agentleFS
xsovad06xsovad06/sova/.agents/skills/sova-review-full/SKILL.md

sova-review-full

Skill3 starsChanged 8 days agoApache-2.0View on GitHub

Full pre-push pipeline (simplify changed code, review as senior engineer, organize commits). Run before the `sova-pr` skill.

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 8 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run a complete pre-push quality pipeline: simplify code, review for issues, then organize commits into clean history.

    line 8
  2. Very specific:

    Follow the sova-simplify skill workflow.

    line 14
  3. Distinctive:

    If no simplifications are needed, state that and move on.

    line 36
  4. Very specific:

    Follow the sova-review skill workflow:

    line 40
  5. Very specific:

    Run the full CI-equivalent checks: make check.

    line 44
  6. Distinctive:

    Create small, logical, atomic commits in dependency order.

    line 54
  7. Distinctive:

    Verify: all changes committed, each commit atomic, total diff matches the backup branch.

    line 55
  8. Very specific:

    After this command completes, run the sova-pr skill to create the pull request.

    line 77
  9. Distinctive:

    All findings are addressed by default: fix or acknowledge with justification (false positive, not applicable, requires human decision).

    line 86
  10. Distinctive:

    Do NOT reformat code that wasn't changed in this branch.

    line 88
  11. Distinctive:

    If a simplification or fix is risky, flag it for human review instead of applying.

    line 89
  12. Distinctive:

    NEVER use emojis in any output.

    line 91

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Full Review Pipeline

Run a complete pre-push quality pipeline: simplify code, review for issues, then organize commits into clean history.

Scope: the arguments provided when this skill is invoked

Phase 1: Simplify

Follow the sova-simplify skill workflow. Review all changed code for opportunities to reduce complexity:

  1. Get the diff scope:
    BASE=$(git symbolic-ref --short refs/remotes/origin/HEAD 2>/dev/null | sed 's#^origin/##')
    BASE=${BASE:-main}
    git fetch --quiet origin "$BASE"
    git diff "origin/$BASE"...HEAD --stat
    git diff --cached --stat
    git diff --stat
  2. For each changed file, read the entire file and check:
    • Code reuse: does new code duplicate existing utilities or helpers? Search the codebase.
    • Over-engineering: unnecessary abstractions, premature generalization, excessive configurability
    • Dead code: unused imports, unreachable branches, commented-out code
    • Redundancy: repeated logic that could be a shared helper (only if 3+ occurrences)
    • Complexity: can any function be simplified without losing clarity?
    • Efficiency: redundant computations, repeated file reads, duplicate API calls
  3. Apply simplifications directly. After each change, verify tests still pass (see CLAUDE.md for commands).
  4. If no simplifications are needed, state that and move on.

Phase 2: Review

Follow the sova-review skill workflow:

  1. Review all changed files for bugs, security, performance, test coverage, consistency, doc freshness, and scout rule (fix pre-existing issues in touched files).
  2. Score each finding (1-10 priority). Address all findings (fix or acknowledge with justification).
  3. Run the full CI-equivalent checks: make check. Fix any failures before proceeding.
  4. Report findings in the standard review format.

See the sova-review skill for the full review checklist and scoring criteria.

Phase 3: Organize Commits

Follow the sova-rearrange-commits skill workflow:

  1. Snapshot uncommitted work as a WIP commit and create a backup branch, then soft reset to the fork point (git merge-base HEAD "origin/$BASE"), exactly as the sova-rearrange-commits skill Step 2 does. Never reset to origin/$BASE itself: re-committing this branch's tree on top of a base that moved silently reverts everything the base gained. Never use git stash: the stash stack is shared by every worktree and session.
  2. Create small, logical, atomic commits in dependency order.
  3. Verify: all changes committed, each commit atomic, total diff matches the backup branch.

See the sova-rearrange-commits skill for the full commit organization process.

Phase 4: Summary

## Review-Full Summary

**Simplifications**: N changes applied
**Review findings**: N total (N fixed, N acknowledged)
**Commits**: reorganized into N clean commits
**Assessment**: ready to push / needs human review

Workflow Chain

This command orchestrates:

  1. Simplify: reduce complexity and duplication
  2. the sova-review skill: senior-engineer code review with auto-fix
  3. the sova-rearrange-commits skill: organize into logical commits

After this command completes, run the sova-pr skill to create the pull request.

Cross-References

  • Came from: the sova-develop-full skill (as an alternative to its built-in Phase 2-3) or manual pre-push check
  • Next step: the sova-pr skill to create the pull request

Rules

  • All findings are addressed by default: fix or acknowledge with justification (false positive, not applicable, requires human decision).
  • Be thorough but not pedantic. Don't flag things that are correct and clear.
  • Do NOT reformat code that wasn't changed in this branch.
  • If a simplification or fix is risky, flag it for human review instead of applying.
  • Each phase builds on the previous: Phase 2 reviews the state after Phase 1's changes.
  • NEVER use emojis in any output.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.