gentle-ai-branch-pr
Gentleman-Programming/gentle-shell1.2k
Gentleman-Programming/gentle-shell1.2kgentle-ai-branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
测试
Gentleman-Programming/gentle-shell
共 12 个 Skill。
gentle-ai-chained-prGentleman-Programming/gentle-shell1.2k
Gentleman-Programming/gentle-shell1.2kgentle-ai-chained-pr
Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.
测试
gentle-ai-cognitive-doc-designGentleman-Programming/gentle-shell1.2k
Gentleman-Programming/gentle-shell1.2kgentle-ai-cognitive-doc-design
Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.
测试
gentle-ai-comment-writerGentleman-Programming/gentle-shell1.2k
Gentleman-Programming/gentle-shell1.2kgentle-ai-comment-writer
Write warm, direct collaboration comments. Trigger: PR feedback, issue replies, reviews, Slack messages, or GitHub comments.
测试
gentle-aiGentleman-Programming/gentle-shell1.2k
Gentleman-Programming/gentle-shell1.2kgentle-ai
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.
测试
gentle-ai-issue-creationGentleman-Programming/gentle-shell1.2k
Gentleman-Programming/gentle-shell1.2kgentle-ai-issue-creation
Create and triage GitHub issues from repository evidence. Trigger: issue creation, bug reports, feature requests, or issue approval.
测试
gentle-ai-judgment-dayGentleman-Programming/gentle-shell1.2k
Gentleman-Programming/gentle-shell1.2kgentle-ai-judgment-day
Trigger: judgment day, judgement day, dual review, adversarial review, juzgar. Run explicit blind dual review with at most two scoped fix/re-judgment rounds.
测试
gentle-ai-rdd-defect-workflowGentleman-Programming/gentle-shell1.2k
Gentleman-Programming/gentle-shell1.2kgentle-ai-rdd-defect-workflow
Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.
测试
gentle-ai-skill-creatorGentleman-Programming/gentle-shell1.2k
Gentleman-Programming/gentle-shell1.2kgentle-ai-skill-creator
Trigger: /skill-creation, skill creation, skill creator, create skill, new skill. Create LLM-first skills with valid frontmatter.
测试
gentle-ai-skill-improverGentleman-Programming/gentle-shell1.2k
Gentleman-Programming/gentle-shell1.2kgentle-ai-skill-improver
Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills.
测试
gentle-ai-skill-registryGentleman-Programming/gentle-shell1.2k
Gentleman-Programming/gentle-shell1.2kgentle-ai-skill-registry
Trigger: update skills, skill registry, actualizar skills, after skill changes. Index available skills by trigger and path.
测试
gentle-ai-work-unit-commitsGentleman-Programming/gentle-shell1.2k
Gentleman-Programming/gentle-shell1.2kgentle-ai-work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
测试