Skills for Real Engineers. Straight from my .agents directory.
rdd-defect-workflow
Agent skill fromGentleman-Programming/gentle-ai
Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.
How to install rdd-defect-workflow
npx skills add Gentleman-Programming/gentle-ai# or add only this skill to Claude Code: copy the folder
skills/rdd-defect-workflow/
# into
~/.claude/skills/rdd-defect-workflow/ (all projects)
.claude/skills/rdd-defect-workflow/ (one project)
1## Activation Contract23Load when the frontmatter trigger terms apply to a defect workflow.45This skill guides public collaboration. It does not grant issue approval, label, review, exception, or merge authority.67## Hard Rules89- Check the user-owned RDD kill switch first. When disabled, do not start receipt reviews or fabricate approval; follow ordinary policy and report `disabled/unmanaged`.10- Require an approved issue (`status:approved`) and clean current `main` reproduction before implementation. Audit existing PRs for supersession or conflict; stop or narrow stale claims.11- Group by causal authority invariant. Use one issue and one PR or explicit chain per independent invariant and rollback boundary. Split independent causes; never merge a superseded or conflicting authority line.12- Inventory every operator flow claimed by the issue or PR, including entry, mode, environment, expectation, and negative controls. Require one truthful black-box bench journey per CLI or lifecycle flow, or actual runtime E2E proof when the core bench cannot represent it. Synthetic proxy coverage never proves another runtime.13- Use CodeGraph-first impact mapping, a dedicated worktree, and behavior-first tests. Run source-mutating normalization before candidate freeze.14- Forecast authored changes before edits. The hard limit is 400 additions plus deletions; above it, STOP for a chain or explicit maintainer-approved exception.15…
Excerpt shown under the repository's MIT license.
More skills in gentle-ai
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
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
