Skills for Real Engineers. Straight from my .agents directory.
test-driven-development
Agent skill fromGanyuanRan/Aegis
Use when the user explicitly requests strict or test-first TDD, or when the current conversation already contains an explicit `TDD Route: strict` decision from another Aegis workflow.
How to install test-driven-development
npx skills add GanyuanRan/Aegis# or add only this skill to Claude Code: copy the folder
skills/test-driven-development/
# into
~/.claude/skills/test-driven-development/ (all projects)
.claude/skills/test-driven-development/ (one project)
1# Execute23→ False-positive entry on a native-direct-skill host? → **Exit immediately unless the user explicitly asked for TDD or the conversation already contains `TDD Route: strict`.**4 In `off` mode, do not start RED / GREEN / REFACTOR from generic bugfix, contract, shared-module, or risky-code wording alone.5 Hand control back to `using-aegis`, `systematic-debugging`, `writing-plans`, or the fast path with verification.6→ Implementing a feature or bugfix under TDD Route `strict`? → **No production code without a failing test first.**7 Gate: medium/high complexity? → route to brainstorming or writing-plans first.8 Mode: default `off` disables automatic TDD, not completion verification; `auto` chooses strict/light/skipped by risk.9 Change Necessity: before strict RED/GREEN enters production edits, confirm the slice really needs a code change.10 Cycle: RED (write test → watch it fail) → GREEN (minimal code → watch it pass) → REFACTOR (clean up → keep green)11 Regression: shared module → related tests. contract change → producer + consumer. core logic → old + new tests.12 Ripple signal hit → cover producer+consumer or real user path before claiming green.13 GREEN proves the currently expressed behavior slice only.14 GREEN does not by itself prove parent-task acceptance, business-value completion, or final completion.15…
Excerpt shown under the repository's MIT license.
More skills in Aegis
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
