Explorar skills

graphmind fornece ao Claude Code memória persistente e inteligência de código estrutural em todos os projetos registrados. Ele é acionado automaticamente em qualquer diretório de projeto registrado e é obrigatório consultar o graphmind antes de usar grep, find ou ler arquivos-fonte.

Internal fetcher module for Google Docs and Sheets. Fetches content via MCP (preferred, when available), Google API with bearer token or public URL export (fallback), or browser DOM extraction via Claude in Chrome (last resort) and returns Markdown. Used by /bedrock:learn and /bedrock:sync — not intended for direct user invocation.

Internal fetcher module for Confluence pages. Fetches content via Atlassian MCP (preferred), REST API with Basic Auth (fallback), or browser DOM extraction via Claude in Chrome (last resort) and returns Markdown. Used by /bedrock:learn and /bedrock:sync — not intended for direct user invocation.

TRIGGER when: user asks to trace a specific route, schema object, file, table, RPC, or error string through its evidence. Covers `route_trace`, `schema_usage`, `file_health`, `auth_path`, `trace_file`, `preflight_table`, `trace_edge`, `trace_error`, `trace_table`, `trace_rpc`.

TRIGGER when: user is working in an unfamiliar repo, asks 'where is X', 'what touches Y', needs broad search across code/schema/routes, or is unsure which mako tool fits the task. Covers `reef_ask`, `reef_status`, `reef_verify`, `reef_impact`, `mako_help`, `tool_search`, `context_packet`, `live_text_search`, `lint_files`, and `tool_batch`.

TRIGGER when: user wants entity-wide context for a table, route, or RPC -- schema + RLS + readers + writers + downstream touches all at once. Covers `table_neighborhood`, `route_context`, `rpc_neighborhood`.

TRIGGER when: user wants an investigation packet, pre-ship artifact, recall of prior work or answers, or to log tool-run feedback / inspect telemetry. Covers `suggest`, `investigate`, `workflow_packet`, `tenant_leak_audit`, `health_trend`, `issues_next`, `session_handoff`, all four artifact tools, `recall_answers`, `recall_tool_runs`, `agent_feedback`, `agent_feedback_report`, `runtime_telemetry_r

TRIGGER when: user wants an investigation packet, pre-ship artifact, recall of prior work or answers, or to log tool-run feedback / inspect telemetry. Covers `suggest`, `investigate`, `workflow_packet`, `tenant_leak_audit`, `health_trend`, `issues_next`, `session_handoff`, all four artifact tools, `recall_answers`, `recall_tool_runs`, `agent_feedback`, `agent_feedback_report`, `runtime_telemetry_r

TRIGGER when: user asks about relationships, dependency paths, import hotspots or cycles, symbol impact, or blast radius of a proposed change. Covers `graph_neighbors`, `graph_path`, `flow_map`, `change_plan`, `imports_deps`, `imports_impact`, `imports_hotspots`, `imports_cycles`, `symbols_of`, `exports_of`.

Start here when working in a project with the mako-ai MCP server configured. Entry point that explains how mako's tool skills are organized and carries the policy for logging `agent_feedback` vs acknowledging static findings with `finding_ack`.

TRIGGER when: user wants an investigation packet, pre-ship artifact, recall of prior work or answers, or to log tool-run feedback / inspect telemetry. Covers `suggest`, `investigate`, `workflow_packet`, `tenant_leak_audit`, `health_trend`, `issues_next`, `session_handoff`, all four artifact tools, `recall_answers`, `recall_tool_runs`, `agent_feedback`, `agent_feedback_report`, `runtime_telemetry_r

TRIGGER when: user is working in an unfamiliar repo, asks 'where is X', 'what touches Y', needs broad search across code/schema/routes, or is unsure which mako tool fits the task. Covers `reef_ask`, `reef_status`, `reef_verify`, `reef_impact`, `mako_help`, `tool_search`, `context_packet`, `live_text_search`, `lint_files`, and `tool_batch`.