cli-for-agents
>-
docs
>-
gitnexus-cli
Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: \"Index this repo\", \"Reanalyze the codebase\", \"Generate a wiki\"
gitnexus-debugging
Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: \"Why is X failing?\", \"Where does this error come from?\", \"Trace this bug\"
gitnexus-exploring
Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: \"How does X work?\", \"What calls this function?\", \"Show me the auth flow\"
gitnexus-guide
Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: \"What GitNexus tools are available?\", \"How do I use GitNexus?\"
gitnexus-impact-analysis
Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: \"Is it safe to change X?\", \"What depends on this?\", \"What will break?\"
gitnexus-refactoring
Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: \"Rename this function\", \"Extract this into a module\", \"Refactor this class\", \"Move this to a separate file\"
mcp-for-agents
>-
prompt-leverage
Strengthen a raw user prompt into an execution-ready instruction set for Amp, Claude Code, Codex, or another AI agent. Use when the user wants to improve an existing prompt, build a reusable prompting framework, wrap the current request with better structure, add clearer tool rules, or create a hook that upgrades prompts before execution.
ask-maestro
Router for choosing the next Maestro skill or lifecycle recipe.
maestro-audit
Audit a project using Maestro read-only: use for code review, architecture review, deepening opportunities, backlog proposals, harness-improvement findings, or repo-wide improvement audits without fixes.
maestro-card
Card work in a project using Maestro after design approval: use for implement, fix, verify, QA, close, release, continue, or unattended prompts like use loop, keep looping, work while away/asleep.
maestro-design
Design in a project using Maestro before implementation: use for brainstorm, plan, PRD synthesis, grilling/stress-test, domain model, deepening candidate, wording, workflow, skill/harness, card/task/feature, architecture, UX, or agent-process decisions.
maestro-research
Pre-design research for Maestro cards: creates or validates a same-card research.md receipt, maps context, stakeholders, hosting, unknowns, and the first design fork. Use before maestro-design when the user brings a new idea, zero-context feature, external/pasted plan, unfamiliar domain, stakeholder-heavy request, hosting-unclear work, or when research is missing, stale, skipped-risky, or needed for READY_FOR_DESIGN.
maestro-setup
Setup Maestro in a project using or adopting Maestro: use for init/install/sync/doctor, global skills, hooks, harness setup, or agent integration diagnosis/repair.
maestro-witness
Witness feature close: use after Maestro feature proof and QA pass, before feature close, to write current witness.md/advisor.md receipts, auto-invoke an independent advisor when allowed, apply risk-tier and human-demo policy, and emit Gate: APPROVED.
maestro-bundle
Route work into the right maestro tier and drive the SPEC/NOTES/VERIFY bundle lifecycle - open, resume, close, recall.
maestro-coach
Decision support and grounded teaching for the human. Invoke when the user signals a message did not land ("wait, what?", "I don't understand", "explain it like I'm five", "which is better?", "I'm not sure") about a question or fork they have been asked, or when they hand over a locked decision, a lesson, or a bundle and want to learn the concept behind it. Also triggers on Vietnamese phrasings such as giải thích chi tiết, giải thích rõ hơn, rõ hơn, tôi không hiểu, cái nào tốt hơn.
maestro-council
Lead-only council for a hard-to-reverse fork - a neutral brief, sealed independent seats, one premise verifier on unanimity, bounded verifiers, one cross-examination round, a draft-verdict audit, and one binding verdict recorded as a decision with its dissent. Never inside a seat.
maestro-design
Resolve material unknowns blocking the next authorized slice, using research, grilling, prototypes, models, or wayfinding. Record durable decisions and apply the shared workflow tier rule.
maestro-diagnose
Diagnosis-only investigation of a failure with unknown cause - reproduce, localize, reduce, deliver root cause with evidence. Read-only; an explicit fix request routes by target and tier instead, never here. Also triggers on Vietnamese phrasings such as root cause là ở đâu, nguyên nhân là gì, tại sao nó không.
