TÂCHES Claude Code Resources 🧩 Skill Open source
Claude Code skills and commands for planning, handoffs and building your own extensions
- GitHub stars
- 2.0k
- Stars this week
- +-1
- Forks
- 409
- Licence
- MIT
- Last push
- 2026-04-01
- Maintainer
- glittercowboy
claude plugin marketplace add glittercowboy/taches-cc-resourcesThird-party agent skills run with your permissions. Read the source before installing, and prefer pinned versions.
Works with
About TÂCHES Claude Code Resources
What it does
TÂCHES Claude Code Resources is a personal but reusable pack of slash commands, skills and subagents for Claude Code, packaged as a plugin. Its focus is on meta-work: generating better prompts, planning projects in stages, handing context over between sessions, and building or auditing your own Claude Code extensions.
What is inside
The skills cover hierarchical project planning (brief, roadmap, then executable plan files with automatic handoff when context runs low), meta-prompt pipelines that chain research, planning and implementation, and generators for new skills, slash commands, subagents, hooks and MCP servers in Python or TypeScript. A debugging skill enforces evidence gathering and hypothesis testing, and another sets up the Ralph autonomous coding loop. Commands include prompt creation and execution in a fresh subagent context, todo capture and resume, a what's-next handoff document, a self-healing command that updates a skill after a failed run, and a set of thinking-model prompts such as first principles, inversion and the 80/20 rule. Three auditor subagents review skills, commands and subagent definitions against best practice.
Works with
Claude Code. A community port for OpenCode is linked from the README but maintained separately.
How to install
claude plugin marketplace add glittercowboy/taches-cc-resources
claude plugin install taches-cc-resources
Manual installation by copying the commands and skills folders into ~/.claude/ is also documented.
Maintenance and safety
MIT licensed and made of readable Markdown prompts rather than executable code, so it is easy to inspect. The last update was in spring 2026 and the pack reflects one author's workflow, so some commands, such as the thinking-model set, are general productivity prompts rather than coding tools. The Ralph loop setup runs the agent autonomously, which deserves the usual care around permissions.
Who should use it
Claude Code users who want structured planning and handoff workflows, or who build their own skills, commands and subagents and want generators and auditors to speed that up.
Pros
- Generators and auditors for skills, commands, subagents, hooks and MCP servers
- Structured planning with automatic context handoff
Cons
- One author's workflow; some commands are general thinking prompts
- No updates since April 2026
Similar agent skills
All development workflow skills →Superpowers 🧩 SkillFree
A skills library that makes coding agents plan, test-first and debug systematically
Matt Pocock's Skills 🧩 SkillOpen source
Small, composable engineering skills: grilling, TDD, specs, tickets and architecture review
Agent Skills (Addy Osmani) 🧩 SkillOpen source
25 lifecycle skills and commands that make agents spec, test, review and ship with discipline
Ponytail 🧩 SkillOpen source
Makes your coding agent write the minimum code a task needs, without cutting safety
Understand Anything 🧩 SkillOpen source
Turns a codebase into an interactive knowledge graph with tours, search and Q&A
Archify 🧩 SkillOpen source
Validated, interactive architecture, sequence and data-flow diagrams compiled from typed JSON