langbot-deploy

Deploy and configure a LangBot instance — Docker / Docker Compose, Kubernetes, the config.yaml model, the Box sandbox runtime, the plugin runtime, and the global API key. Use when installing, deploying, upgrading, or configuring LangBot in production or self-hosted environments. Triggers on "deploy langbot", "langbot docker", "langbot compose", "langbot kubernetes", "langbot config.yaml", "langbot box runtime", "langbot global api key".

0.96x

Quality

88%

Does it follow best practices?

Impact

57%

0.96x

2 of 3 eval scenarios. Add 1 more for a full score.

Securityby

Passed

No findings from the security scan

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, dense deployment reference with executable commands, a clear config key table, and genuinely useful pitfall recovery guidance. The main shortfalls are the thin Kubernetes section, a missing explicit post-deploy verification step, and some inline Box token detail that could be split out.

Suggestions

Add a post-deploy validation step to the Compose workflow (e.g. curl the API/UI on :5300 and confirm the langbot/langbot_box containers are healthy) so the sequence ends in a checkpoint.

Give the Kubernetes section minimal executable substance — the kubectl apply command for docker/kubernetes.yaml and the Secret setup for langbot-plugin-runtime-control — instead of only pointing to the file.

Move the extended Box control-token security discussion (when the token is required, length, generation) into a separate reference file, keeping a one-line rule plus pointer in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Every line carries deployment-specific facts — ports (":5300", ":5410"), env overrides ("BOX__BACKEND"), defaults, and failure modes — with no explanation of concepts Claude already knows and no padding. The token budget is fully earned.	5 / 5
Actionability	The Compose path is copy-paste ready ("git clone … && cd LangBot/docker", "docker compose --profile all up"), the config.yaml snippet is directly usable, and concrete commands like "openssl rand -hex 32" and "sudo usermod -aG docker <user>" are given. It falls short of 5 because the Kubernetes section is a bare pointer ("See docker/kubernetes.yaml and the deployment guide") with no executable steps inline.	4 / 5
Workflow Clarity	The deploy sequence (clone → cd → compose up) is clear, and the Pitfalls section supplies error→fix feedback loops (e.g. "No supported sandbox backend" → usermod docker group + restart in new shell). The 5 anchor is not met because there is no explicit post-deploy validation step such as verifying the API/UI on port 5300 before proceeding.	4 / 5
Progressive Disclosure	Sections are well-organized and external material is signaled one level deep ("See `langbot-dev` for development", "See `langbot-mcp-ops` … and `docs/API_KEY_AUTH.md`"). It stays at 4 rather than 5 because the inline Box token-security discussion is lengthy for an overview, and Kubernetes detail lives entirely outside with no bundled reference file to anchor it.	4 / 5
	Total	17 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states what the skill covers (deploy/configure across Docker/Compose, Kubernetes, config.yaml, Box, plugin runtime, API key) and when to use it, with explicit trigger phrases. The only gap is that the action vocabulary is limited to deploy/configure rather than a richer set of concrete operations.

Dimension	Reasoning	Score
Specificity	"Deploy and configure a LangBot instance — Docker / Docker Compose, Kubernetes, the config.yaml model, the Box sandbox runtime, the plugin runtime, and the global API key" names the domain and comprehensively enumerates coverage areas. It stays at 4 rather than 5 because only two action verbs (deploy, configure) carry the description instead of multiple distinct concrete actions.	4 / 5
Completeness	Both questions are answered explicitly: the what is "Deploy and configure a LangBot instance" with enumerated subsystems, and the when is "Use when installing, deploying, upgrading, or configuring LangBot in production or self-hosted environments" with concrete trigger phrases appended.	5 / 5
Trigger Term Quality	"Use when installing, deploying, upgrading, or configuring LangBot in production or self-hosted environments" plus explicit trigger phrases ("deploy langbot", "langbot docker", "langbot compose", "langbot kubernetes", "langbot config.yaml") give good natural-term coverage. A few plausible user phrasings (e.g. "self-host langbot", "langbot helm", "langbot upgrade") are missing, so it falls just short of the 5 anchor.	4 / 5
Distinctiveness Conflict Risk	The product-specific niche (LangBot production deployment) and product-named triggers make wrong-skill activation unlikely. Adjacent skills (langbot-dev, langbot-mcp-ops) cover development and MCP operations respectively, leaving only minimal overlap risk.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: langbot-app/LangBot
Path: skills/skills/langbot-deploy/SKILL.md
Commit: 40a3a94

Reviewed: 3 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.