CtrlK
BlogDocsLog inGet started
Tessl Logo

langfuse-debug-bundle

Collect Langfuse debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Langfuse problems. Trigger with phrases like "langfuse debug", "langfuse support bundle", "collect langfuse logs", "langfuse diagnostic", "langfuse troubleshoot".

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./plugins/saas-packs/langfuse-pack/skills/langfuse-debug-bundle/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.

The body is highly actionable with an executable, well-redacting diagnostic script and a sensible submit workflow. Its main gaps are conciseness (duplicated command blocks) and progressive disclosure (the script should live in a bundle file rather than inline).

Suggestions

Move the debug script into scripts/langfuse-debug.sh and reference it from SKILL.md instead of inlining ~110 lines, enabling one-level-deep progressive disclosure.

Remove the redundant "Current State" bash blocks (or Step 4's quick check) since they duplicate commands already in the main script.

Add an explicit validation loop in Step 2 (e.g., grep for pk-lf-/sk-lf- in the bundle; if found, re-redact and re-check before submitting) to strengthen the redaction checkpoint.

DimensionReasoningScore

Conciseness

The core bash script earns its tokens, but the "Current State" section and "Step 4: Quick Inline Diagnostic" duplicate commands already in the main script, adding padding that could be trimmed; mostly efficient with some redundancy.

3 / 5

Actionability

A complete, copy-paste-ready bash script covers environment, SDK versions, redacted config, network/auth tests, log redaction, package deps, and a reproduction template — fully executable across the common cases.

5 / 5

Workflow Clarity

Steps are clearly sequenced (run script, review/redact, submit, optional quick check) with a pre-share redaction checkpoint, but there is no explicit validate-and-retry loop if leaked secrets are found in the bundle.

4 / 5

Progressive Disclosure

Sections are organized, but the large debug script is inlined in SKILL.md rather than shipped as a scripts/langfuse-debug.sh bundle file, and no references/scripts/assets bundle exists despite the skill being script-centric.

3 / 5

Total

15

/

20

Passed

Description

82%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.

The description is well-formed: it answers both what and when with concrete trigger phrases and is tightly scoped to Langfuse. Its only weakness is specificity, naming just one concrete action where a fuller enumeration of bundle contents would help.

DimensionReasoningScore

Specificity

Names the Langfuse domain and one concrete action ("Collect Langfuse debug evidence for support tickets") but offers no further specific actions, matching the 1-2 concrete-actions anchor rather than the comprehensive 5.

3 / 5

Completeness

Explicitly states what it does ("Collect Langfuse debug evidence for support tickets") and when to use it ("Use when encountering persistent issues, preparing support tickets..."), with concrete trigger phrases — a clear match to the top anchor.

5 / 5

Trigger Term Quality

Lists five natural phrases ("langfuse debug", "langfuse support bundle", "collect langfuse logs", "langfuse diagnostic", "langfuse troubleshoot") with good synonym coverage, but lacks file-extension-style variants that would push it to a 5.

4 / 5

Distinctiveness Conflict Risk

Every trigger is prefixed with "langfuse" and scoped to Langfuse debugging, giving it a clear niche with minimal overlap risk against unrelated skills.

5 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation14 / 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

Total

14

/

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.