langfuse-ci-integration

Configure Langfuse CI/CD integration with GitHub Actions and automated testing. Use when setting up automated testing, configuring CI pipelines, or integrating Langfuse tests into your build process. Trigger with phrases like "langfuse CI", "langfuse GitHub Actions", "langfuse automated tests", "CI langfuse", "langfuse pipeline".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

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

The body is highly actionable with copy-paste executable code and clear sequencing, but it is hurt by repeated boilerplate, a batch deployment step lacking validation checkpoints, and monolithic inline scripts that would benefit from being split into referenced files.

Suggestions

Add a pre-deploy validation checkpoint to Step 4 (e.g., run the experiment gate or prompt tests before promoting prompts to the "production" label) and include an explicit validate->fix->retry feedback loop, since unvalidated production deployment caps workflow clarity.

Extract the full deploy-prompts and check-quality-regression scripts into actual files under scripts/ and reference them one level deep from SKILL.md, keeping the body as an overview to improve progressive disclosure.

De-duplicate the OpenAI/Langfuse client setup shared by Steps 2 and 3 and drop or justify the no-op connectivity check whose `.catch(() => {})` swallows errors, to tighten the body.

Dimension	Reasoning	Score
Conciseness	Prose is tight and assumes Claude's knowledge (no concept explanations), but the ~267-line body repeats OpenAI client boilerplate across Steps 2 and 3 and includes a no-op "Langfuse connectivity check" whose `.catch(() => {})` swallows errors, so it could be tightened rather than being fully lean.	2 / 3
Actionability	Each step ships fully executable TypeScript/YAML with concrete file paths (`.github/workflows/langfuse-tests.yml`, `tests/ai/prompt-quality.test.ts`) and copy-paste commands (`npx vitest run tests/ai/`, `node scripts/deploy-prompts.mjs`), matching the score-3 anchor for executable, specific examples.	3 / 3
Workflow Clarity	The five steps are clearly sequenced, but Step 4 (Automated Prompt Deployment) is a batch production operation that pushes prompts labeled "production" directly on push to main with no pre-deploy validation or validate->fix->retry feedback loop, which the rubric caps at 2 for destructive/batch workflows.	2 / 3
Progressive Disclosure	No bundle files exist, yet the body inlines full deploy/regression scripts (e.g. `scripts/deploy-prompts.mjs`, `scripts/check-quality-regression.ts`) as code rather than as separate referenced files, so content that should be split is inline; section headers and external doc links provide some structure but no one-level-deep references.	2 / 3
	Total	9 / 12 Passed

Description

100%

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

The description is strong: it states concrete capabilities, includes an explicit 'Use when' trigger clause, and provides natural trigger phrases tied to a distinct Langfuse CI/CD niche. Minor weakness is limited diversity among the trigger phrases (several near-duplicates of 'langfuse CI').

Dimension	Reasoning	Score
Specificity	"Configure Langfuse CI/CD integration with GitHub Actions and automated testing" names multiple concrete actions (configure integration, GitHub Actions, automated testing), matching the score-3 anchor listing several specific actions rather than just a domain plus partial actions.	3 / 3
Completeness	It answers both what ("Configure Langfuse CI/CD integration...") and when via an explicit "Use when setting up automated testing, configuring CI pipelines, or integrating Langfuse tests into your build process" clause, satisfying the score-3 anchor; the required 'Use when...' clause is present so it is not capped at 2.	3 / 3
Trigger Term Quality	Explicit trigger phrases ("langfuse CI", "langfuse GitHub Actions", "langfuse automated tests", "CI langfuse", "langfuse pipeline") give good coverage of natural terms a user would actually say, matching the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	The Langfuse-specific niche with distinct langfuse-prefixed triggers makes it unlikely to fire for an unrelated skill, matching the score-3 anchor; it is not generic enough to broadly conflict, though the trigger phrasing is somewhat repetitive rather than diverse.	3 / 3
	Total	12 / 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 — 13 / 16 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
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	13 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 3022dd3

Reviewed: 1 day 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.