Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
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
  • Authors
  • 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
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Docs

ASecurity

Keep the discoverable surfaces in sync whenever you add or change a `room-cli` CLI command, flag, or a user-facing configuration knob (env var, `.bb/` workspace file, settings field): - Update the in-CLI guide templates under `packages/templates/src/templates/bb-guide-*.md`, turbo regenerates `packages/templates/src/generated/templates.generated.ts` (not committed) before every build, typecheck, and test task. - For core commands, update the room-cli skill at `plugins/bb-guide/skills/room-cli...

11 stars
0 votes
0 copies
0 views
Added 10/5/2026
ai-agentsdockerdebugging

Works with

cli

Security Analysis

A100/100

Pro scans all 19 files and shows the line behind each finding

Scanned 10/5/2026

$npx -y skills add davidondrej/cloudroom-gui --skill docs --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Docs?

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

Security grade badge for Docs
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/davidondrej-docs/badge)](https://www.skillsdirectory.com/skills/davidondrej-docs)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
CODE_REVIEW.md
# CLI, Guide, And Skill

Keep the discoverable surfaces in sync whenever you add or change a `room-cli` CLI command, flag, or a user-facing configuration knob (env var, `.bb/` workspace file, settings field):

- Update the in-CLI guide templates under `packages/templates/src/templates/bb-guide-*.md`, turbo regenerates `packages/templates/src/generated/templates.generated.ts` (not committed) before every build, typecheck, and test task.
- For core commands, update the room-cli skill at `plugins/bb-guide/skills/room-cli/SKILL.md` or its relevant reference. For plugin commands and settings, update the owning plugin's `skills/<name>/SKILL.md` or supporting reference, including built-in plugins. Keep plugin-specific behavior out of the core CLI skill. Configuration knobs also belong in `docs/configuration.md`.
- Match the existing chapter/section style; keep entries concise and accurate against the implementation.

Environment lifecycle hooks are core policy: cloudroom runs `.bb-env-setup.sh` after
an environment provider creates an owned path, and `.bb-env-teardown.sh` before
provider removal. Each has a 15-minute timeout; setup failure fails provisioning,
while reported teardown script failure does not block removal. Transport failure
keeps cleanup pending until the daemon confirms hook termination. Hook identity
and completion persist across server restarts. Attached checkout and
personal-workspace paths skip both hooks. These semantics apply equally to CLI,
SDK, and app launches; see [worktrees.md](worktrees.md).

The Machines settings creation drawer prepares an existing-machine command when access is ready, otherwise shows setup guidance. After access is ready, Choose a machine provider reviews provider inputs and launches through `hosts.experimental_create`/`room-cli machine create`. A machine belongs to no project; projects reach it later through project sources.

`room-cli machine list` enumerates persistent machines and takes `--all` to include
disposable provider sandboxes, matching the app's Show all machines reveal.
`room-cli updates` and `room-cli skill install-cli-skills` default to persistent machines
and still accept a sandbox through an explicit `--machine`.

Machine maintenance state is part of `room-cli machine list --json`; there is no
separate machine lifecycle command. Keep the machine guide and cloudroom command
index aligned with this surface.

Local installed-daemon start, stop, and uninstall operations are flags on
`install-machine.sh`, not `room-cli machine` subcommands.

Modal connection and machine commands are documented in [modal-sandboxes](../plugins/environment-modal-sandbox/skills/modal-sandboxes/SKILL.md). `room-cli modal image show [--json]` reads the Dockerfile shown in settings; `room-cli modal image set --file PATH [--json]` saves a validated plugin-wide override and `room-cli modal image reset [--json]` restores the bundled default for future machines; `room-cli modal account inspect --json` checks credentials; `room-cli machine create --provider modal-sandbox --json` automatically prepares the bundled image and installs the daemon. `room-cli machine remove MACHINE --yes` explicitly removes compute and private snapshots.

`room-cli thread spawn --machine-inputs <json>` configures either an explicit
`--new-machine` or the machine provider owned by a composed
`--environment-provider`; a composition rejects separate machine selectors.

Modal image debugging uses `room-cli modal image build`, `room-cli modal sandbox run`, `room-cli modal sandbox exec ID [--json] -- COMMAND...`, and `room-cli modal sandbox stop ID`. Debug compute expires after 30 minutes and skips BB enrollment and project setup. See the plugin skill for output limits and typed RPC equivalents.

Attribution

davidondrejdavidondrej
View sourceSee grades on GitHubMore from davidondrej →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →