elb-pr

Use when determining project tone, voice, and marketing angle after deep-dive and crystal-ball phases. Conducts brainstorming session with Gemini.

Use when analysing future opportunities after deep-dive phase. Identifies performance improvements, technical debt, security hardening, and feature gaps. Outputs roadmap candidates table.

Use when starting the README pipeline to extract technical facts from codebase. Identifies project type, tech stack, dependencies, entry points, CI configuration. Outputs Reality Report.

Use when writing the final README after all phases complete. Synthesises outputs from deep-dive, crystal-ball, brain-jam, and think-tank. Applies Anti-Slop style guide.

Use when researching documentation patterns after brain-jam phase. Analyses exemplar READMEs from similar high-star repositories, scores against rubric, extracts patterns.

Use when creating or updating a README. It enforces the 5-step 'Anti-Slop' pipeline and triggers the correct sub-skill for the current phase.

Use when running claudikins-kernel:execute, decomposing plans into tasks, setting up two-stage review, deciding batch sizes, or handling stuck agents — enforces isolation, verification, and human checkpoints; prevents runaway parallelization and context death

Use when running claudikins-kernel:outline, brainstorming implementation approaches, gathering requirements iteratively, structuring complex technical plans, or facing analysis paralysis with too many options — provides iterative human-in-the-loop planning with explicit checkpoints and trade-off presentation

Use when running claudikins-kernel:ship, preparing PRs, writing changelogs, deciding merge strategy, or handling CI failures — enforces GRFP-style iterative approval, code integrity validation, and human-gated merges

Use when running claudikins-kernel:verify, checking implementation quality, deciding pass/fail verdicts, or enforcing cross-command gates — requires actual evidence of code working, not just passing tests

Use when a task needs capabilities BEYOND basic tools (Read/Grep/Glob/Bash) - semantic search, AI analysis, research, image generation, etc.

Use this skill when users ask "add MCP server", "remove MCP", "configure tool executor", "add new tool", "environment variables for tool executor", "regenerate registry", or need to modify which MCP servers are available in the sandbox.

Use this skill when users say "tool executor not working", "diagnose tool executor", "check MCP health", "run tool executor tests", "debug search_tools", "execute_code failing", or need to troubleshoot issues with the Tool Executor.

Use this skill when users ask "how does tool executor work", "how to use execute_code", "workspace API", "MCP client examples", "search_tools examples", "context-efficient patterns", or need guidance writing code for the Tool Executor sandbox.

Use when the user wants to customize Claudikins Automatic Context Manager behavior, configure trigger threshold, snooze duration, summary length, or runs '/acm:config'. Interactively asks questions and saves preferences to config file.

Use when resuming work from a previous session that reached context threshold, or when a handoff summary exists. Reads handoff state and markdown to restore context, todos, and continue seamlessly.

Use when debugging complex issues that require methodical analysis, when you are truly stuck, or when facing bugs that resist quick fixes. Systematic 8-phase methodology.