langbot-dev

Develop, build, and debug the LangBot core backend and web frontend. Use when working inside the LangBot repository — backend (Python/Quart, src/langbot/pkg), the Vite/React web UI, HTTP API controllers/services, Alembic migrations, or the MCP server. Covers the dev environment (uv, pnpm), repo layout, the API auth model (user token / API key / global key), adding API endpoints, and the rule that API changes must update the MCP server and skills. Triggers on "langbot backend", "langbot dev", "langbot api", "add langbot endpoint", "langbot migration".

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

90%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 strong, dense skill body: fully executable commands, precise paths, and repo-specific knowledge that assumes Claude's competence with zero filler. The endpoint workflow is well sequenced but leaves validation implicit (tests are documented but not wired into the workflow), and the auth-model section is the only candidate for extraction to a reference file.

Dimension	Reasoning	Score
Conciseness	Every section carries non-inferable, repo-specific knowledge (the repo layout tree, 'Route auth is declared per-route via AuthType in pkg/api/http/controller/group.py', exact uv/pnpm/pytest commands) with no padding or explanation of concepts Claude already knows. Assumes competence throughout, e.g. 'NOT Next.js — dev script is vite' delivers the one non-obvious fact in a parenthetical.	5 / 5
Actionability	Commands are copy-paste ready and specific: 'uv run python -m langbot.pkg.persistence.alembic_runner autogenerate "description"', 'uv run pytest tests/unit_tests/api -q', 'cd web; pnpm install; pnpm dev'. The endpoint workflow gives exact directories ('pkg/api/http/controller/groups/', 'pkg/api/mcp/server.py') and enumerated AuthType values; only the conditional OpenAPI step is slightly vague, which is explicitly hedged.	5 / 5
Workflow Clarity	The 'Adding an API endpoint' section is a clear numbered sequence with real checkpoints ('API and MCP surface must stay aligned', 'check the separate langbot-cli client for compatibility'). However, no explicit validation step is wired into the workflow — test commands exist in a separate 'Tests' section but the workflow never says to run them after an endpoint change, a minor checkpoint gap.	4 / 5
Progressive Disclosure	Good structure for a single-file skill: well-organized sections (Stack, Dev environment, Repo layout, auth model, endpoint workflow, Tests, See also) with clear one-level pointers to sibling skills ('langbot-mcp-ops', 'langbot-plugin-dev'). No bundle files exist, and the ~30-line auth-model detail is the only content that arguably belongs in a separate reference file were the skill to grow.	4 / 5
	Total	18 / 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.

An effective description that explicitly answers both what (develop/build/debug backend and web frontend, with the covered areas enumerated) and when (repository scope plus literal trigger phrases), in third person with a clearly bounded niche. Minor gaps: trigger coverage omits frontend/web-UI phrasings, and the capability list skips tests/standards the body actually covers.

Dimension	Reasoning	Score
Specificity	Lists several specific capabilities with concrete technology named — 'Develop, build, and debug the LangBot core backend and web frontend', 'HTTP API controllers/services, Alembic migrations, or the MCP server', 'the API auth model (user token / API key / global key)'. Minor gaps in coverage: running tests, coding standards, and commit conventions are covered by the skill body but not mentioned.	4 / 5
Completeness	Both what and when are explicit and concrete: what — 'Develop, build, and debug the LangBot core backend and web frontend... Covers the dev environment (uv, pnpm), repo layout, the API auth model..., adding API endpoints'; when — 'Use when working inside the LangBot repository' reinforced with literal trigger phrases.	5 / 5
Trigger Term Quality	Explicit triggers are natural user phrasings: "Triggers on 'langbot backend', 'langbot dev', 'langbot api', 'add langbot endpoint', 'langbot migration'", plus 'Use when working inside the LangBot repository'. A few natural variations are missing, e.g. 'langbot frontend', 'langbot web', or 'langbot webui'.	4 / 5
Distinctiveness Conflict Risk	Clear niche with minimal conflict risk: everything is scoped to 'the LangBot core (the main repo), distinct from plugin development... and deployment', and all triggers are langbot-prefixed phrases. The core-vs-plugin/deploy/mcp-ops boundary is explicitly drawn, so wrong-skill triggering is unlikely.	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-dev/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.