tesslio/Tessl Skill Eval

Generate reviewable Tessl scenarios and run skill evals from PR changes or comments

Trust Signals

name	description	required	default
enabled	Enable eval runs. Set to false to disable entirely.	—	true
skip-label	PR label that skips eval even when enabled. Set empty to disable.	—	skip-eval
path	Root path to search for SKILL.md files	—	.
comment	Whether to post results as a PR comment	—	true
eval-workspace	Tessl workspace name. Used to link checked-out plugins/tiles to existing Tessl projects.	—	""
eval-agent	Agent:model pair for evals (e.g. claude:claude-sonnet-4-6)	—	claude:claude-sonnet-4-6
eval-timeout	Max minutes to wait for each eval run to complete	—	45
eval-runs	Number of times to repeat each agent configuration per scenario	—	1
eval-fail-on-regression	Fail the check if any scenario scores worse with context than baseline	—	true
eval-generate-scenarios	Generate fresh scenarios before running evals	—	false
eval-scenario-count	Number of scenarios to generate per tile	—	3
eval-commit-scenarios	Commit generated scenarios back to the PR branch (requires contents: write)	—	false
test-mode	Action development only: use mock scenario generation and mock eval results without calling Tessl APIs.	—	false
cli-version	Tessl CLI version to install (for example "0.x.y", or "latest")	—	latest
tessl-token	Tessl API token for authentication. Pass via secrets.	yes	—

no outputs