docs(skills): bring the harvesting-review skill and its house style to stable - #10270
Merged
Conversation
…o stable Extracted from #10030 so the next harvest runs with the improved skill instead of waiting for the develop -> stable release train. Every file here is byte-identical to #10030's version, so the branches converge rather than drift. - .agents/skills/harvesting-review/SKILL.md: 'Refine, don't accrete' leads the skill and outranks its other rules (measure the target file against its size range, compress or split one at its limit, repoint every inbound reference on a move, cut what the new rule supersedes, report added/removed lines). Adds the per-run rot sweep that fixes stale citations and defect-snapshot notes in the same PR, and routes a lesson into the skill that owns its workflow. - dev/guidelines/documentation.md: the 'For Internal Docs' writing style the skill points at, plus the no-line-number and relative-measurement rules. The skill's house-style pointer would dangle without this. - .agents/commands/pre-ci.md: plain 'ruff check' CI-parity step, since the invoke tasks run 'ruff check --diff' and exit 0 on violations with no autofix. - .agents/skills/monitoring-pull-requests/SKILL.md: don't escalate from a stale 'commits behind' count. Deliberately not included, because they would not be correct on stable yet: the speckit-extract repoint (targets dev/guidelines/backend/exceptions.md, which only exists on develop), and the .agents/rules/* and creating-changelog-entries changes (their stable copies have diverged, and #10259 already edits them against stable). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Contributor
There was a problem hiding this comment.
All reported issues were addressed across 4 files
Shadow auto-approve: would not auto-approve because issues were found.
Re-trigger cubic
saltas888
added a commit
that referenced
this pull request
Aug 14, 2026
cubic flagged these on #10270, the stable extraction; the files are byte-identical so they were live here too. The lint claim was factually wrong. Verified against tasks/main.py and tasks/backend.py: _lint_ruff runs 'uv run ruff check tasks models utilities python_testcontainers' and backend.ruff runs 'uv run ruff check backend', both plain. The only --diff is 'ruff format --check --diff', the formatter step. So the invoke tasks do exit nonzero on an unsuppressed BLE001 inside the paths they cover, and the real reason the whole-repo check is not redundant is coverage: CI runs 'ruff check . --exclude python_sdk', so a violation in development/, tests/, or a root-level script passes locally and fails in CI. Corrected in .agents/commands/pre-ci.md (both phases) and root AGENTS.md. - dev/guidelines/documentation.md: the citation example named core/regeneration/models.py::TargetSelection, a real module on develop but absent from stable. Replaced with a generic some/module.py::SomeClass, which is correct on both branches and cannot rot. - .agents/skills/harvesting-review/SKILL.md: the report template pointed at '(§6)' for house style, but §6 is Report; it now points at 'Refine, don't accrete'. The rot-sweep glob 'AGENTS.md */AGENTS.md' matched only one level deep, missing frontend/app/AGENTS.md and development/grafana/AGENTS.md; $(git ls-files '*AGENTS.md') covers all five and skips .venv, which a recursive glob would have pulled in. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Same fixes as on #10030 (757b34f), keeping every file byte-identical across the two branches. - the invoke-lint justification was factually wrong: main.lint and backend.ruff both run a plain 'ruff check', the only --diff is the formatter's. The real reason the whole-repo check matters is coverage, since CI lints everything outside the four dirs main.lint covers - the citation example named a develop-only module; now a generic placeholder - the report template's '(§6)' house-style pointer aimed at Report - the rot-sweep glob missed AGENTS.md files two levels deep Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Contributor
There was a problem hiding this comment.
0 issues found across 3 files (changes from recent commits).
Confidence score: 5/5
- Automated review surfaced no issues in the provided summaries.
- No files require special attention.
Shadow auto-approve: would auto-approve. Docs and agent-tooling only—updates markdown guidelines and agent skills with no code, schema, or operational tradeoffs. Changes are bounded and self-consistent to the docs tree.
Re-trigger cubic
minitriga
approved these changes
Aug 14, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Why
This is just the extraction for the stable branch from the already approved #10030