Explore skills
Showing 25801–25830 of 77079 skills
Check authored skills for required metadata, duplicate names, missing local resources and broken cross-skill links without imposing a fixed skill inventory or agent-tool configuration.
neohaskell/NeoHaskell
Stars: 348Claude CodeCodexBuild and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings. Ingest sources into linked Markdown, answer questions with citations, lint or upgrade a wiki, and preserve useful synthesis across sessions and agents. Also capture verified task experience, consolidate success/failure patterns, and propose, evaluate, apply or roll back evidence-linked skill improvements. Trigger on "add this to my wiki", "what does the wiki say", "learn from this task", "improve this procedure", /wiki:learn or /wiki:evolve. Works on a local folder or a hosted wiki URL (MCP). Use index-first navigation, atomic pages and hybrid search.
praneybehl/llm-wiki-plugin
Stars: 124Claude CodeCodexVerify cited paper identity and decide whether claims in an Artifact are supported by their linked Evidence using a governed source snapshot.
openJiuwen-ai/sciencediscovery
Stars: 229Claude CodeCodexCheck whether numeric claims marked with Evidence aliases in an Artifact agree with the linked Evidence content and context.
openJiuwen-ai/sciencediscovery
Stars: 229Claude CodeCodexPrepare supplied inputs for autonomous Idea Tree research and explain its saved results.
openJiuwen-ai/sciencediscovery
Stars: 229Claude CodeCodexCreate a reviewable reusable Agent Skill draft from a user's explicit natural-language description. Use when the user asks the Agent to create, build, or revise a Skill; do not use merely because a workflow seems reusable.
openJiuwen-ai/sciencediscovery
Stars: 229Claude CodeCodexCode-drawn stills, films, 3D motion graphics, explainers and web animations in 32 styles, with scores, narration and subtitles. Use when asked for an illustration, animation, video or drawing lesson.
alexgreensh/anidoodle
Stars: 1.7kClaude CodeCodexMinimal, pattern-matching code output. Write the least code that satisfies requirements. Match existing project patterns. Use Write/Edit tools only.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexEvidence requirement enforcement ensuring all claims are backed by logs, test results, or exit codes. Zero = success, non-zero = failure. No guessing allowed.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexGit-backed state management for safe rollback. Create and restore checkpoints with tagged commits and metadata tracking.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexCoordinate Crew (persistent) and Polecat (transient) agents using Gas Town's hook-based work distribution and GUPP principle.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexTrack beads as git-backed issues with persistent attribution, supporting Gas Town's bead lifecycle and convoy progress monitoring.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexProcess the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify integration.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexContinuous monitoring using Deacon/Witness patterns for agent health checks, stuck detection, and automated recovery.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexManage agent sessions including initialization, handoffs, revival (seance), and persistent identity for Polecats and Crew agents.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexDecompose goals into MEOWs (Molecular Expressions of Work) - trackable atomic units following Gas Town's bead-based work model.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexUrgent issue classification, root cause analysis, and fast-path routing for production hotfixes
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexCapture, validate, query, and sync architectural patterns and design decisions in the knowledge graph
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexTechnical debt management including branch cleanup, doc verification, TODO scanning, and dependency auditing
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexInteractive PM interview with expertise-adaptive questioning for requirements elicitation
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexConvert requirements into structured technical specifications with architecture decisions
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexBreak technical specifications into small, implementable stories with dependency ordering
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexAutomated test validation, coverage checking, and quality metrics with aggressive defaults
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexFresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fresh reviewer spawning.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexParallel design review by 6 specialist agents (PM, Architect, Designer, Security Design, UX, CTO) with mandatory unanimous approval.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexAdversarial plan review by 3 independent reviewers (Feasibility, Completeness, Scope & Alignment) before presenting to user.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexMonitor PR lifecycle from creation through merge including CI monitoring, review comment handling, thread resolution, and merge readiness verification.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexClarify vague requirements through exploratory questioning and option generation before committing to research or implementation.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexCreate Architecture Decision Records (ADRs) documenting significant technical choices with context, options, consequences, and sequential numbering.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexFinal completion discipline including summary generation, plan document updates, and confirmation that all success criteria from the original plan are satisfied.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodex