Internal Auto-Harness generator skill for QA fix cycles. Use only inside the Generator subagent when it is addressing named defects from QA or retest.
Scanned 5/27/2026
Install to Claude Code
npx -y skills add redker56/auto-harness --skill generator-apply-fixes --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Generator Apply Fixes?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/redker56-generator-apply-fixes)More formats (shields.io, HTML) on the badges page.
---
name: generator-apply-fixes
description: Internal Auto-Harness generator skill for QA fix cycles. Use only inside the Generator subagent when it is addressing named defects from QA or retest.
user-invocable: false
---
# Generator Apply Fixes
This skill governs Generator **fix mode**.
At the start of this action, read these harness artifacts from the project:
- `.harness/status.md`
- `.harness/intake.md`
- `.harness/spec.md`
- `.harness/design-direction.md` when the named defects touch UX, layout, or interaction rules.
- `.harness/contracts/sprint-XX-contract.md`
- `.harness/contracts/sprint-XX-review.md` when it exists for the current sprint.
- `.harness/runtime.md`
- `.harness/qa/sprint-XX-qa-report.md`
- `.harness/qa/sprint-XX-retest.md` when the current fix cycle follows a failed retest.
- `.harness/qa/sprint-XX-fix-log.md` when revising the current sprint fix log.
Then inspect the current project implementation relevant to this action:
- Read the source files, routes, components, services, tests, and config touched by the named defects and the necessary regression surface around them.
- Use code and runtime evidence to scope fixes precisely instead of broad cleanup.
Then read these skill references:
- `references/protocols/file-ownership.md`
- `references/templates/fix-log.md`
- `references/templates/runtime-template.md`
Follow these rules:
- Fix only defects named in the current QA or retest context unless a tightly related adjustment is required.
- Treat the current sprint review, when present, as implementation guidance and cautions that still apply during the fix cycle.
- Update the runtime contract when startup, access, or healthcheck behavior changed.
- Record the actual fixes in the sprint fix log.
- Keep the fix log tied to named defects, changed files, and any verification notes that matter for retest.
- Do not rewrite QA or retest artifacts yourself.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.