maestro-explore
Answer an evidence question without touching production code - research external facts against primary sources, build or iterate a disposable prototype (its own bugfixes included), or baseline current repository behavior before deciding or implementing. Use when the question is answerable by reading, building, or measuring with no user decision required; unsettled decisions belong to maestro-design. Prototypes are throwaway. Also triggers on Vietnamese phrasings such as làm 1 vòng research xem, research xem.
maestro-graph
Drive a pre-known multi-agent path as a maestro graph - run it by name or from a file you just wrote, pull each agent node with graph next, spawn it as a sub-agent under its maestro-<profile> definition, hand the result back with graph result, repeat until the verdict. A sub-agent node is read-only scouting; a node that writes files or is accepted is opened as a pane instead. Author a new graph from the reference when no preset fits.
maestro-improve
Turn filed lessons into the smallest doctrine edit. Use when a Lead assigns improvement work for one target: group pending lessons, make one evidence-linked commit per target, return it for independent challenge, and process each accepted or rejected lesson without deleting history.
maestro-questionnaire
Turn a decision the user cannot fully answer into a Markdown questionnaire for the one person who can - filled in async, or together over a meeting. Also triggers on Vietnamese phrasings such as phỏng vấn đi, phỏng vấn tôi, interview tôi.
maestro-verify
Verify and close - cross-check coverage, run the VERIFY table, deliver the verdict, harvest durable lessons into decisions, close the bundle, and never claim remote state from local evidence.
maestro-work
Implement or fix one authorized unit with minimal edits and sufficient evidence. Reuse existing checks and add tests only for concrete uncovered behavior or risk.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
maestro-bundle
Route work into the right maestro tier and drive the SPEC/NOTES/VERIFY bundle lifecycle - open, resume, close, recall.
maestro-coach
Decision support and grounded teaching for the human. Invoke when the user signals a message did not land ("wait, what?", "I don't understand", "explain it like I'm five", "which is better?", "I'm not sure") about a question or fork they have been asked, or when they hand over a locked decision, a lesson, or a bundle and want to learn the concept behind it.
maestro-council
Lead-only council for a hard-to-reverse fork - a neutral brief, sealed independent seats, one premise verifier on unanimity, bounded verifiers, one cross-examination round, a draft-verdict audit, and one binding verdict recorded as a decision with its dissent. Never inside a seat.
maestro-design
Settle unknowns and lock decisions before implementation - pick the mode per unknown (grill, research, prototype, model, wayfind), recall past bundles, walk one fork at a time, record every settled choice with a rationale, and open the bundle only when a Full trigger holds.
maestro-diagnose
Diagnosis-only investigation of a failure with unknown cause - reproduce, localize, reduce, deliver root cause with evidence. Read-only; an explicit fix request routes by target and tier instead, never here.
maestro-explore
Answer an evidence question without touching production code - research external facts against primary sources, build or iterate a disposable prototype (its own bugfixes included), or baseline current repository behavior before deciding or implementing. Use when the question is answerable by reading, building, or measuring with no user decision required; unsettled decisions belong to maestro-design. Prototypes are throwaway.
maestro-graph
Drive a pre-known multi-agent path as a maestro graph - run it by name or from a file you just wrote, pull each agent node with graph next, spawn it as a sub-agent under its maestro-<profile> definition, hand the result back with graph result, repeat until the verdict. Author a new graph from the reference when no preset fits.
maestro-improve
Turn filed lessons into the smallest doctrine edit. Use when a Lead assigns improvement work for one target: group pending lessons, make one evidence-linked commit per target, return it for independent challenge, and process each accepted or rejected lesson without deleting history.
maestro-questionnaire
Turn a decision the user cannot fully answer into a Markdown questionnaire for the one person who can - filled in async, or together over a meeting.
maestro-verify
Verify and close - cross-check coverage, run the VERIFY table, deliver the verdict, harvest durable lessons into decisions, close the bundle, and never claim remote state from local evidence.
maestro-work
Drive one accepted implementation unit - smallest falsifiable behavior, minimum edits, evidence that names the real falsifier; red tests only inside a Full bundle.