docs: add AGENTS.md with Cursor Cloud dev environment setup notes - #121
Draft
nieblara wants to merge 1 commit into
Draft
docs: add AGENTS.md with Cursor Cloud dev environment setup notes#121nieblara wants to merge 1 commit into
nieblara wants to merge 1 commit into
Conversation
Co-authored-by: Ramon Niebla <nieblara@users.noreply.github.com>
Skill eval results
Only suites whose source actually changed since their last recorded score were re-run. Soft-failing while we stabilise the baseline. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
AGENTS.mdwith a## Cursor Cloud specific instructionssection capturing two non-obvious gotchas for running the LLM evals: (1) the default/exec-daemon/node(v22.14.0) is too old for Promptfoo which needs>=22.22.0(use the nvm-installed Node 22), and (2)ANTHROPIC_API_KEYis required fornpm run eval.Testing
Ran the CI-equivalent checks (all pass, no secrets needed):
python3 scripts/validate_skills.py-> Validated 48 SKILL.md files successfully.python3 -m unittest discover -s tests-> Ran 8 tests, OK.python3 scripts/generate_catalog.py --check-> skills.json is up to date.npm test --prefix evals-> 90 pass / 0 fail.npm run eval:flag-command:single(with nvm Node 22) -> harness loads the skill and launches the provider, erroring only on the unsetANTHROPIC_API_KEY, confirming end-to-end wiring up to the API boundary.Notes
npm run eval) is blocked only on a missingANTHROPIC_API_KEYsecret; everything else runs locally.npm ci --legacy-peer-deps --prefix evalsandnpm ci --legacy-peer-deps --prefix tests. Python tooling is stdlib-only.