plugin-maintenance
claudeMaintenance utilities for Claude Code plugins, including version bumping for modified plugins.
1 command
Agentic engineering skills codifying patterns and best practices including TDD, refactoring, architecture patterns, diagramming, scaffolding, and AI development workflows.
Plugin praxis from marketplace lightfactory in 8thlight/lightfactory. Commands read from the repo's manifest — 9 days ago.
adrGuides writing minimal Architecture Decision Records (ADRs). Use when recording architectural decisions, documenting design choices, capturing technical decisions with context and alternatives, or when user mentions ADR, architecture decision, or decision record.
harnessAssess and strengthen the agentic coding environment surrounding a codebase. Audits instruction files, hooks, type safety, linting, pre-commit, architecture tests, CI gates, and sandbox permissions — then produces a gap analysis with actionable improvements. Use when the user wants to improve their
implementExecute an approved implementation plan using task-graph-driven orchestration with isolated TDD agents (RED/GREEN/VALIDATE gates). Reads a task graph from yaks, beads, or native tasks and dispatches agents phase by phase. Use when the user has an approved plan and wants to start building, execute a
plan-tasksCreate a detailed implementation plan with test specs, phased task breakdown, and Agent Context blocks for agent-driven execution. Consumes a research artifact or works from a feature description directly. Creates a task graph in yaks, beads, or native tasks. Use when the user wants to plan a featur
reflectPost-session skill to reflect on what was built and produce improvement proposals. Reads recent git history, artifacts, and context files to extract learnings for skills, CLAUDE.md, hooks, and plan templates. Use after any substantive session as a post-mortem or retrospective.
researchExplore a codebase and research external patterns before building a non-trivial feature. Spawns parallel subagents for codebase exploration AND web/pattern research, then synthesizes findings into a compact research artifact at .light/sessions/. Use when the user wants to understand existing code, i
tddBoundary-focused TDD workflow enforcing L3/L4 altitude testing, property-based tests, and red-green-refactor phase separation. Use when starting a new module or feature with test-first discipline.
agent-implWrite minimal implementation to make failing tests pass. Use this agent when the implement skill dispatches an implementation task from a yak with agent-type 'agent-impl'. The agent writes implementation ONLY — never modifies test files. Applies a YAGNI simplification pass after tests pass. Reports
agent-no-testExecute non-TDD phase tasks like schema migrations, infrastructure setup, or configuration. Use this agent when the implement skill dispatches a task from a yak with agent-type 'no-test'. The agent executes the task as described and verifies the acceptance gate.
agent-remediateFix implementation after validation finds failures. Use this agent when the implement skill creates a remediation yak with agent-type 'agent-remediate'. The agent fixes implementation code ONLY — never modifies test files. Receives failure output from the validation agent. The orchestrator escalates
agent-testWrite failing tests for a TDD phase. Use this agent when the implement skill dispatches a test-writing task from a yak with agent-type 'agent-test'. The agent writes tests ONLY — never implementation code. It receives a self-contained task context with file paths, test spec, and test command. Report
agent-validateRun the validate task's tests, type-check and lint, and report results without modifying any files. Use this agent when the implement skill dispatches a validation task from a yak with agent-type 'agent-validate'. The agent runs tests, type-checks, and linting — all must exit 0 for the VALIDATE gate
reuse-simplify-reviewerReview a diff for logic the codebase already has and for code it doesn't need, including a check against research's reuse candidates. Use this agent when implement's slice review checks a phase's diff after its VALIDATE gate, or when a code review needs a reuse/simplify pass. Takes a diff (git range
technical-project-managerPlan a change's rollout phases and risk mitigations, then check the code against them. Use this agent with mode 'plan' when plan-tasks needs a plan's Rollout Phases and Risks & Mitigations sections, with mode 'slice-check' when implement checks one phase's diff against the mitigations tagged to that
Maintenance utilities for Claude Code plugins, including version bumping for modified plugins.
1 command
14 Karpathy-inspired working methods + 1 methodology router, distilled from his 2023-2026 public X posts and Gists into executable agent skills: agentic-engineering, vibe-to-agentic, autoresearch, llm-simulator, llm-wiki, minimalism, supply-chain-hygiene, understanding-first, idea-files, output-evolution, education-first, system-prompt-learning, practice-environments, meta-reflection. Every skill cites its original source. Unofficial, not endorsed by Andrej Karpathy.
15 skills
You already have the agent. This is everything around it. great_cto runs Claude Code as a pipeline of 73 specialist agents — an independent model checks each stage before the next builds on it, spending caps refuse rather than warn, and three decisions stay yours: what gets built, how, and whether it ships.
37 skills · 21 commands · 73 agents · 1 MCP server · hooks
Twenty-two slash commands wrapping Google Antigravity CLI (agy): /agy:deep-research (multi-agent deep research — builds an evidence matrix + plan gate, then agy browses each angle while Claude orchestrates adaptive rounds L≤2/H≤4 + an agy red-team pass + synthesis with an applied recommendation; complements /agy:research, docs/agy/research/), /agy:transcribe (audio/video to a faithful transcript + summary; YouTube/remote URLs too), /agy:media (multimodal Q&A over an audio/video/image — time-referenced answers), /agy:notebook-ask (Q&A over a notebook corpus from the per-doc summaries, with citations), /agy:model (set the active agy model by writing ~/.gemini/antigravity-cli/settings.json — the reliable lever; --model is unreliable), /agy:notebook (local NotebookLM — sweep a folder of documents into objective-driven per-doc summaries + a relevance INDEX.md + a cited RESUMEN_MAESTRO.md, hybrid text/vision OCR, docs/agy/notebook/), /agy:report (branded HTML from markdown via 5 TRAID Design System templates, docs/agy/reports/), /agy:ask (one-shot quick prompt), /agy:review (git-diff code review), /agy:research (deep web research with citations, docs/agy/research/), /agy:rescue (code/diagnosis task delegation), /agy:record (browser walkthrough recording — .webm + optional MP4 via ffmpeg), /agy:scrape (structured data extraction from URL — markdown or JSON), /agy:doc-to-md (PDF/docx/image to clean Markdown via multimodal Gemini), /agy:design-review (UX/visual audit with desktop+mobile screenshots and 10-dimension scoring), /agy:setup (health check). /agy:report supports --images native|external|none for reliable infographics (pre-generate with Nano Banana 2 for brand quality). Includes full issue-#76 handling (write_file workaround + transcript.jsonl recovery + headless auth-timeout detection + stdin-hang fix) and Windows rename-bug (#217) mitigation. Thin Bash forwarder, no runtime dependencies.
2 skills · 22 commands · 1 agent
GABBE core: 44 agent skills for the everyday engineering loop — spec, plan, TDD, review, research, security, memory and audit, with Brain and Loki mode. Add the gabbe-* topic plugins from the same marketplace for the rest of the 214.
44 skills
Rolling-wave engineering workflow skills for shaping, preparing, implementing, delivering, finalizing, and debugging one project slice at a time.
13 skills · 14 agents
Engineering discipline for AI agent systems — four always-on principles, test-driven development, verification-before-completion, system-architecture playbooks, a scope-disciplined product manager, docs/-native project management, and Claude Code → GitHub Copilot agent conversion.
7 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.