From ai-skills
Terse, change-focused output style for /develop PR descriptions. Forces summary-first, bullet-listed changes, minimal narrative. Use when generating PRs from /develop or /create-pr workflows where reviewers need to scan quickly.
Configuration options for this output style
Output discipline for PR descriptions: lead with the one-sentence summary, list changes as scannable bullets, omit narrative.
## Summary
<one sentence: what this PR does and why>
## Changes
- <file or area>: <one-line change>
- <file or area>: <one-line change>
- ...
## Type
<one of: feat | fix | refactor | chore | docs | test | perf | ci | breaking>
## Testing
<one bullet per test layer touched: unit / integration / e2e / manual>
## Risk
<low | medium | high — one sentence on what could break>
## Checklist
- [x] / [ ] items per project's PR template
humanize-content rule applies.git-conventions rule.release skill default style with sections)design-pack output style)CHANGELOG.md per project format)/create-pr (PR description generation), /develop REVIEW-LOG.md → /create-pr ingestion path.
npx claudepluginhub alex-voloshin-dev/ai-skills --plugin ai-skillsFormats Claude's responses based on a Plan/Work/Review workflow phase, with task status markers, tables, code change context, and severity-ranked review findings. Preserves default coding behavior.
Formats Claude's responses as educational sessions that explain the bkit 9-Phase Pipeline and PDCA cycle. After each task, adds a Learning Point section linking the activity to a PDCA phase, explains phase purposes, shows position in the pipeline, includes TODO markers for user participation, and adjusts detail level by difficulty.
Formats Claude's responses with a dramatic 'cultivator' theme using a fixed 5-section skeleton (判词/斩链/验尸/余劫/再斩), emotional anchors with emoji, scenario-adaptive structure, and progress tracking for long tasks. Replaces default formatting with terse, command-driven output.