Evaluate user inputs against skill descriptions from YAML test files.
npx skills add https://github.com/Dataslayer-AI/Marketing-skills --skill ds-eval
Please help me install this Agent Skill. Skill: ds-eval Source: https://github.com/Dataslayer-AI/Marketing-skills/tree/main/skills/ds-eval Command: npx skills add https://github.com/Dataslayer-AI/Marketing-skills --skill ds-eval
Internal development tool that tests whether skill descriptions trigger correctly for different user inputs. Reads test cases from a YAML file and evaluates each one by matching the input against all skill descriptions. Use when the user says "run triggering eval", "test skill descriptions", "check triggering accuracy", "eval skills", or after editing a skill description to verify it still triggers correctly.
Run ds-eval with a sample input to verify which skill would trigger.
High-intent search queries and answers about installing and using this skill.
To test skill trigger accuracy after updating descriptions, run a regression evaluation using a YAML test file of user inputs. The evaluation reads each skill's name and description from SKILL.md frontmatter, matching inputs against descriptions to report best matches, mismatches, or ambiguities.
Skill triggering evaluation in QA is the process of verifying whether user inputs correctly match the intended skill descriptions. It reads test inputs from a YAML file, loads skill names and descriptions from frontmatter, and reports the best-matching skill, mismatches, or ambiguous triggers.
To check for ambiguous skill matches, evaluate user inputs against all loaded skill descriptions. The tool compares each input to the frontmatter descriptions and explicitly reports any ambiguities where multiple skills might trigger, alongside the best match and mismatches.
Yes, you can use a YAML file to run regression tests on skill descriptions. The evaluation reads test cases from the YAML file, matches them against current frontmatter descriptions, and verifies that triggering remains correct after any skill description updates.
A user input triggers the wrong skill description when the input matches an unintended skill's frontmatter more closely than the target. Running a triggering evaluation identifies these mismatches and ambiguities by comparing the input against all loaded skill descriptions.
coreyjaDraft SKILL.md frontmatter and structure guidance for Claude Code skills.
LucasMatuszewskiDesign, draft, and iteratively improve Claude skills with SKILL.md frontmatter.
mkgs-databricks-demosLocate root SKILL.md files and extract YAML frontmatter metadata into YAML documents.
anthropicsReconcile general ledger and subledger data to detect differences and classify causes.
