← ClaudeAtlas

oss-pr-distilllisted

Distillation phase for oss-pr-lessons playbook — compress raw learnings into repo-specific patterns and update shared general skill
kookr-ai/kookr · ★ 2 · AI & Automation · score 78
Install: claude install-skill kookr-ai/kookr
# OSS PR Distill > **Requires:** the `pr-contribution-excellence` skill at `~/.claude/skills/pr-contribution-excellence/SKILL.md` (bundled with the `kookr-toolkit` plugin since 0.5 — see `docs/hooks-setup.md`). If absent, the plugin is not installed; stop and report the missing dependency rather than fabricating distilled patterns. Read all accumulated raw learnings, identify patterns, and write them to repo-specific and general output files. Generalized version of `codex-pr-distill`. ## When to Use Invoked when `oss-pr-threshold` returns `DISTILL`. ## Non-Negotiable Rules | # | Rule | Violation Example | Correct Pattern | |---|------|-------------------|-----------------| | 1 | Read ALL raw learnings before distilling | Only reading the latest batch | Read entire learnings-raw.md | | 2 | Preserve prior distilled content | Overwriting previous distillation | Read existing distilled files, merge new patterns | | 3 | Separate repo-specific from general patterns | Putting repo-specific convention in general skill | Repo-specific -> patterns.md; General -> pr-contribution-excellence | | 4 | Reset learnings-raw.md after distillation | Leaving raw file to grow unboundedly | Reset to header template (6 lines) | | 5 | Update distillation_count in state.json | Forgetting to track | Increment count, set last_distillation_at | | 6 | Patterns must be evidence-based | "I think PRs should..." | "PRs that {pattern} were {outcome} — seen in #{n1}, #{n2}" | ## Parameters - **repoFullN