CtrlK
BlogDocsLog inGet started
Tessl Logo

langfuse-cost-tuning

Monitor and optimize LLM costs using Langfuse analytics and dashboards. Use when tracking LLM spending, identifying cost anomalies, or implementing cost controls for AI applications. Trigger with phrases like "langfuse costs", "LLM spending", "track AI costs", "langfuse token usage", "optimize LLM budget".

64

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/saas-packs/langfuse-pack/skills/langfuse-cost-tuning/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

Executable, well-sequenced guidance that stays lean and assumes Claude's competence, scoring well on conciseness, actionability, and workflow clarity. The main weakness is progressive disclosure: the bundled references/implementation.md is not referenced from the body and its content is duplicated inline rather than split out with a clear navigation pointer.

Suggestions

Add a clearly signaled pointer to references/implementation.md (e.g. a '## Implementation details' section linking to it) and move the overlapping cost-alert and model-selection code out of the body into that file, keeping only a concise example inline.

Define or stub the undefined helpers (callModel, sendAlert) so the code examples are fully copy-paste runnable, or note explicitly that they are user-provided.

Tighten the getCostReport example by dropping the step-by-step console.log formatting lines, which add tokens without adding instructional value.

DimensionReasoningScore

Conciseness

Prose is lean and assumes Claude's competence (no basic concept explanations), with compact tables for strategies and error handling; the only trimmable fat is the verbose console.log formatting inside the getCostReport example, which keeps it just below a 5.

4 / 5

Actionability

Four mostly complete, executable TypeScript examples cover the common cases (token capture, Metrics API query, model routing, budget alerts), but undefined helpers like callModel() and sendAlert() leave minor gaps that prevent copy-paste perfection.

4 / 5

Workflow Clarity

A clear four-step sequence (capture usage, query costs, route models, alert on budget) with a supporting error-handling table, but there are no explicit validate-then-fix feedback loops within the workflow itself, which is the gap that keeps it off 5.

4 / 5

Progressive Disclosure

The body is well-sectioned, but the provided bundle file references/implementation.md is never linked or signaled from the body, and large code blocks (cost alerts, model selection) are inlined despite overlapping with that reference file, matching the anchor for content that should be separate being inline with an un-signaled reference.

3 / 5

Total

15

/

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, well-structured description that explicitly answers both what and when with concrete Langfuse-anchored trigger phrases and third-person voice. The only soft spot is specificity, where a couple of the named actions lean abstract rather than naming concrete cost-control mechanisms.

DimensionReasoningScore

Specificity

Names the domain and lists several concrete actions ('Monitor and optimize LLM costs', 'tracking LLM spending', 'identifying cost anomalies', 'implementing cost controls'), but 'implementing cost controls' stays somewhat abstract rather than naming concrete mechanisms, so it stops short of comprehensive coverage.

4 / 5

Completeness

Clearly states what the skill does ('Monitor and optimize LLM costs using Langfuse analytics and dashboards') and explicitly states when to use it with concrete trigger phrases, matching the anchor that requires both an explicit what and an explicit when.

5 / 5

Trigger Term Quality

Provides five natural trigger phrases ('langfuse costs', 'LLM spending', 'track AI costs', 'langfuse token usage', 'optimize LLM budget') that users would plausibly say, but a few common synonyms (e.g. 'reduce LLM costs', 'AI spend') are missing.

4 / 5

Distinctiveness Conflict Risk

The Langfuse-specific anchoring ('Langfuse analytics and dashboards', 'langfuse costs', 'langfuse token usage') carves a clear niche with distinct triggers and minimal overlap risk with non-Langfuse cost skills.

5 / 5

Total

18

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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: 1 missing

Warning

Total

13

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.