From cf-powers
Loads and executes written implementation plans with review checkpoints, branch safety, and verification steps. Useful for multi-phase or single-phase plan execution.
How this skill is triggered — by the user, by Claude, or both
Slash command
/cf-powers:executing-plansThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Load plan, review critically, execute all tasks, report when complete.
Load plan, review critically, execute all tasks, report when complete.
Announce at start: "I'm using the executing-plans skill to implement this plan."
Note: Subagent-driven development (cf-powers:subagent-driven-development) produces significantly higher quality results. If subagents are available, prefer that skill over this one.
git branch --show-currentmain or master: STOP — ask user to create/switch to a feature branch firstFor multi-phase plans (index exists):
For single-phase plans:
Context loading principle: Only load what you need for the current phase. If you need context from a previous phase's plan, read it on-demand, not upfront.
For each task:
After all tasks complete and verified:
STOP executing immediately when:
Ask for clarification rather than guessing.
Return to Review (Step 1) when:
Don't force through blockers - stop and ask.
Required workflow skills:
Note: User manages their own branches. Step 0 verifies a feature branch exists — do NOT create worktrees automatically.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub cloudfieldcz/cf-powers --plugin cf-powers