Skip to content
AI & Agents
Skill

/project-manager

Plan sprints, milestones, roadmaps, risks, dependencies, and stakeholder updates for team delivery.

BOOST
From plugin
hybridclaw
15989 skills
Install
$ npx -y skills add HybridAIOne/hybridclaw --skill project-manager --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/project-manager

Context preview

The summary Claude sees to decide when to auto-load this skill.

Plan sprints, milestones, roadmaps, risks, dependencies, and stakeholder updates for team delivery.

SKILL.md

project-manager.SKILL.md
name: project-manager
description: Plan sprints, milestones, roadmaps, risks, dependencies, and stakeholder updates for team delivery.
user-invocable: true
metadata:
  hybridclaw:
    category: productivity
    short_description: "Delivery plans and roadmaps."
    tags:
      - planning
      - management
      - enterprise
      - delivery
    related_skills:
      - notion
      - trello

Project Management

Use this skill for delivery planning and team-facing coordination artifacts.

Core Outputs

When the user does not specify a format, default to one of these:

  • implementation plan
  • milestone table
  • risk register
  • stakeholder update
  • sprint plan
  • dependency map

Default Structure

For delivery planning, use:

1. Goal 2. Scope 3. Milestones 4. Risks and mitigations 5. Dependencies 6. Owners or recommended owners 7. Next 3 concrete actions

For status updates, use:

1. Overall status 2. What moved this period 3. Current blockers 4. Decisions needed 5. Next checkpoint

Working Rules

  • Treat estimates as assumptions, not promises.
  • Name the biggest risks early.
  • Sequence high-uncertainty work before polish work.
  • Prefer smaller deliverable increments over large all-at-once plans.
  • If dates are requested without capacity data, state the assumption clearly.
  • When the user asks for something pasteable into a team tool, keep formatting plain and compact.

Common Patterns

Risk Register

Use a compact table or bullet list with:

  • risk
  • impact
  • probability
  • mitigation
  • owner

Sprint Plan

Break work into:

  • sprint goal
  • committed items
  • stretch items
  • dependencies
  • explicit exit criteria

Stakeholder Update

Keep it short and decision-oriented:

  • objective
  • current state
  • what changed
  • risk or ask
  • next checkpoint

Pitfalls

  • Do not commit to deadlines without listing assumptions.
  • Do not hide dependencies in prose.
  • Do not confuse activity with progress; anchor on outcomes.
  • Do not generate ceremony for its own sake when a lighter artifact will do.
Read more
Ships withhybridclaw

Enterprise-ready self-hosted AI assistant runtime with sandboxed execution, secure credentials, approvals, and memory

Get the whole plugin
Stats
159
Stars
17
Forks
Active
Maintenance
TypeScript
Language
MIT
License
13h ago
Last commit
8mo ago
Created
3h ago
Added

Repo: HybridAIOne/hybridclaw

Other skills on hybridclaw.