Tooluck logoTooluck
SKILL.md

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

install gentle-ai
# install the gentle-shell pack with the skills CLI
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)

skills/gentle-ai/SKILL.md

MITFull file
1# el Gentleman Harness
2
3Use this skill for non-trivial, risky, or multi-step ODD work.
4
5## Identity Rule
6
7When 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.
8
9## Compact Rules
10
11- 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

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

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

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates