CtrlK
BlogDocsLog inGet started
Tessl Logo

langbot-mcp-ops

Operate a LangBot instance through its built-in MCP (Model Context Protocol) server. Use when an AI agent needs to manage LangBot — list/create/update/delete bots, pipelines, models, knowledge bases, MCP servers, and skills — over MCP instead of raw HTTP. Covers the /mcp endpoint, API-key auth (web-UI lbk_ keys and the config.yaml global key), the tool surface, and client configuration. Triggers on "langbot mcp", "manage langbot via mcp", "langbot /mcp", "langbot mcp server".

69

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

76%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 concise, well-structured operational reference with concrete endpoint, auth, and client-configuration guidance. Its weaknesses are the absence of an example mutation request body and the lack of verification steps for destructive operations, the latter capping workflow clarity.

Suggestions

Add a concrete example request body for one create_*/update_* tool so mutating-tool guidance is copy-paste ready, not just shape-described.

Insert an explicit verify step after mutations (e.g. re-call get_* to confirm the change) and a 401/403 → fix-key/scope → retry loop in the How-to-use workflow to lift workflow clarity past the destructive-ops cap.

Consider moving the full tool-surface table and auth detail into a references/ file linked from the body, so the SKILL.md stays a lean overview with one-level-deep navigation.

DimensionReasoningScore

Conciseness

Lean body that assumes Claude's competence — it never explains what MCP or HTTP is, and jumps to non-obvious operational specifics (two key types, workspace binding, SHA-256 storage) where every token earns its place.

5 / 5

Actionability

Concrete endpoint URL, exact auth headers, a copy-paste JSON client config, and a full tool table make it mostly executable, but mutating tools are described only as "a JSON object matching the same shape as the corresponding HTTP API request body" with no example body — a real gap.

4 / 5

Workflow Clarity

The numbered how-to sequences get-key → point-client → get_system_info → mutate with a connectivity checkpoint, but destructive create/update/delete operations have no post-mutation verification or validate-fix-retry loop, so the destructive-ops cap holds at 3.

3 / 5

Progressive Disclosure

Well-organized single-file structure with clear section headers and no nested references, but a reference-heavy skill surface (full tool reference, auth detail) ships with no bundle files and no one-level-deep reference split, leaving a minor organization gap.

4 / 5

Total

16

/

20

Passed

Description

92%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: third-person voice, explicit what-and-when, concrete resource actions, and clear MCP-specific triggers that distinguish it from sibling LangBot skills. The only minor gap is trigger-term breadth, which clusters around a single phrase family.

DimensionReasoningScore

Specificity

Lists multiple concrete CRUD actions across bots, pipelines, models, knowledge bases, MCP servers, and skills ("list/create/update/delete"), plus endpoint, auth, tool surface, and client configuration — comprehensive coverage matching the top anchor.

5 / 5

Completeness

Clearly states what (operate LangBot via its MCP server, manage resources over MCP instead of raw HTTP) and when ("Use when an AI agent needs to manage LangBot" plus explicit "Triggers on" phrases), matching the top anchor.

5 / 5

Trigger Term Quality

Explicit triggers ("langbot mcp", "manage langbot via mcp", "langbot /mcp", "langbot mcp server") give good natural-term coverage, but they are narrow synonyms of one phrase rather than broad variations, so it sits just below the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

A clear MCP-specific niche ("over MCP instead of raw HTTP", the /mcp endpoint) with distinct triggers minimizes conflict with general LangBot or HTTP-API skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
langbot-app/LangBot
Reviewed

Table of Contents

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.