zaffnet
- 10 skills
- 0 followers
- 7 hours ago last updated
- ▌
- ▌ Align Docs With Code · zaffnetFan a team of subagents across a project's code and its docs, find every place the docs contradict the code, fix the docs surgically, then tighten the prose and open a PR. Use only when the user runs /align-docs-with-code.
- ▌ Deep Claude Code Review · zaffnetClaude-only variant of deep-pr-review: several independent Claude Code subagents review the same change at the highest effort available, findings merged by agreement. Reviews a GitHub PR URL and posts inline comments after per-comment confirmation, or, with no PR, reviews the current branch or working tree and writes deep-review.local.md. Use only when the user asks for a Claude-only deep review or runs /deep-claude-code-review.
- ▌ Sync Machine Config To Repo · zaffnetScan this macOS machine for dotfiles, configs, installed apps, and packages that whetstone does not manage yet, decide how each one should be managed, then add the worthwhile ones to the repo on a branch and open a PR. Use only when the user runs /sync-machine-config-to-repo.
- ▌ Address Pr Comments Sequential · zaffnetAddress unresolved GitHub PR review comments one at a time.
- ▌
- ▌ Writing Whip · zaffnetKill all AI writing tropes and behaviours at the source: generation. Focus on quelling behaviour-driven triggers. Load before writing, especially for anything longer than a paragraph and re-check output against it, extremely important for communications, documentation, outbound, client-facing copy and for your own replies to the user.
- ▌ Prose Honesty · zaffnetJudge every sentence a coding agent writes that is not language syntax -- comments, docstrings, READMEs, design docs, ADRs, PR and commit bodies -- against one bar: does a reader who arrives next year, having never seen this change, need it? Load before writing or editing any such text, and re-check the output against it before handing back.
- ▌ Deep Pr Review · zaffnetMulti-model code review: one independent reviewer per model you can reach (OpenAI, Anthropic, Google, ...), findings merged by agreement. Reviews a GitHub PR URL and posts inline comments after per-comment confirmation, or, with no PR, reviews the current branch or working tree and writes deep-review.local.md. Use only when the user asks for a deep or multi-model review or runs /deep-pr-review.
- ▌