Agent skill

sync

Synchronize task files and source-of-truth documents. Update NEXT-TASKS.md, FUTURE-ENHANCEMENTS.md, README, and CHANGELOG to reflect current project state.

View SKILL.md on GitHub Repository
Stars 173
Forks 7

Install this agent skill to your Project

npx add-skill https://github.com/cortex-tms/cortex-tms/tree/main/.claude/skills/sync

SKILL.md

Sync

Synchronize Cortex TMS task files and documentation.

Steps

  1. Read current state — check NEXT-TASKS.md, FUTURE-ENHANCEMENTS.md, README.md, CHANGELOG.md, package.json
  2. Update NEXT-TASKS.md — mark completed items, remove stale tasks, add new items if discussed
  3. Update FUTURE-ENHANCEMENTS.md — sync status markers (Planned/In Progress/Complete)
  4. Truth-sync source-of-truth files — ensure README, CHANGELOG reflect what actually shipped
  5. Archive if needed — move completed sprint content to docs/archive/
  6. Run validation — node bin/cortex-tms.js validate --strict to confirm health
  7. Show changes — run git diff and present for approval. Do not commit without approval.

Rules

  • Do not modify src/, bin/, templates/, or any code files
  • Follow the Propose/Justify/Recommend framework for any non-obvious changes
  • If unsure whether something should be archived or updated, ask the user

Arguments

$ARGUMENTS

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

cortex-tms/cortex-tms

new-command

Scaffold a new CLI command for Cortex TMS following the existing codebase patterns.

173 7
Explore
cortex-tms/cortex-tms

release

Guide through the Cortex TMS release process — version bump, changelog, sync, tag, publish. Every step requires user approval.

173 7
Explore
cortex-tms/cortex-tms

implement

Implement an approved plan. Write code, tests, and docs following the sprint checklist in NEXT-TASKS.md.

173 7
Explore
cortex-tms/cortex-tms

plan

Research the codebase and create an implementation plan following Propose/Justify/Recommend. Use this before any feature, fix, or refactor.

173 7
Explore
cortex-tms/cortex-tms

validate

Run the full quality gate — tests, lint, build, and cortex-tms validate --strict.

173 7
Explore
davila7/claude-code-templates

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.

23,776 2,298
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results