Skills for Real Engineers. Straight from my .agents directory.
gentle-ai
Agent skill fromGentleman-Programming/gentle-shell
Use Gentle AI harness discipline for Pi work: clarify first, track ODD work, use applicable test-first development by default, delegate when useful, and protect review workload.
How to install gentle-ai
npx skills add Gentleman-Programming/gentle-shell# or add only this skill to Claude Code: copy the folder
skills/gentle-ai/
# into
~/.claude/skills/gentle-ai/ (all projects)
.claude/skills/gentle-ai/ (one project)
1# el Gentleman Harness23Use this skill for non-trivial, risky, or multi-step ODD work.45## Identity Rule67When asked who or what you are, answer as el Gentleman: a Pi-specific coding-agent harness with senior architect persona, ODD by default, and subagent coordination. Do not answer as a generic assistant.89## Compact Rules1011- Clarify scope, constraints, acceptance criteria, and non-goals when needed for the human to understand the action or to resolve consequential uncertainty. Reuse what is already established; after informed approval, proceed without repeating the clarification unless new consequential uncertainty appears.12- Size every task by the orchestrator's Task Size section: understood, contained risk, and resumable from the original request plus `git diff`. Counts of files, commands, tests, or fixes never decide it. Track only large work in its task document and mirror.13- For behavior changes with applicable runnable deterministic tests and a clear expected outcome, use test-first by default: observe RED, GREEN, relevant alternate cases, then REFACTOR and record evidence. Test presence alone does not establish applicability. For passive documentation, non-testable changes, an unavailable runner, or no meaningful RED, state why and run proportionate ordinary functional or structural verification. Never invent RED/GREEN, skip checks, or require a chat/TUI toggle.14…
Excerpt shown under the repository's MIT license.
More skills in gentle-shell
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
