Accept upstream's ce-review pipeline rewrite (6-stage persona-based architecture with structured JSON, confidence gating, three execution modes). Retire 4 overlapping review agents (security-sentinel, performance-oracle, data-migration-expert, data-integrity-guardian) replaced by upstream equivalents. Add 5 local review agents as conditional personas in the persona catalog (kieran-python, tiangolo- fastapi, kieran-typescript, julik-frontend-races, architecture- strategist). Accept upstream skill renames (file-todos→todo-create, resolve_todo_ parallel→todo-resolve), port local Assessment and worktree constraint additions to new files. Merge best-practices-researcher with upstream platform-agnostic discovery + local FastAPI mappings. Remove Rails/Ruby skills (dhh-rails-style, andrew-kane-gem-writer, dspy-ruby) per fork's FastAPI pivot. Component counts: 36 agents, 48 skills, 7 commands. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2.0 KiB
2.0 KiB
Tone Guide for Ticket Writing
Core Principle
A human will read this ticket. Write like a teammate asking for help, not an AI generating a spec.
Pressure Test Checklist
Review every sentence against these questions:
1. Patronizing language
- Does any sentence explain the reader's own domain back to them?
- Would you say this to a senior engineer's face without feeling awkward?
- Are you telling them HOW to implement something in their own system?
- Are you preemptively arguing against approaches they haven't proposed?
Examples of patronizing language:
- "This is a common pattern in Kubernetes deployments" (they know)
- "Helm charts support templating via {{ .Values }}" (they wrote the chart)
- "Why X, not Y" sections that dismiss alternatives before anyone suggested them
2. AI-isms to remove
- Em dashes used more than once per paragraph
- Every thought is a bullet point instead of a sentence
- Rigid structure that feels generated (Ask -> Why -> Context -> AC)
- Spec-writing voice: "When absent or false, existing behavior is preserved"
- Overuse of "ensures", "leverages", "facilitates", "streamlines"
- Unnecessary hedging: "It should be noted that..."
- Filler transitions: "Additionally", "Furthermore", "Moreover"
- Lists where prose would be more natural
3. Human voice check
- Does it sound like something you'd type in Slack, cleaned up slightly?
- Are there moments of humility? ("you'd know better than us", "if we're missing something")
- Is the tone collaborative rather than directive?
- Would you feel comfortable putting your name on this?
4. Kindness check
- Frame requests as requests, not demands
- Acknowledge the reader's expertise
- Offer context without over-explaining
- "Happy to chat more" > "Please advise"
What to keep
- Technical detail and specifics (the reader needs these)
- Code snippets showing current state and desired state
- File references with line numbers
- Clear "done when" criteria (but keep them minimal)