Updated today
by Gentleman-Programming
gentle-ai
Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Organic-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in.
8.4k GitHub stars (8,418)
+839 in 30 days
| Period | New stars |
|---|---|
| Sep 27 | +5 |
| Sep 28 | +24 |
| Sep 29 | +39 |
| Sep 30 | +32 |
| Oct 1 | +15 |
| Oct 2 | +35 |
| Oct 3 | +36 |
| Oct 4 | +13 |
| Oct 5 | +27 |
| Oct 6 | +15 |
| Oct 7 | +21 |
| Oct 8 | +13 |
| Oct 9 | +22 |
| Oct 10 | +19 |
| Oct 11 | +31 |
| Oct 12 | +24 |
| Oct 13 | +29 |
| Oct 14 | +28 |
| Oct 15 | +27 |
| Oct 16 | +29 |
| Oct 17 | +25 |
| Oct 18 | +7 |
| Oct 19 | +14 |
| Oct 20 | +17 |
| Oct 21 | +30 |
| Oct 22 | +21 |
| Oct 23 | +26 |
| Oct 24 | +24 |
| Oct 25 | +28 |
| Oct 26 | +19 |
| Oct 27 | +27 |
| Oct 28 | +31 |
| Oct 29 | +42 |
| Oct 30 | +30 |
| Oct 31 | +8 |
| Nov 1 | +10 |
| Nov 2 | +10 |
| Nov 3 | +19 |
| Nov 4 | +17 |
| Nov 5 | +68 |
| Nov 6 | +144 |
- 20 skills (20 skills found in its SKILL.md files)
- 883 forks (883 forks)
- Today last update (Last updated today)
Install
Skills CLI
npx skills add Gentleman-Programming/gentle-ai
Asks which skills and agents to install. Just one: npx skills add Gentleman-Programming/gentle-ai --skill gentle-ai-branch-pr — add -g for every project.
Claude Code
git clone https://github.com/Gentleman-Programming/gentle-aicp -r "gentle-ai/skills/branch-pr" ~/.claude/skills/
Copies the gentle-ai-branch-pr skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add Gentleman-Programming/gentle-ai
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
gentle-ai-branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
skills/branch-pr/ on GitHub (opens in a new tab)SKILL.md -
gentle-ai-chained-pr
Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.
skills/chained-pr/ on GitHub (opens in a new tab)SKILL.md -
cognitive-doc-design
Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.
skills/cognitive-doc-design/ on GitHub (opens in a new tab)SKILL.md -
comment-writer
Write warm, direct collaboration comments. Trigger: PR feedback, issue replies, reviews, Slack messages, or GitHub comments.
skills/comment-writer/ on GitHub (opens in a new tab)SKILL.md -
gentle-ai-bench
Trigger: bench, journey, journeys, driven mode, gentle-ai-bench, journey corpus, j-numbers, bench axis. Author and verify gentle-ai bench journeys; go test ./bench never proves driven execution.
skills/gentle-ai-bench/ on GitHub (opens in a new tab)SKILL.md -
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the contribution flow is in scope: opening an issue, drafting or editing a PR body, spli…
skills/gentle-ai-collab-perfect/ on GitHub (opens in a new tab)SKILL.md -
issue-root-resolution
Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue clusters by verified root cause.
skills/issue-root-resolution/ on GitHub (opens in a new tab)SKILL.md -
rdd-advisory-transport
Trigger: reviewer transport, advisory transport, review adapter, lens prompt/schema, OpenCode reviewer plugin, Codex reviewer, ReviewProviderContract. Enforce the shared Go advisory reviewer transport contract.
skills/rdd-advisory-transport/ on GitHub (opens in a new tab)SKILL.md -
rdd-defect-workflow
Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.
skills/rdd-defect-workflow/ on GitHub (opens in a new tab)SKILL.md -
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
skills/systemic-issue-triage/ on GitHub (opens in a new tab)SKILL.md -
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
skills/work-unit-commits/ on GitHub (opens in a new tab)SKILL.md -
branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
internal/assets/ on GitHub (opens in a new tab)skills/ branch-pr/ SKILL.md -
chained-pr
Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.
internal/assets/ on GitHub (opens in a new tab)skills/ chained-pr/ SKILL.md -
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
internal/assets/ on GitHub (opens in a new tab)skills/ go-testing/ SKILL.md -
hermes-ephemeral-delegation
Trigger: a mapping need, parallel units, context backstop, high-risk verify, fresh review, or multi-step debug. Delegate via delegate_task for a named reason.
internal/assets/ on GitHub (opens in a new tab)skills/ hermes-ephemeral-delegation/ SKILL.md -
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
internal/assets/ on GitHub (opens in a new tab)skills/ issue-creation/ SKILL.md -
judgment-day
Trigger: judgment day, dual review, adversarial review, juzgar. Run explicit blind dual review with at most two scoped fix/re-judgment rounds.
internal/assets/ on GitHub (opens in a new tab)skills/ judgment-day/ SKILL.md -
skill-creator
Trigger: new skills, agent instructions, documenting AI usage patterns. Create LLM-first skills with valid frontmatter.
internal/assets/ on GitHub (opens in a new tab)skills/ skill-creator/ SKILL.md -
skill-improver
Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills.
internal/assets/ on GitHub (opens in a new tab)skills/ skill-improver/ SKILL.md -
skill-registry
Trigger: update skills, skill registry, actualizar skills, after skill changes. Index available skills by trigger and path.
internal/assets/ on GitHub (opens in a new tab)skills/ skill-registry/ SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.