langfuse-local-dev-loop

Set up Langfuse local development workflow with hot reload and debugging. Use when developing LLM applications locally, debugging traces, or setting up a fast iteration loop with Langfuse. Trigger with phrases like "langfuse local dev", "langfuse development", "debug langfuse traces", "langfuse hot reload", "langfuse dev workflow".

Quality

77%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/saas-packs/langfuse-pack/skills/langfuse-local-dev-loop/SKILL.md

Quality

Content

64%

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

This skill provides highly actionable, executable guidance for setting up a Langfuse local development workflow with good structural organization. Its main weaknesses are verbosity (including both v3 and v4 setups inline, lengthy utility code) and the lack of explicit validation checkpoints to confirm each step succeeded. The content would benefit from splitting legacy/advanced content into separate files and adding verification steps.

Suggestions

Add explicit validation checkpoints after key steps—e.g., 'Run the dev script and verify you see a trace URL printed to console' or 'Confirm trace appears in the Langfuse UI before proceeding.'

Move the v3 legacy setup into a separate reference file (e.g., LEGACY-V3.md) and link to it, keeping the main skill focused on the current v4+ approach.

Add a quick smoke test step after the docker-compose setup, such as a curl health check command to verify the local instance is running before proceeding.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes both v4+ and v3 legacy setup steps which adds bulk. Some code examples are lengthy and could be tightened—e.g., the devTrace utility and example workflow contain boilerplate that a capable model could infer. The error handling table and docker-compose are useful but the overall content is longer than necessary.	2 / 3
Actionability	The skill provides fully executable, copy-paste ready code for every step: TypeScript files, package.json scripts, docker-compose YAML, bash commands, and .env files. Concrete examples with specific library imports and function signatures make this highly actionable.	3 / 3
Workflow Clarity	Steps are clearly numbered and sequenced, but there are no explicit validation checkpoints—no step to verify traces are actually appearing, no verification that the local instance is healthy beyond 'wait 10s', and no feedback loop for debugging failed setups. For a multi-step dev environment setup, validation steps would be important.	2 / 3
Progressive Disclosure	The content is well-structured with clear headers and the self-hosted section is appropriately marked as optional. However, with no bundle files, all content is inline in a single file that runs quite long. The v3 legacy code and the dev utilities could be split into separate reference files. The reference to `langfuse-sdk-patterns` and `langfuse-install-auth` provides some cross-referencing but the main file is monolithic.	2 / 3
	Total	9 / 12 Passed

Description

89%

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

This is a well-structured skill description with strong trigger terms, clear 'what' and 'when' clauses, and a distinctive niche around Langfuse local development. The main weakness is that the specific capabilities could be more concrete — listing actual setup steps or tools involved rather than general concepts like 'hot reload' and 'debugging'.

Suggestions

Add more concrete actions to improve specificity, e.g., 'configure Docker Compose for local Langfuse server, set up SDK instrumentation, configure environment variables for local tracing'.

Dimension	Reasoning	Score
Specificity	It names the domain (Langfuse local development) and some actions (hot reload, debugging, fast iteration loop), but doesn't list multiple concrete specific actions like configuring environment variables, setting up Docker containers, or instrumenting code.	2 / 3
Completeness	Clearly answers both 'what' (set up Langfuse local development workflow with hot reload and debugging) and 'when' (developing LLM applications locally, debugging traces, setting up fast iteration loop) with explicit trigger phrases.	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms including 'langfuse local dev', 'langfuse development', 'debug langfuse traces', 'langfuse hot reload', 'langfuse dev workflow' — these are phrases a user would naturally say when needing this skill.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive — 'Langfuse' is a specific tool, and the focus on local development workflow with hot reload creates a clear niche that is unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 57b5254

Reviewed: 2 days 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.