| Skill | Added | Review |
|---|---|---|
Architecture-Deepening .claude/skills/architecture-deepening/SKILL.md Guide the agent through a structured 4-phase process (Explore, Synthesize, Validate, and Issue/Reject) to systematically deepen codebase architecture. | — | |
autoreview .agents/skills/autoreview/SKILL.md Auto Review closeout. Runs as parallel review subagents inside the current coding agent (Claude Code or Cursor) — no external reviewer CLI. | 57 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 5b08822 | |
harden-environment .agents/skills/harden-environment/SKILL.md Use when the same agent mistake, review finding, mutation survivor, or CI failure appears twice, or when spot-checking recently merged PRs, to turn the pattern into a permanent constraint instead of another prose rule. | 68 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 5b08822 | |
mine-agent-transcripts .agents/skills/mine-agent-transcripts/SKILL.md Use when the user asks what keeps going wrong, after a session where the agent needed repeated correction, or before hardening the environment, to mine past OpenCode sessions in this repository for recurring corrections. | 72 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 5b08822 | |
qa .factory/skills/qa/SKILL.md Run functional QA for Zipper. Maps the git diff to CLI flows, tests the built application through Droid Control, and writes a concise QA report. Use when testing PRs, releases, or local changes. | 71 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 5b08822 | |
qa-cli .factory/skills/qa-cli/SKILL.md QA tests for the Zipper CLI. Exercises Standard, Loadfile-Only, Chaos Engine, Production Set, Source-Driven Generation, Load File Formats, Archive Test Fixtures, Production Manifest comparison, version output, and CLI boundaries. | 62 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 5b08822 | |
Root-Cause-Tracing .claude/skills/root-cause-tracing/SKILL.md Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior | — | |
Systematic-Debugging .claude/skills/systematic-debugging/SKILL.md Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions | — | |
Test-Driven Development (TDD) .claude/skills/test-driven-development/SKILL.md Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first | — | |
Testing-Anti-Patterns .claude/skills/testing-anti-patterns/SKILL.md Use when writing or changing tests, adding mocks, or tempted to add test-only methods to production code - prevents testing mock behavior, production pollution with test-only methods, and mocking without understanding dependencies | — | |
verify-zipper-change .agents/skills/verify-zipper-change/SKILL.md Use when about to claim a Zipper change is done, fixed, or passing, especially for CLI behavior, Load File formats, Production Sets, or output bytes, to gather real-artifact evidence before the claim. | 68 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 5b08822 |