Skills for Real Engineers. Straight from my .agents directory.
executing-plans
Agent skill fromGanyuanRan/Aegis
Use when executing a written implementation plan across sessions or with review checkpoints. Small or single-slice plans stay inline. For same-session independent tasks, use subagent-driven-development instead.
How to install executing-plans
npx skills add GanyuanRan/Aegis# or add only this skill to Claude Code: copy the folder
skills/executing-plans/
# into
~/.claude/skills/executing-plans/ (all projects)
.claude/skills/executing-plans/ (one project)
1# Executing Plans23## Overview45Load plan, review critically, execute all tasks, report when complete.67**Announce at start:** "I'm using the executing-plans skill to implement this plan."89For non-trivial execution, include `Aegis Visibility`: briefly tie the active10slice to its plan, checkpoint, drift or verification boundary. At completion,11pass plan adherence, evidence, complexity and residual risk to12`verification-before-completion` for the unified receipt.1314If subagents are available and the plan has genuinely independent tasks,15prefer `subagent-driven-development`; lack of subagent support does not block16inline execution. Same-task agents share one workspace, and the coordinator17remains the only Git mutation owner.1819## The Process2021### Step 1: Load and Review Plan221. Read plan file232. If the plan or active checkpoint includes an `Execution Readiness View`,24 read it before implementation and compare the plan against its intent lock,25 scope fence, baseline lock, owner / contract constraints, compatibility26 boundary, retirement boundary, test obligations, review gates, drift /27 rewind rules, and evidence required before completion.283. Review critically - identify any questions or concerns about the plan294. If the view contradicts the plan, baseline, or current worktree evidence,30 return to plan review or refresh the advisory handoff before editing.315. Run the TDD Route Guard before implementation: confirm `Mode`, `Decision`, `Strict authority`,32…
Excerpt shown under the repository's MIT license.
More skills in Aegis
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
