CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

trace-claude-code

Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical traces.

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/plugins/braintrust-tracing/skills/trace-claude-code/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 a well-structured, mostly executable guide with clear sections and useful troubleshooting, slightly held back by placeholder paths, mild intro/JSON redundancy, and validation steps placed in troubleshooting rather than inline in the setup workflow.

DimensionReasoningScore

Conciseness

The body is mostly lean — tables, code blocks, and a compact env-var table — with only minor padding (the intro re-states the description and the manual-setup JSON overlaps the setup-script mention).

4 / 5

Actionability

Provides concrete executable commands and complete config/SDK snippets, but paths like '/path/to/hooks/' are placeholders requiring substitution, so it is not fully copy-paste ready as-is.

4 / 5

Workflow Clarity

A clear setup sequence with prerequisites and a troubleshooting section containing validation/feedback steps (check hooks running, verify env vars, enable debug); the verify step exists but lives in troubleshooting rather than inline in the primary setup flow.

4 / 5

Progressive Disclosure

Well-organized into clear sections with content appropriately placed and an external doc link for the SDK alternative; a single ~240-line comprehensive doc with no one-level-deep reference files keeps it just short of a 5.

4 / 5

Total

16

/

20

Passed

Description

63%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 clearly and specifically conveys what the skill does and occupies a distinct niche, but it omits an explicit 'Use when...' trigger clause and natural trigger synonyms, which caps completeness and trigger-term quality at 3.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when you want to observe or debug Claude Code sessions, send traces to Braintrust, or monitor tool calls and conversation turns') to satisfy the trigger-guidance requirement and raise completeness.

Include natural synonyms users would actually say (e.g., 'logging', 'monitoring', 'debug Claude Code') alongside 'tracing' and 'observability' to broaden trigger-term coverage.

Optionally append file/extension or integration cues (e.g., 'Braintrust', 'claude-code traces') to strengthen distinctiveness against generic logging skills.

DimensionReasoningScore

Specificity

Names the domain and multiple concrete actions — 'Captures sessions, conversation turns, and tool calls as hierarchical traces' — giving comprehensive coverage of what is captured.

5 / 5

Completeness

The 'what' is clear (trace conversations, capture sessions/turns/tool calls) but the 'when' is only weakly implied with no explicit trigger guidance, capping completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Contains relevant keywords ('Claude Code conversations', 'Braintrust', 'observability', 'traces') but lacks common variations/synonyms and has no explicit 'Use when...' trigger phrase.

3 / 5

Distinctiveness Conflict Risk

Targets a clear niche (Braintrust observability for Claude Code) with mostly distinct triggers; minor overlap risk only with closely related logging/observability skills.

4 / 5

Total

15

/

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

parcadei/Continuous-Claude-v3

Path

.claude/plugins/braintrust-tracing/skills/trace-claude-code/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.