Skip to content

im-shashanks/claude-plugins / shaktra/skills/shaktra-quality

shaktra-quality

Verified

Quality engine for the TDD pipeline — provides quick-check (36 checks) for gate reviews and comprehensive review (14 dimensions) for final quality assessment. Loaded by sw-quality agent.

FileKindSize
SKILL.mdskill md3.5 KB
architecture-checks.mdmarkdown6.4 KB
comprehensive-review.mdmarkdown6.5 KB
performance-data-checks.mdmarkdown6.5 KB
quick-check.mdmarkdown13.1 KB
security-checks.mdmarkdown6.0 KB
---
name: shaktra-quality
description: >
  Quality engine for the TDD pipeline — provides quick-check (36 checks) for gate reviews
  and comprehensive review (14 dimensions) for final quality assessment. Loaded by sw-quality agent.
user-invocable: false
---

# Shaktra Quality — Quality Engine

This skill provides the review checklists and processes used by the sw-quality agent during TDD pipeline gates. It operates in two modes: quick-check for gate reviews and comprehensive for final assessment.

## Boundary

**This skill defines:** HOW to evaluate code and tests (check procedures, gate logic, review processes).

**shaktra-reference defines:** WHAT severity levels mean (`severity-taxonomy.md`), WHAT quality dimensions exist (`quality-dimensions.md`), and WHAT the merge gate logic is.

**shaktra-tdd defines:** HOW to write tests and code (practices, patterns). This skill evaluates adherence to those practices.

This skill never restates severity definitions or quality dimension frameworks — it references them.

## Modes

### QUICK_CHECK (TDD Gate Reviews)

- 36 checks organized by gate (Plan, Test, Code)
- All checks loaded regardless of tier (check depth controls severity enforcement, not loading)
- Gate-specific focus: sw-quality applies the subset relevant to the current gate
- Max 3 fix loops per gate
- Defined in `quick-check.md`

### COMPREHENSIVE (Final Quality Review)

- Full 14-dimension review (A-M from `quality-dimensions.md` + Dimension N: Plan Adherence)
- Coverage verification via actual test execution
- Observation capture: extract observations from handoff for memory-curator consolidation
- Cross-story consistency: compare against existing `principles.yml`
- Defined in `comprehensive-review.md`

### REFACTOR_VERIFY (Refactoring Verification)

- Confirms refactoring preserved behavior and improved quality
- Verifies: all tests green, coverage not decreased, no new P0/P1, smell count reduced
- For structural tier: additionally checks architecture boundaries and circular dependencies
- Emits `REFACTOR_PASS` or `REFACTOR_BLOCKED`

## Gate Logic

Read from `shaktra-reference/severity-taxonomy.md` — restated here as operational reference:

```
p0_count = count findings where severity == P0
p1_count = count findings where severity == P1
p1_max   = read settings.quality.p1_threshold

if p0_count > 0:
    emit CHECK_BLOCKED
else if p1_count > p1_max:
    emit CHECK_BLOCKED
else:
    emit CHECK_PASSED
```

Max fix loops: 3 per gate. After 3 failed attempts, emit `MAX_LOOPS_REACHED` and escalate to user with all unresolved findings.

## Sub-Files

| File | Purpose |
|---|---|
| `quick-check.md` | 36 checks with IDs, severities, gates, detection guidance, and examples |
| `comprehensive-review.md` | Full 14-dimension review process with plan adherence and decision consolidation |
| `performance-data-checks.md` | Performance and data layer checks (PG-01 through PG-08, DL-01 through DL-08) |
| `security-checks.md` | Security checks aligned with OWASP Top 10 (SE-01 through SE-12, ST-01 through ST-03) |
| `architecture-checks.md` | Architecture governance checks enforcing `settings.project.architecture` (ARC-01 through ARC-06) |

## References

- `shaktra-reference/severity-taxonomy.md` — P0-P3 definitions and merge gate logic
- `shaktra-reference/quality-dimensions.md` — 13 dimensions (A-M) framework
- `shaktra-reference/quality-principles.md` — 10 core principles
- `shaktra-reference/guard-tokens.md` — tokens emitted during reviews
- `shaktra-stories/story-tiers.md` — tier-based check depth behavior
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall