Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Dump

ASecurity

Use when a long brainstorm or brain dump needs deep capture, prior-art routing, and durable next states.

22 stars
0 votes
0 copies
0 views
Added 9/20/2026
documentationgo

Works with

cli

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add lev-os/agents --skill dump --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Dump?

Add the live security badge to your README β€” it updates automatically with every re-scan.

Security grade badge for Dump
[![Security: A β€” Skills Directory](https://www.skillsdirectory.com/api/skills/lev-os-dump/badge)](https://www.skillsdirectory.com/skills/lev-os-dump)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
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 - Action Wrapper for /capture --deep

`/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.

## Entity Reconciliation

After authorized material progress, reconcile touched and causally affected
artifacts before routing, handoff, or final response. Track entity ref,
island/provider locator (a path for file storage), basis/evidence, and the
reason/action due. Update through the verified owning CLI/adapter; use a
write-authorized skill fallback only when that operation is unavailable.
Record updated, no_change(reason), or blocked(reason), preserving unresolved
refs. Reading or mentioning a path alone creates no update obligation.
Read-only work reports pending changes only. Reminders grant no write authority;
task status stays with the bound tracker. Update only artifacts whose content
or evidence changed; do not rewrite every referenced document.

## Work Link

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} πŸ“₯{capture_count} ⏸️{paused_count} βœ…{done_count} | 🚦{gate}={score} | ⏭️ {next} | πŸ”{loop_state}`

## Protocol

```yaml
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 compact <capture-results> delta used by /capture; retain the complete ledger in the durable artifact.
    validation: "The response names what was saved, what remains in memory, the highest-leverage decision, and the next route."
    on_failure: "Do not route. Show the full ledger only for --full, audit, or debug."

  - 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."
```

## Output

Render the `/capture --deep` delta:

Render the Markdown inside this template; do not print the XML wrapper tags.

<capture-results>
## /dump results

Saved: {count_and_artifact_refs_or_none}
Still in memory: {count_and_topics_or_none}
Decision needed: {one_highest_leverage_decision_or_none}
Ready next: {count_and_route_or_none}
Next: {one_primary_action}

Details: {ledger_artifact_ref_or_use_--full}
</capture-results>

## Red Flags

- "Dump can skip prior-art."
- "This is just a list."
- "We can leave low-priority items in memory."
- "Dump should implement its own capture protocol."
- "Dump can skip the shared ledger because it routes immediately."
- "A metric table is enough to prove what is on disk."
- "Dump can turn proposal language into writes without a canon write gate."

## Related

- `/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.

Attribution

lev-oslev-os
View sourceMore from lev-os β†’
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots Β· $299/mo Β· GSC-verified traffic Β· sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots Β· $299/mo Β· GSC-verified traffic Β· sponsors can never buy grades.

See placements

Related Skills

Context Fundamentals

Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.

179001 votes

release-notes

Draft release notes and changelog entries from git history or merged PRs between two refs (tags/SHAs/branches), including breaking changes, migrations, and upgrade steps. Use when the user asks for release notes, changelog updates, or a GitHub Release draft.

1301 votes

docs-style-guide

Documentation style guide enforcer by @planetabhi. Applies and reviews the writing style guide when authoring or editing product documentation and tutorials. Use to check prose for voice, tense, word choice, inclusive language, formatting, code block, UI, Markdown, and number/date conventions.

11 votes

Caveman Help

Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".

1023330 votes

How It Works

Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".

929660 votes
View all in documentation β†’