view-results

npx skills add majiayu000/claude-skill-registry --skill hawk-view-results-tbroadley-dotfiles-2 --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

# View Hawk Eval Results When the user wants to analyze evaluation results, use these hawk CLI commands: ## 1. List Eval Sets You can list all eval sets if the user do not know the eval set ID: ```bash hawk list eval-sets ``` Shows: eval set ID, creation date, creator. You can increase the limit of results returned by `--limit N`. ```bash hawk list eval-sets --limit 50 ``` Or you can search for a specific eval set by using `--search QUERY`. ```bash hawk list eval-sets --search pico ``` ## 2. List Evaluations With an eval set ID, you can list all evaluations in the eval-set: ```bash hawk list evals [EVAL_SET_ID] ``` Shows: task name, model, status (success/error/cancelled), and sample counts. ## 3. List Samples Or you can list individual samples and their scores: ```bash hawk list samples [EVAL_SET_ID] [--eval FILE] [--limit N] ``` ## 4. Download Transcript To get the full conversation for a specific sample: ```bash hawk transcript <UUID> ``` The transcript includes full conversation with tool calls, scores, and metadata. To get even more details, you can get the raw data by using `--raw`: ```bash hawk transcript <UUID> --raw ``` ### Batch Transcript Download You can also download a

hawk list eval-sets
hawk list eval-sets --limit 50
hawk list eval-sets --search pico
hawk list evals [EVAL_SET_ID]
hawk list samples [EVAL_SET_ID] [--eval FILE] [--limit N]
hawk transcript <UUID>
hawk transcript <UUID> --raw
Fetch all samples in an eval set
hawk transcripts <EVAL_SET_ID>
Write to individual files in a directory