Menu
Enforces test-driven development with 80%+ coverage — unit, integration, and E2E. Use when writing new features, fixing bugs, or refactoring.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when designing memory or persistent context for an agent — deciding what to persist vs. recompute, how to retrieve only what's relevant, and how to summarize/compact history to fit the context window. Use when an agent forgets, bloats its context, or repeats work.
Interactive installer for Rosetta. Guides users through selecting and installing skills and language-specific rules at user-level or project-level, verifies paths, and optionally optimizes installed files.
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills, commands, and agents.
Use when building or reviewing an evaluation for an LLM feature — assembling a representative test set, choosing pass criteria (exact match, programmatic checks, rubric, or LLM-as-judge), and catching regressions. Use when asking "how do I know this prompt or model change is better?"
Use when writing or reviewing a prompt for an LLM — making it specific, structured, and testable (clear task, role/context, examples, an explicit output contract, decomposition, room to reason) and avoiding the anti-patterns that make prompts brittle. Provider-agnostic.
Pattern for progressively refining context retrieval to solve the subagent context problem.
| name | tdd-workflow |
| description | Enforces test-driven development with 80%+ coverage — unit, integration, and E2E. Use when writing new features, fixing bugs, or refactoring. |
Write tests first. Always.
Never skip the failing step. A test that was never red doesn't prove anything.
Unit — individual functions and modules in isolation. Mock external dependencies at the boundary.
Integration — where components connect: API handlers, database operations, service interactions. Test the wiring, not just the units.
E2E — critical user-facing flows only. Slow and expensive; reserve for paths where breakage would be severe.
80% line and branch coverage minimum. Coverage is a floor, not a goal — a well-tested critical path matters more than padding an untested utility to hit a number.
Use the project's existing test framework and coverage tooling. Match the conventions already in the codebase.
For every non-trivial function: the happy path, null/empty/boundary inputs, and error paths. Test observable behavior, not implementation details — tests that assert on internal state break during refactoring and provide no safety guarantee.
