SkillProof tested Claude skills

Langsmith Fetch

Debugujte agenty LangChain/LangGraph načítáním LangSmith traces pomocí langsmith-fetch CLI

od ECNU-ICALK · ECNU-ICALK/AutoSkill

Funguje s nastavením ★ 7.6/10

Langsmith Fetch — Debugujte agenty LangChain/LangGraph načítáním LangSmith traces pomocí langsmith-fetch CLI

Co umí

Obaluje the external langsmith-fetch CLI to pull recent execution traces from a LangSmith project, then analyzes errors, tool calls, token usage, and memory operations. Spouští se, když uživatel asks to debug an agent, show recent traces, check for errors, or review agent performance. Vyžaduje the pip package langsmith-fetch plus a LANGSMITH_API_KEY and a project that already has traces.

Testovací report

Nalezeno SKILL.md at SkillBank/Common/AwesomeClaudeSkills/langsmith-fetch/SKILL.md; frontmatter se parsuje s name+description. The body bundles no scripts — it only shells out to the external langsmith-fetch CLI, which I confirmed is a real PyPI package (v0.3.1) whose documented commands (traces/trace/threads/thread, --limit, --last-n-minutes, --format pretty|json|raw, --include-metadata) match the skill. Both referenced repos returned HTTP 200. No security smells (no curl|sh, base64, or exfiltration). Could NOT run the output stage: langsmith-fetch needs a valid LANGSMITH_API_KEY and a project holding real agent traces, which I cannot provision, so no baseline-vs-skill artifact was produced. Docs lose a point for minor drift (skill shows --after and a config show/set subcommand; the real CLI uses --since) and fabricated example outputs.

Testováno: 2026-07-21 · Claude Code 2.x (agent harness)

Instalace

git clone --depth 1 https://github.com/ECNU-ICALK/AutoSkill.git /tmp/langsmith-fetch-src
mkdir -p ~/.claude/skills
cp -R /tmp/langsmith-fetch-src/SkillBank/Common/AwesomeClaudeSkills/langsmith-fetch ~/.claude/skills/langsmith-fetch
# Required external dependency (the skill only calls this CLI; nothing is bundled):
#   pip install langsmith-fetch        # PyPI package, currently v0.3.1
# Required environment (skill produces nothing without these):
#   export LANGSMITH_API_KEY=lsv2_...
#   export LANGSMITH_PROJECT=your-project-name
# The target project must already contain traces from a running LangChain/LangGraph agent.
# Note: SKILL.md references some flags that differ from the real CLI (e.g. --after; real CLI uses --since).

Příkazy a ukázkové prompty

  • /langsmith-fetchDebugujte agenty LangChain/LangGraph načítáním LangSmith traces pomocí langsmith-fetch CLI

Skilly se spouštějí běžnými požadavky — žádné příkazy k zapamatování. Po instalaci ho aktivují prompty jako tyto (anglicky):

  • Fetch the latest LangSmith trace for this agent
  • Why did my LangGraph agent call the wrong tool
  • Analyze recent agent traces for memory errors

Kompletní testovací report (anglicky) →