← 返回 Skills 市场
744
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install afrexai-capacity-planner
功能描述
Analyzes team size, workload, and pipeline data to forecast capacity, identify bottlenecks, and recommend actions 4-8 weeks before crises occur.
使用说明 (SKILL.md)
Capacity Planner
Plan team and infrastructure capacity before it becomes a crisis.
What It Does
Takes your current workload data — team size, utilization rates, project pipeline, seasonal patterns — and builds a forward-looking capacity model. Flags bottlenecks 4-8 weeks before they hit.
When to Use
- Sprint planning feels like guesswork
- You're not sure if you can take on a new client/project
- Hiring decisions need data, not gut feel
- Infrastructure keeps getting slammed at predictable times
How to Use
Tell the agent about your situation:
"We have 8 engineers, 3 active projects, and a new client starting in March. Can we handle it?"
The agent will:
- Audit current load — Map people to commitments, calculate true utilization (not the number in your head)
- Model scenarios — What happens if the new project lands? What if two people quit? What if scope grows 30%?
- Flag risks — Identify single points of failure, overloaded roles, deadline clusters
- Recommend actions — Hire, redistribute, defer, or say no — with numbers behind each option
Capacity Framework
Utilization Bands
| Band | Rate | Meaning |
|---|---|---|
| 🟢 Green | \x3C70% | Healthy buffer for unplanned work |
| 🟡 Yellow | 70-85% | Sustainable but tight |
| 🔴 Red | >85% | Burnout zone — something will slip |
Key Metrics
- Effective capacity = headcount × available hours × efficiency factor (typically 0.7-0.8)
- Demand pipeline = committed hours + probable hours (weighted by likelihood)
- Buffer ratio = (capacity - demand) / capacity — target 15-25%
- Time to constraint = weeks until demand exceeds capacity at current trajectory
Scenario Template
For each scenario, output:
- Headcount needed vs. available
- Skill gaps (specific roles/capabilities missing)
- Timeline risk (which deadlines move)
- Cost impact (overtime, contractors, lost revenue from saying no)
- Recommended action with confidence level
Output Format
CAPACITY SNAPSHOT — [Date]
━━━━━━━━━━━━━━━━━━━━━━━━━━
Team: [size] | Utilization: [%] | Buffer: [%]
Status: 🟢/🟡/🔴
CURRENT COMMITMENTS
- [Project A]: [X people, Y hours/week, end date]
- [Project B]: ...
PIPELINE (next 8 weeks)
- [Incoming work]: probability %, estimated load
- ...
RISKS
1. [Risk description + impact + timeframe]
2. ...
SCENARIOS
A) [Scenario]: [outcome summary]
B) [Scenario]: [outcome summary]
RECOMMENDATION
[Clear action with reasoning]
Tips
- Refresh capacity snapshots weekly during planning
- Track actual vs. predicted utilization to calibrate your efficiency factor
- Include non-project work (meetings, support, admin) — it's usually 20-30% of capacity
- Don't plan above 80% utilization. The remaining 20% isn't slack, it's where real work happens.
Go Deeper
Your capacity model is one piece of operational planning. For full business context packs covering finance, operations, and growth strategy across 10 industries:
→ AfrexAI Context Packs — $47 each, built by operators who've done the work.
→ AI Revenue Calculator — Find out where your business is leaking money (free tool).
→ Agent Setup Wizard — Get your AI agent configured for your specific business in 5 minutes.
安全使用建议
This skill appears coherent and low-risk: it only provides instructions for capacity planning and requests no credentials or installs. Before installing, consider: (1) what team/project data you'll share with the agent—avoid pasting secrets or sensitive PII; (2) the external links in the docs are marketing pages—verify them independently before paying; and (3) if you prefer to limit autonomous behavior, restrict model-invocation or agent permissions in your agent settings so the skill cannot be called without your approval.
功能分析
Type: OpenClaw Skill
Name: afrexai-capacity-planner
Version: 1.0.0
The skill bundle provides instructions for an AI agent to perform capacity planning. All files (_meta.json, SKILL.md, README.md) are consistent with the stated purpose. SKILL.md contains detailed instructions for the agent's logic and output format, and there are no signs of prompt injection attempting to make the agent deviate from its purpose or perform malicious actions. The external links in SKILL.md and README.md are promotional and informational, pointing to related resources on `github.io` domains, and are not presented as commands for the agent to execute or data to exfiltrate. There is no evidence of data exfiltration, malicious execution, persistence, or obfuscation.
能力评估
Purpose & Capability
The README and SKILL.md both describe a capacity-planning assistant (team/infrastructure modeling, scenario analysis, recommendations). There are no declared binaries, environment variables, or config paths that are unrelated to that purpose. The only minor issue is that the top-level description field is empty in the registry metadata, but the included files provide the expected functionality.
Instruction Scope
All runtime instructions are high-level workflow guidance (what to ask, what outputs to produce). The SKILL.md does not instruct the agent to read local files, access environment variables, call arbitrary endpoints, or exfiltrate data. Output format and scenario templates are scoped to capacity planning.
Install Mechanism
This is an instruction-only skill with no install spec and no code files — nothing is written to disk or downloaded. That is the lowest-risk install model.
Credentials
The skill declares no required environment variables, credentials, or config paths. There are no requests for keys, tokens, or unrelated service credentials — proportional to the described purpose.
Persistence & Privilege
Flags show default behavior (always: false, agent-invocable, model invocation allowed). The skill does not request permanent presence nor instruct modifications to 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 afrexai-capacity-planner - 安装完成后，直接呼叫该 Skill 的名称或使用
/afrexai-capacity-planner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 of Capacity Planner skill.
- Build forward-looking workload models based on team size, utilization, pipeline, and seasonal trends.
- Automatically flag bottlenecks and risks 4-8 weeks in advance.
- Output structured capacity snapshots, risk summaries, and actionable recommendations.
- Includes built-in scenario modeling for hiring, project changes, and unexpected staff loss.
- Provides clear utilization bands and key metrics to support data-driven planning.
元数据
常见问题
Capacity Planner 是什么？
Analyzes team size, workload, and pipeline data to forecast capacity, identify bottlenecks, and recommend actions 4-8 weeks before crises occur. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 744 次。
如何安装 Capacity Planner？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install afrexai-capacity-planner」即可一键安装，无需额外配置。
Capacity Planner 是免费的吗？
是的，Capacity Planner 完全免费（开源免费），可自由下载、安装和使用。
Capacity Planner 支持哪些平台？
Capacity Planner 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 Capacity Planner？
由 1kalin（@1kalin）开发并维护，当前版本 v1.0.0。
推荐 Skills