Spawns three parallel subagents to produce diverse solutions, then scores them and returns the best with trade-offs.
Turns feature requests into detailed, sequential implementation plans with file-level tasks and dependencies.
A skill that guides Claude to copy, move, and extract functions or classes between files with line-level precision.
Proven architecture patterns for robot software — behavior trees, FSMs, HALs, safety systems — with working code examples.
A skill for designing and reviewing robot software modules using SOLID, real-time rate separation, and fail-safe defaults.
A persona framework that has Claude read SOUL.md, STYLE.md and curated examples so it writes and argues exactly like a specific person.
A repo-specific playbook that guides Claude through the correct PR path, validation commands, and review gate for JSONbored/awesome-claude.
Turns post concepts or a content calendar into on-brand, ready-to-post captions with hooks, CTAs and hashtags across Instagram, LinkedIn, Facebook, TikTok and X.
Takes approved posts from outputs/, generates infographic visuals for flagged posts, and schedules everything across platforms through Blotato MCP with a mandatory approval gate.
Researches a client's website and Instagram, sends a pre-filled intake doc, and synthesises everything into context/brand-style.md as the single source of truth for social work.
A meta skill that interviews you and writes a complete, standards-compliant Claude Code SKILL.md.
Generates consistent, standards-compliant Claude Code sub-agent files from a short role description.
Describe what you want to build and this skill scaffolds an OpenSpec change plus proposal, design and tasks documents in one pass.
Generates INVENTORY-SKILLS-JAVA.md by treating the Plinth repo's skills.xml as the single source of truth for every Java system prompt skill.
Creates an OpenSpec change and generates proposal, design and tasks artifacts in a single step.
A research-grade playbook for diagnosing dataset bias and imbalance, building stratified splits, planning expansion, and running an ethics review.
A 7-step methodology skill for designing ablations, baselines, experiment matrices, and analysis plans.
Clears pre-existing repo-wide lint warnings, type errors, and suppressions in safe waves — one rule at a time, tests green after each.
One-time setup that detects your project's stack, interviews you for a handful of preferences, and writes the shared JSON config every other absolute-* command reads.
A defensive security-audit skill that scans your whole repo for dependency CVEs and risky code patterns, triages them by severity and reachability, then fixes them without suppressing alerts.