Investigate an agent run by reviewing its execution trace, a record of steps and tool calls. Start with a run overview, then inspect relevant inputs, outputs, errors, and token use to explain what happened or diagnose a failure.
Analyze and answer questions about agent execution traces. Use this skill when the user asks about a trace, wants to debug a failed agent run, understand what an agent did, analyze token usage or efficiency, or asks "what happened in trace X". Triggers: trace analysis, trace debugging, trace QA, execution review, agent run review.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Analyze agent execution traces to answer questions about what happened, why it failed, how efficient it was, or any other aspect of the run.
Always start with overview to understand the trace before diving into details.
python scripts/fetch_trace.py <trace_id> overview
This returns metadata (status, duration, tokens, model) and summaries (request, answer preview, tool usage counts). Use this to orient yourself before going deeper.
Depending on the user's question, drill into the relevant data:
| User wants to know... | Command |
|---|---|
| What tools were called and in what order | steps [start] [count] |
| Full input/output of a specific tool call | step <N> |
| How many LLM calls and their token costs | llm-calls [start] [count] |
| What messages were sent to Claude in a specific turn | llm-call <N> |
| Just the final result | answer |
When content is large, the script automatically segments output to ~4000 characters.
If you see a [CONTINUED: ...] message at the end of output, call the command shown
in that message to read the next segment. Repeat until all content is read.
Example sequence:
python scripts/fetch_trace.py <id> step 5
# Output ends with: [CONTINUED: use 'step 5 --offset 4000' for next segment]
python scripts/fetch_trace.py <id> step 5 --offset 4000
# Output ends with: [CONTINUED: use 'step 5 --offset 8000' for next segment]
python scripts/fetch_trace.py <id> step 5 --offset 8000
# Full content now read
| Mode | Syntax | Description |
|---|---|---|
overview | fetch_trace.py <id> overview | Metadata + summary stats |
steps | fetch_trace.py <id> steps [start] [count] | Paginated step list (default: 30/page) |
step | fetch_trace.py <id> step <N> [--offset <chars>] | Single step full content |
llm-calls | fetch_trace.py <id> llm-calls [start] [count] | Paginated LLM call list |
llm-call | fetch_trace.py <id> llm-call <N> [--offset <chars>] | Single LLM call full content |
answer | fetch_trace.py <id> answer | Final answer only |
Failure diagnosis: overview → find error → steps list → examine failing step detail
Token efficiency: overview (total tokens) → llm-calls list (per-call breakdown) → identify expensive calls
Behavior understanding: overview → steps list → step details for key tool calls
Tool usage audit: overview (tool summary) → steps list filtered by tool name
Set API_BASE_URL to override the default API endpoint (http://127.0.0.1:62610).
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Review text for patterns associated with AI-generated writing, including vocabulary, structure, formatting, citations, and model-specific artifacts. The skill combines multiple signals, weighs context and mitigating evidence, and presents a cautious assessment with confidence and caveats.
Extract audio from videos or download audio from supported websites with yt-dlp, then save it as MP3, M4A, FLAC, WAV, or OPUS. The workflow can embed track metadata and cover art, and process playlists or podcast episodes in batches.
Use Biopython to process DNA, RNA, and protein sequences, read and convert common biology file formats, run alignments or BLAST searches, access NCBI records, and work with protein structures and phylogenetic trees in Python.
Turn a project description into a coordinated visual identity package. Define logo variants, color palettes, and typography, then create layouts for business cards and social media covers along with a brand specification document for consistent use.
Create original posters and static artwork by first defining a visual direction for color, shape, space, and typography. Receive a Markdown design philosophy alongside a PNG or PDF artwork that communicates primarily through visuals.
Turn a codebase into Mermaid diagrams such as architecture, ER, sequence, class, and flow diagrams. It analyzes relevant files, writes diagram source, renders SVG and PNG images, and checks the rendered result for readability and correctness.