popey/Tessl Skill Eval

Run Tessl evals against tiles with scenarios when SKILL.md files change in a PR

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
enabledEnable eval runs. Set to false to disable entirely.true
skip-labelPR label that skips eval even when enabled. Set empty to disable.skip-eval
pathRoot path to search for SKILL.md files.
commentWhether to post results as a PR commenttrue
eval-workspaceTessl workspace name. Optional when tiles have workspace set in tile.json.""
eval-agentAgent:model pair for evals (e.g. claude:claude-sonnet-4-6)claude:claude-sonnet-4-6
eval-timeoutMax minutes to wait for each eval run to complete45
eval-fail-on-regressionFail the check if any scenario scores worse with context than baselinetrue
eval-generate-scenariosGenerate fresh scenarios before running evalsfalse
eval-scenario-countNumber of scenarios to generate per tile3
eval-commit-scenariosCommit generated scenarios back to the PR branch (requires contents: write)false
tessl-tokenTessl API token for authentication. Pass via secrets.yes

no outputs