بنقرة واحدة
dump
Use when a long brainstorm or brain dump needs deep capture, prior-art routing, and durable next states.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Use when a long brainstorm or brain dump needs deep capture, prior-art routing, and durable next states.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Routes adaptive multi-agent deliberation with fractal context cycles. Use when using /cdo, think/deep/debug/parliament work, or long runs paired with autoresearch scheduling.
Use when you need an evidence-first provenance report from `cass`, repo docs, `.lev`, `~/.agents/diagrams`, `qmd`, or Grep/Glob tools.
Use the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show dependencies, impact analysis, dead code, unused functions, high fan-out, refactor candidates, code quality audit, graph query syntax, Cypher query examples, edge types, how to use search_graph.
Handle blocked destructive commands. Use when dcg blocks rm -rf, git reset --hard, DROP DATABASE, kubectl delete, or when configuring agent safety guardrails.
Use when running a visible Lev autopilot that coordinates research, interview, arch, propose, AgentPing, warm-worker intent, realtime dashboard intent, and lev exec updates across the lifecycle.
Heartbeat-driven autonomous development loop using lev loop autodev, with interval, budget, and tick controls for in-process SDLC execution.
| name | dump |
| description | Use when a long brainstorm or brain dump needs deep capture, prior-art routing, and durable next states. |
| skill_type | alias |
| category | lifecycle |
| output_template | hud |
/dump is not a separate capture engine. It invokes /capture --deep, renders
the shared lifecycle ledger, then takes the obvious next lifecycle action only
when the ledger proves the row is durable and write-authorized.
Lifecycle lane: Shape -> Plan
Entity movement: memory -> captured | proposed | execution_ready | blocked
Workstream: resolve active workstream before writing capture artifacts
Upstream: conversation, /work
Downstream: /capture --deep, /prior-art, /propose, /exec
Router: /work
HUD: end with 🧬 {ws} ⚡{exec_count} 📥{capture_count} ⏸️{paused_count} ✅{done_count} | 🚦{gate}={score} | ⏭️ {next} | 🔁{loop_state}
steps:
- id: invoke_capture_deep
action: Run the /capture deep-mode inventory and fidelity loop.
validation: "Every topic has a durable route or blocker and appears in the shared capture ledger."
on_failure: "Return to /capture with the unresolved bucket."
- id: render_capture_ledger
action: Render the same <capture-results> lifecycle ledger used by /capture.
validation: "The table shows compiled_intent, current_location, artifact_ref, route_state, fidelity, next_route, and blocker for every item."
on_failure: "Do not route. Show the missing ledger fields."
- id: probe_prior_art
action: Search existing work per topic before creating new artifacts.
validation: "Each new proposal has no better existing home."
on_failure: "Route to /prior-art and stop proposal creation for that topic."
- id: route_next
action: Take the next action for shovel-ready rows: /exec for execution_ready, /propose for aligned captured work, /interview for ambiguous rows.
validation: "No routed item has current_location=memory without artifact_ref, blocker, or explicit write authorization."
on_failure: "Show the blocked items and missing gate."
First render the exact /capture --deep ledger block:
| ID | Topic | Compiled Intent | Current Location | Artifact | Route State | Fidelity | Next Route | Blocker |
|---|---|---|---|---|---|---|---|---|
| {intent_id} | {topic} | {compiled_intent} | {current_location} | {artifact_ref} | {route_state} | {fidelity_pct} | {next_route} | {blocker} |
{items_that_could_not_be_written}
{blocked_items}
{transitioning_items}
Then show action stats:
| Metric | Count |
|---|---|
| Total inventoried | N |
| Routed to existing files | N |
| New proposals created | N |
| Ready for /exec | N |
| Needs /interview | N |
| Blocked | N |
/capture --deep owns inventory, fidelity, durable artifact writes, the canon write gate, and the shared ledger./prior-art avoids duplicate artifacts./propose creates task DNA and execution plans./exec handles execution-ready entities.