gentle-ai SKILL.md skillA

This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.

gentle-ai from gentleman-programming/gentle-shell is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add gentleman-programming/gentle-shell/gentle-ai@git:20261105.895f353

Pins git:20261105.895f353 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
gentleman-programming/gentle-shell
Path
skills/gentle-ai/SKILL.md
Versions recorded
17
Latest version
git:20261105.895f353, committed Nov 5, 2026
First version recorded
Aug 15, 2026
Size
5,586 bytes
Repository stars
2,084
License
MIT

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.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# el Gentleman Harness

Use this skill for non-trivial, risky, or multi-step ODD work.

## Identity Rule

When 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.

## Compact Rules

- 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.
- 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.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add gentleman-programming/gentle-shell/gentle-ai@sha256:d0724dcb007d092d

The line at the top of this page pins the label git:20261105.895f353, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_iqosfcfu5ovwysso.svg)](https://markdownregistry.com/a/art_iqosfcfu5ovwysso)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 17 versions of this file, between Aug 15, 2026 and Nov 5, 2026, about one every 5 days.

versioncommittedcommitsizeaudit
git:20261105.895f353 latest2026-11-05 895f353 5,586 BA view · diff
git:20261031.6c780fc2026-10-31 6c780fc 5,542 BA view · diff
git:20261029.4446a192026-10-29 4446a19 5,283 BA view · diff
git:20261015.f4a7bef2026-10-15 f4a7bef 5,064 BA view · diff
git:20261014.922af3f2026-10-14 922af3f 4,913 BA view · diff
git:20261004.6f3d8cc2026-10-04 6f3d8cc 4,827 BA view · diff
git:20261004.d45f1982026-10-04 d45f198 4,756 BA view · diff
git:20261003.696dcee2026-10-03 696dcee 4,801 BA view · diff
git:20261003.94df6002026-10-03 94df600 4,794 BA view · diff
git:20261003.fea6c542026-10-03 fea6c54 4,715 BA view · diff
git:20260930.14bd2352026-09-30 14bd235 4,347 BA view · diff
git:20260925.a76e6f22026-09-25 a76e6f2 3,926 BA view · diff
git:20260821.c4079d12026-08-21 c4079d1 3,708 BA view · diff
git:20260817.818c3e62026-08-17 818c3e6 12,932 BA view · diff
git:20260816.5e1bfd22026-08-16 5e1bfd2 12,932 BA view · diff
git:20260816.10735342026-08-16 1073534 12,933 BA view · diff
git:20260815.adad5792026-08-15 adad579 12,826 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5586 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

gentleman-programming/gentle-shell · 2,084 stars · license MIT · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_iqosfcfu5ovwysso
GET https://markdownregistry.com/api/v1/resolve?ref=gentleman-programming/gentle-shell/gentle-ai
GET https://markdownregistry.com/api/v1/blob/d0724dcb007d092dca44433b348fbadfd43c2ad83f5f7c37d2cf0ec2dbf36827

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from gentleman-programming/gentle-shell

gentle-ai-branch-pr SKILL.md skill
gentleman-programming/gentle-shell · skills/branch-pr/SKILL.md · Prepare pull requests using the target repository's contribution policy. Trigger: creating, opening, or preparing PRs…
v2.1 · audit A · 2,084 stars
gentle-ai-chained-pr SKILL.md skill
gentleman-programming/gentle-shell · skills/chained-pr/SKILL.md · Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review…
v1.0 · audit A · 2,084 stars
gentle-ai-cognitive-doc-design SKILL.md skill
gentleman-programming/gentle-shell · skills/cognitive-doc-design/SKILL.md · Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or…
v1.0 · audit A · 2,084 stars
gentle-ai-comment-writer SKILL.md skill
gentleman-programming/gentle-shell · skills/comment-writer/SKILL.md · Write warm, direct collaboration comments. Trigger: PR feedback, issue replies, reviews, Slack messages, or GitHub…
v1.0 · audit A · 2,084 stars
gentle-design SKILL.md skill
gentleman-programming/gentle-shell · skills/design/SKILL.md · Trigger: design a screen or page, mockup, landing page, UI directions, artboards, try a different approach, design…
v1.0 · audit A · 2,084 stars
gentle-ui-design SKILL.md skill
gentleman-programming/gentle-shell · skills/gentle-ui-design/SKILL.md · Trigger: product interface design, web UI, design critique, browsing experience, responsive layout. Guide usable…
v1.0 · audit A · 2,084 stars
gentle-ai-issue-creation SKILL.md skill
gentleman-programming/gentle-shell · skills/issue-creation/SKILL.md · Create and triage GitHub issues from repository evidence. Trigger: issue creation, bug reports, feature requests, or…
v1.3 · audit A · 2,084 stars
gentle-ai-judgment-day SKILL.md skill
gentleman-programming/gentle-shell · skills/judgment-day/SKILL.md · Trigger: judgment day, judgement day, dual review, adversarial review, juzgar. Run explicit blind dual review with at…
v1.7 · audit A · 2,084 stars
gentle-ai-rdd-defect-workflow SKILL.md skill
gentleman-programming/gentle-shell · skills/rdd-defect-workflow/SKILL.md · Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill…
v1.0 · audit A · 2,084 stars
gentle-ai-skill-creator SKILL.md skill
gentleman-programming/gentle-shell · skills/skill-creator/SKILL.md · Trigger: /skill-creation, skill creation, skill creator, create skill, new skill. Create LLM-first skills with valid…
v1.0 · audit A · 2,084 stars
gentle-ai-skill-improver SKILL.md skill
gentleman-programming/gentle-shell · skills/skill-improver/SKILL.md · Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills.
v1.0 · audit A · 2,084 stars
gentle-ai-skill-registry SKILL.md skill
gentleman-programming/gentle-shell · skills/skill-registry/SKILL.md · Trigger: update skills, skill registry, actualizar skills, after skill changes. Index available skills by trigger and…
v1.0 · audit A · 2,084 stars

Every file in gentleman-programming/gentle-shell

Other files named gentle-ai

gentle-ai SKILL.md skill
gentleman-programming/gentle-pi · skills/gentle-ai/SKILL.md · Use Gentle AI harness discipline for Pi work: clarify first, track ODD work, use applicable test-first development by…
git:20261105.895f353 · audit A · 2,023 stars

Browse by kind, by grade A, or by owner.