nanlabs-agents
claudecodexOptional full set of NaNLABS agent / subagent personas (reviewers, architect, planner, e2e, …)
36 agents
Recommended install: setup/onboarding, orchestrator, companion, handshake, Pyright report-only typing, PR fallback, knowledge sync, and code-reviewer agent
Plugin nanlabs-core from marketplace nanlabs-agent-toolkit in nanlabs/agent-toolkit. Commands read from the repo's manifest — 1 month ago.
nanlabs-assistantHOW — Default NaNLABS orchestrator. Use for repo discovery, conflict resolution, and routing to workflow/tool skills. Do NOT use for ticket CLI steps, forge automation, or deep procedure execution. author: nanlabs version: "2.2
nanlabs-dev-companionWHAT — NaNLABS Dev Companion (general): layered companion for client delivery; modes, gates, delegation to nanlabs-assistant and nanlabs-workflow-generic-project; no CLI matrices.
nanlabs-output-handshakeWHAT — Default gate for any deliverable: confirm where the final artifact will live and that a human will review, before writing PRDs, TRDs, ADRs, or PR bodies. Storage (repo, wiki, ticket) differs by engagement; never assume a single location.
nanlabs-pr-fallbackWHAT, Structure the pull-request body with the NaNLABS default in references/pr-body-default.md when the repo has no GitHub PR template. Pair with nanlabs-output-handshake and github-cli-workflow. Does not open the PR; HOW stays in the forge skill.
nanlabs-pyrightinationHOW — Run Pyright in report-only mode for Python projects, summarize the diagnostics by severity and file, and recommend the next fix order without auto-applying code changes. author: nanlabs version: "0.1.0" status: public
nanlabs-setupHOW — First-run setup for the NaNLABS agent toolkit. Inspect the local environment against bundled contracts, report missing baseline tools, ask approval before installs, and print a change report. Never print or store secrets. author: nanlabs version: "0.2.0" status: bundled-in-nanlabs-core
nanlabs-workspace-knowledge-syncSyncs knowledge to the internal-ai-workspace knowledge base. Use when the assistant discovers new patterns, learns user preferences, or identifies information worth preserving for future sessions. Can be triggered manually or by orchestrators.
/nanlabs-core:core-helpSummarize nanlabs-core contents and when to use each skill
/nanlabs-core:setupInspect the local environment against NaNLABS contracts and guide first-run setup
nanlabs-code-reviewerExpert code review for quality, security, and maintainability. Use immediately after significant code changes.
nanlabs-code-reviewerExpert code review for quality, security, and maintainability. Use immediately after significant code changes.
Optional full set of NaNLABS agent / subagent personas (reviewers, architect, planner, e2e, …)
36 agents
PRD, TRD, ADR, work items, assessments, and delivery process
19 skills
ClickUp, Slack, Linear, Shortcut, Notion, and Atlassian (Jira/Confluence) MCP plus CLI skills
4 skills · 6 MCP servers
Figma MCP and UI/UX intelligence (not a full designer workflow)
6 skills · 1 MCP server
GitHub and GitLab CLI automation plus official GitHub and GitLab MCP
4 skills · 2 MCP servers
Workstation triage, presentations ops, skill contribution, and HOL Guard local runtime safety
4 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
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.