taches-toolkit

Plugin taches-toolkit from marketplace lars-cc-skills in lars-hh/lars-cc-skills. Commands read from the repo's manifest — 19 days ago.

Skills (7)

• create-agent-skills

  Expert guidance for creating, writing, building, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.

• create-meta-prompts

  Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce outputs for other prompts to consume, or when running multi-stage workflows (research -> plan -> implement).

• create-plans

  Create hierarchical project plans optimized for solo agentic development. Use when planning projects, phases, or tasks that Claude will execute. Produces Claude-executable plans with verification criteria, not enterprise documentation. Handles briefs, roadmaps, phase plans, and context handoffs.

• create-slash-commands

  Expert guidance for creating Claude Code slash commands. Use when working with slash commands, creating custom commands, understanding command structure, or learning YAML configuration.

• create-subagents

  Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.

• debug-like-expert

  Deep analysis debugging mode for complex issues. Activates methodical investigation protocol with evidence gathering, hypothesis testing, and rigorous verification. Use when standard troubleshooting fails or when issues require systematic root cause analysis.

• setup-ralph

  Set up and configure Geoffrey Huntley's original Ralph Wiggum autonomous coding loop in any directory with proper structure, prompts, and backpressure.

Slash commands (28)

• /taches-toolkit:ask-me-questions

  Gather requirements through adaptive questioning before executing any task

• /taches-toolkit:audit-skill

  Audit skill for YAML compliance, pure XML structure, progressive disclosure, and best practices

• /taches-toolkit:audit-slash-command

  Audit slash command file for YAML, arguments, dynamic context, tool restrictions, and content quality

• /taches-toolkit:audit-subagent

  Audit subagent configuration for role definition, prompt quality, tool selection, XML structure compliance, and effectiveness

• /taches-toolkit:consider:10-10-10

  Evaluate decisions across three time horizons

• /taches-toolkit:consider:5-whys

  Drill to root cause by asking why repeatedly

• /taches-toolkit:consider:eisenhower-matrix

  Apply Eisenhower matrix (urgent/important) to prioritize tasks or decisions

• /taches-toolkit:consider:first-principles

  Break down to fundamentals and rebuild from base truths

• /taches-toolkit:consider:inversion

  Solve problems backwards - what would guarantee failure?

• /taches-toolkit:consider:occams-razor

  Find simplest explanation that fits all the facts

• /taches-toolkit:consider:one-thing

  Identify the single highest-leverage action

• /taches-toolkit:consider:opportunity-cost

  Analyze what you give up by choosing this option

• /taches-toolkit:consider:pareto

  Apply Pareto's principle (80/20 rule) to analyze arguments or current discussion

• /taches-toolkit:consider:second-order

  Think through consequences of consequences

• /taches-toolkit:consider:swot

  Map strengths, weaknesses, opportunities, and threats

• /taches-toolkit:consider:via-negativa

  Improve by removing rather than adding

• /taches-toolkit:create-agent-skill

  Create or edit Claude Code skills with expert guidance on structure and best practices

• /taches-toolkit:create-meta-prompt

  Create optimized prompts for Claude-to-Claude pipelines (research -> plan -> implement)

• /taches-toolkit:create-plan

  Create hierarchical project plans for solo agentic development (briefs, roadmaps, phase plans)

• /taches-toolkit:create-prompt

  Create a new prompt that another Claude can execute

• /taches-toolkit:create-slash-command

  Create a new slash command following best practices and patterns

• /taches-toolkit:create-subagent

  Create specialized Claude Code subagents with expert guidance

• /taches-toolkit:debug

  Apply expert debugging methodology to investigate a specific issue

• /taches-toolkit:heal-skill

  Heal skill documentation by applying corrections discovered during execution with approval workflow

• /taches-toolkit:run-plan

  Execute a PLAN.md file directly without loading planning skill context

• /taches-toolkit:run-prompt

  Delegate one or more prompts to fresh sub-task contexts with parallel or sequential execution

• /taches-toolkit:setup-ralph

  Set up Geoffrey Huntley's original Ralph Wiggum autonomous coding loop

• /taches-toolkit:whats-next

  Analyze the current conversation and create a handoff document for continuing this work in a fresh context

Subagents (3)

• skill-auditor

  Expert skill auditor for Claude Code Skills. Use when auditing, reviewing, or evaluating SKILL.md files for best practices compliance. MUST BE USED when user asks to audit a skill.

• slash-command-auditor

  Expert slash command auditor for Claude Code slash commands. Use when auditing, reviewing, or evaluating slash command .md files for best practices compliance. MUST BE USED when user asks to audit a slash command.

• subagent-auditor

  Expert subagent auditor for Claude Code subagents. Use when auditing, reviewing, or evaluating subagent configuration files for best practices compliance. MUST BE USED when user asks to audit a subagent.

Similar plugins