Gentleman-Programming

Gentleman-Programming/gentle-ai

Agent Claude Code

You are a judgment-day surgical fix agent. Execute the fix instructions provided in the delegate prompt exactly.

Gentleman-Programming/gentle-ai

Agent Claude Code

You are a judgment-day adversarial reviewer (Judge A). Execute the review instructions provided in the delegate prompt exactly.

Gentleman-Programming/gentle-ai

Agent Claude Code

You are a judgment-day adversarial reviewer (Judge B). Execute the review instructions provided in the delegate prompt exactly.

Gentleman-Programming/gentle-ai

Agent Claude Code

R2 Readability reviewer — naming, complexity, intention, maintainability, review size, and context clarity.

Gentleman-Programming/gentle-ai

Agent Claude Code

Detached read-only refuter for one transaction-wide batch of inferential severe findings.

Gentleman-Programming/gentle-ai

Agent Claude Code

R3 Reliability reviewer — behavior-first tests, coverage value, edge cases, determinism, contracts, and regressions.

Gentleman-Programming/gentle-ai

Agent Claude Code

R4 Resilience reviewer — fallbacks, retry/backoff, graceful degradation, observability, load, rollback, and SLO risks.

Gentleman-Programming/gentle-ai

Agent Claude Code

R1 Risk reviewer — security, privilege boundaries, data exposure, dependency risks, and merge-blocking vulnerabilities.

Gentleman-Programming/gentle-ai

Command Claude Code

Create or update an OpenCode skill using the bundled skill-creator workflow.

Gentleman-Programming/gentle-ai

Command Claude Code

Rebuild the OpenCode skill registry for the current project and installed skills.

Gentleman-Programming/gentle-ai

Skill Claude CodeCodex needs its repo

Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.

Gentleman-Programming/gentle-ai

Skill Claude CodeCodex

Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.

Gentleman-Programming/gentle-ai

Skill Claude CodeCodex

Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.

Gentleman-Programming/gentle-ai

Skill Claude CodeCodex

Write warm, direct collaboration comments. Trigger: PR feedback, issue replies, reviews, Slack messages, or GitHub comments.

Gentleman-Programming/gentle-ai

Skill Claude CodeCodex

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.

Gentleman-Programming/gentle-ai

Skill Claude CodeCodex

Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.

Gentleman-Programming/gentle-ai

Skill Claude CodeCodex

Trigger: a mapping need, parallel units, context backstop, high-risk verify, fresh review, or multi-step debug. Delegate via delegatetask for a named reason.

Gentleman-Programming/gentle-ai

Skill Claude CodeCodex

Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.

Gentleman-Programming/gentle-ai

Skill Claude CodeCodex

Trigger: judgment day, dual review, adversarial review, juzgar. Run explicit blind dual review with at most two scoped fix/re-judgment rounds.

Gentleman-Programming/gentle-ai

Skill Claude CodeCodex

Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.

Gentleman-Programming/gentle-ai

Skill Claude CodeCodex

Trigger: new skills, agent instructions, documenting AI usage patterns. Create LLM-first skills with valid frontmatter.

Gentleman-Programming/gentle-ai

Skill Claude CodeCodex

Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills.

Gentleman-Programming/gentle-ai

Skill Claude CodeCodex

Trigger: update skills, skill registry, actualizar skills, after skill changes. Index available skills by trigger and path.

Gentleman-Programming/gentle-ai

Skill Claude CodeCodex

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.