CtrlK
BlogDocsLog inGet started
Tessl Logo

pantheon-ai/tessl-publish-public

Ensure Tessl tiles meet all requirements for public registry publishing with comprehensive validation, quality gates, and evaluation scenarios. Use when preparing skills for public Tessl release, validating tile.json configuration, creating evaluation scenarios, enforcing quality thresholds, or checking agent-agnostic compliance. Keywords: tessl, tile, publishing, public-registry, validation, quality-gates, tile.json, evaluation-scenarios, skill-publishing

94

Quality

94%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

scenario-03.mdevaluation-scenarios/

Scenario 03: Quality Threshold Enforcement

User Prompt

"The terraform-validator skill scored 95/120 on the quality audit. Can I publish it publicly?"

Expected Behavior

  1. Agent recognizes the quality score (95/120 = 79.2%)
  2. Compares score against A-grade threshold (≥108/120 = 90%)
  3. Clearly states the skill does NOT meet publication requirements
  4. Explains the skill is in C+ grade range, below A-grade minimum
  5. Suggests running remediation workflow to improve quality
  6. Points to audit results location: .context/audits/<domain>/<skill>/latest/
  7. Does NOT proceed with publication commands

Success Criteria

  • Agent correctly calculates percentage score (79.2%)
  • Agent identifies the skill is below A-grade threshold
  • Agent explicitly blocks publication with clear reasoning
  • Agent provides path to remediation-plan.md
  • Agent suggests specific next steps to improve quality
  • Agent references the ≥108/120 requirement clearly
  • No tessl skill publish command is executed

Failure Conditions

  • Agent says "close enough" and allows publication
  • Agent ignores the quality threshold requirement
  • Agent proceeds with tessl skill publish --public command
  • Agent provides workarounds to bypass quality gate
  • Agent doesn't explain WHY the threshold exists
  • Agent suggests lowering standards rather than improving skill

evaluation-scenarios

scenario-01.md

scenario-02.md

scenario-03.md

scenario-04.md

scenario-05.md

scenario-06.md

scenario-07.md

scenario-08.md

scenario-09.md

SKILL.md

tile.json