Agent skill
implement
Implement an approved plan. Write code, tests, and docs following the sprint checklist in NEXT-TASKS.md.
Install this agent skill to your Project
npx add-skill https://github.com/cortex-tms/cortex-tms/tree/main/.claude/skills/implement
SKILL.md
Implement
You are implementing an approved plan for Cortex TMS.
Rules
- Read NEXT-TASKS.md first — find the active sprint checklist. If there is no approved plan, STOP and tell the user to run /plan first.
- Follow the checklist — implement items in order. Check them off as you complete each one.
- Research before claiming anything — if you need to understand how something works, read the code. Do not guess. Do not speculate.
- Stand behind your decisions — if your implementation is sound, say so and explain why. Do not backtrack without a concrete technical reason backed by evidence from the codebase.
- If the user asks a question — STOP implementation immediately. Answer the question clearly and completely. Resume only when the user says to continue.
- Follow existing patterns — read similar commands/tests/files in the codebase and match their style.
- Show changes before committing — run git diff and present it. Wait for approval before any git command.
Git Protocol
- Show every git command before running it
- Wait for explicit user approval
- Use conventional commit format
- Include Co-Authored-By
Arguments
$ARGUMENTS
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
new-command
Scaffold a new CLI command for Cortex TMS following the existing codebase patterns.
release
Guide through the Cortex TMS release process — version bump, changelog, sync, tag, publish. Every step requires user approval.
sync
Synchronize task files and source-of-truth documents. Update NEXT-TASKS.md, FUTURE-ENHANCEMENTS.md, README, and CHANGELOG to reflect current project state.
plan
Research the codebase and create an implementation plan following Propose/Justify/Recommend. Use this before any feature, fix, or refactor.
validate
Run the full quality gate — tests, lint, build, and cortex-tms validate --strict.
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
Didn't find tool you were looking for?