read-inspect-eval
Read and analyze Inspect AI evaluation log files using the Python API. Extract samples, messages, events, and metrics from .eval files.
npx skills add majiayu000/claude-skill-registry --skill read-inspect-eval-tbroadley-dotfiles-2 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Read Inspect AI Evaluation Files This skill provides instructions for reading and analyzing Inspect AI evaluation log files using the Python API. ## When to Use Use this skill when the user needs to: - Read evaluation results from `.eval` log files - Extract samples, messages, or events from evaluations - Analyze model performance metrics and scores - Convert eval data to dataframes for analysis - Debug evaluation failures or errors - Access specific samples by task or epoch ## Prerequisites Requires the `inspect_ai` package: ```bash pip install inspect-ai ``` ## Core Functions The `inspect_ai.log` module provides these primary functions: | Function | Purpose | |----------|---------| | `list_eval_logs()` | List all eval logs at a location | | `read_eval_log()` | Read an EvalLog from a file path | | `read_eval_log_sample()` | Retrieve a single EvalSample | | `read_eval_log_samples()` | Read all samples incrementally (generator) | | `read_eval_log_sample_summaries()` | Access summary-level info for all samples | ## Reading Eval Logs ### Basic Usage ```python from inspect_ai import log # List available logs logs = log.list_eval_logs("./logs") # Read a specific log eval_log = log.rea
- When to Use
- Prerequisites
- Core Functions
- Reading Eval Logs
- Basic Usage
- Read Options
- Iterating Samples
- EvalLog Structure
- EvalSample Structure
- Dataframe API
- Evaluation-Level Data
- Sample-Level Data
- Message-Level Data
- Event-Level Data
pip install inspect-ai
What does the read-inspect-eval skill do?
Read and analyze Inspect AI evaluation log files using the Python API. Extract samples, messages, events, and metrics from .eval files.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill read-inspect-eval-tbroadley-dotfiles-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.