phase 1: Log Compression
- Read all weekly_daily_logs
- Extract: findings, decisions, completions, blockers
- Separate actual progress from busy-work
Phase 2: Gap Analysis
- Compare weekly_outputs against weekly_daily_logs stated objectives
- Identify: what was claimed vs what was delivered
- Mark stale_tasks as resolved or remaining
Phase 3: State Refresh
- Update current_phase based on evidence (not ambition)
- Identify current bottleneck (the one thing blocking most progress)
- Assess risk: what's the biggest threat to the project right now?
Phase 4: Forward Planning
- Set next_week_goal (one clear goal)
- List next_3_actions (ranked by impact)
- Write one_page_project_summary for human readability
Phase 5: Writeback
- Populate review_writeback with structured record
- Set review_confidence based on evidence quality
Failure Handling
If evidence is insufficient (e.g., logs are missing, can't determine progress):
- Mark
review_confidence = "low" - Do not fabricate phase changes or bottleneck updates
- Request missing log recovery before completing review
- Write partial review with explicit gaps noted
安全使用建议
This skill appears internally consistent and limited to processing project data. Before installing, confirm where review_writeback will be stored (project memory vs. an external datastore) and whether you’re comfortable the agent may write structured review records into that memory. Because the skill can be invoked autonomously (platform default), review its outputs and writeback targets after first runs to ensure it behaves as you expect. No credentials or system access are requested by this skill.
功能分析
Type: OpenClaw Skill
Name: weekly-review-builder
Version: 1.0.0
The skill bundle is a project management tool designed to synthesize weekly activity logs into a structured status report. It contains only metadata and markdown instructions (SKILL.md) for an AI agent, with no executable code, network requests, or attempts to access sensitive system resources. The logic is entirely focused on data processing and reporting based on provided inputs.
能力评估
Purpose & Capability
The name and description match the SKILL.md: the skill asks for a project_card, weekly logs, decisions, outputs and stale tasks to produce an updated phase, bottleneck, next actions, and a writeback. All requested inputs are proportional to producing a weekly review.
Instruction Scope
Runtime instructions are limited to processing the provided inputs, performing evidence-based analysis, and producing a structured writeback. The SKILL.md does not instruct the agent to read unrelated system files, environment variables, or transmit data to external endpoints.
Install Mechanism
This is an instruction-only skill (no install spec, no code). Nothing will be downloaded or written to disk as part of an install, minimizing execution-surface risk.
Credentials
The skill requests no environment variables, credentials, or config paths. Inputs are explicit and scoped to project data; writeback is a structured object intended for project memory which is appropriate for this purpose.
Persistence & Privilege
Flags show always:false and default autonomous invocation settings. The skill does ask to populate review_writeback (normal for a review tool) but does not request persistent platform privileges or to modify other skills or system-wide settings.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install weekly-review-builder - 安装完成后,直接呼叫该 Skill 的名称或使用
/weekly-review-builder触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release: compress weekly activity into updated project state
元数据
常见问题
Weekly Review Builder 是什么?
Build a weekly review that refreshes project phase, bottleneck, and next steps. Use on: weekly schedule, after several daily loops, before resetting project... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 116 次。
如何安装 Weekly Review Builder?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install weekly-review-builder」即可一键安装,无需额外配置。
Weekly Review Builder 是免费的吗?
是的,Weekly Review Builder 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Weekly Review Builder 支持哪些平台?
Weekly Review Builder 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Weekly Review Builder?
由 sunbinnju-star(@sunbinnju-star)开发并维护,当前版本 v1.0.0。
推荐 Skills