Alex the Planning Strategist
Turns confirmed requirements into an ordered, dependency-aware implementation checklist with milestones.
- Repository
- sickn33/agentic-awesome-skills
- Stars
- 49,023
- Licence
- MIT
- Files
- 1 file
What it does
This is a planning persona for an AI agent. Once installed, the agent takes a written requirements document and breaks it into small, ordered tasks, shows which tasks block others, groups them into shippable milestones, and gives each task a pass/fail 'definition of done'. It is designed to sit inside a multi-agent squad, handing its plan to architecture, implementation and review roles, but it works as a standalone planning method as well. It only plans; it does not write code.
Great for
- Developers who want a structured task breakdown before starting a feature
- Tech leads drafting an ordered checklist with acceptance criteria from a spec
- Teams running a multi-agent workflow that expects a planning step
Skip it if
- Simple one-off coding tasks, where a plan adds overhead without benefit
- Projects with no written requirements, since the skill expects a confirmed requirement input and will flag gaps rather than invent them
- Anyone expecting time estimates: it deliberately uses relative sizes (S/M/L/XL) instead
Try asking
- “Here is our requirements doc for a multi-tenant billing feature. Produce an ordered implementation checklist with dependencies and definitions of done.”
- “Break the user-profile feature into milestones I can demo, and mark which tasks are security-sensitive.”
- “Re-plan the auth work now that we've dropped social login, showing only the changes to the critical path.”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
alex.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip alex.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip alex.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Give it a clear, confirmed requirements document first; vague input produces [BLOCKED] items rather than a useful plan.
- Ask for a plan amendment rather than a full rewrite when scope changes, so you can see exactly what moved.
- Treat the output as a draft to review: the skill itself warns that agents can hallucinate and plans should be checked by a human.
What's inside
- SKILL.md
Redistributed unmodified from sickn33/agentic-awesome-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.