CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

langfuse

Langfuse was decommissioned on 2026-07-09 — do not add Langfuse tracing or query Langfuse for usage/cost. Use this skill only to learn where usage observability lives now. Token usage and cost questions route to `joelclaw usage` and ClickHouse otel_events.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

An exemplary decommissioned-service skill: dense with non-inferable repo facts, fully executable commands, an unambiguous question-to-replacement mapping, and clean organization with no padding. Nothing here explains what Claude already knows, and every pointer is concrete and one level deep.

DimensionReasoningScore

Conciseness

Every line carries repo-specific facts Claude cannot know (dates, file paths, event names, failure modes, cadence); it explains no general concepts and contains no version-conditional branching — its dates are decommission facts placed under an explicitly 'decommissioned' header. This is the lean, every-token-earns-its-place anchor.

5 / 5

Actionability

Provides copy-paste-ready commands (`joelclaw usage --hours 24 [--source router|agents|all] [--model X] [--machine Y] [--json]`, `grep -ri langfuse packages/ apps/`) plus exact file paths, event names (`model_router.result`, `agent_usage.turn`), and scan schedule — fully executable guidance covering the common usage/cost questions.

5 / 5

Workflow Clarity

This is a simple, single-purpose tombstone/redirect skill and its single action is unambiguous: never use Langfuse, map each need (CLI, query layer, router usage, agent sessions, pricing, daily report) to its replacement. The grep command even supplies a verification checkpoint, and no destructive workflow is instructed so no cap applies.

5 / 5

Progressive Disclosure

The body is ~30 lines (under 50), self-contained with no need for external references, and organized into clear sections ('Where usage observability lives now', 'Residue'); the single external pointer (`.svx` project receipt) is one level deep and clearly signaled. Under the under-50-lines guideline this earns the top anchor.

5 / 5

Total

20

/

20

Passed

Description

78%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, distinctive tombstone description that states what happened, what not to do, and where usage observability lives now, with concrete routing targets. Its main gaps are the absence of an explicit 'Use when the user mentions Langfuse' trigger phrase and a few natural synonym terms (e.g., spend, billing).

Suggestions

Add an explicit trigger clause such as 'Use when the user mentions Langfuse or asks where token usage/cost data lives now' to lift completeness from the 'when could be more explicit' anchor to the top anchor.

Broaden trigger coverage with natural synonyms users actually say — e.g., 'spend', 'billing', 'token metrics', 'telemetry' — alongside the existing 'token usage and cost' phrasing.

DimensionReasoningScore

Specificity

Names several concrete actions and targets — 'do not add Langfuse tracing or query Langfuse for usage/cost' and routing 'to `joelclaw usage` and ClickHouse otel_events' — but coverage of what 'learn where usage observability lives now' entails is partial, so it fits 'several specific actions; minor gaps' rather than the comprehensive anchor 5.

4 / 5

Completeness

The 'what' is clear (tombstone: Langfuse is decommissioned; learn where usage observability lives now) and a 'when' is present via 'Use this skill only to learn…' plus the token-usage/cost routing sentence, but there is no explicit 'Use when the user mentions Langfuse' trigger phrase, so it fits anchor 4 rather than 5.

4 / 5

Trigger Term Quality

Includes good natural keywords users would say — 'Langfuse', 'token usage', 'cost', 'usage observability', 'tracing' — but misses common synonyms like 'spend', 'billing', or 'metrics', matching anchor 4 ('good keyword coverage; a few natural terms missing') rather than the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

'Langfuse' is a unique proper noun and the description stakes a clear niche (decommissioned tombstone with explicit redirect targets), giving it distinct triggers and minimal conflict risk with any other skill — anchor 5.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

joelhooks/joelclaw

Path

skills/langfuse/SKILL.md

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.