docs/browser-testing-driven-ai/SKILL.md
Structured Task Orchestration (STO) workflow for AI-driven browser testing. Use this skill when performing automated UI verification, CRUD testing, or navigation audits. Ensures systematic verification with blocking gates that prevent continuation on failure.
npx skillsauth add ldsgroups225/yeko browser-testing-stosInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
A comprehensive skill for AI browser agents to perform systematic, self-correcting UI verification with the STO (Structured Task Orchestration) methodology.
Reference these guidelines when:
| Principle | Description | | ----------- | ------------- | | No Forward Progress With Red Status | Never continue if current verification fails | | Transactional Verification | CHECK → VERIFY → COMPARE → DECIDE → FIX → RE-VERIFY → PASS → NEXT | | UI ≠ Source of Truth | Always compare UI behavior against code | | Restriction Flags Are Blocking | Any permission/access error blocks progress |
| STO | Name | Priority | Purpose | | ----- | ------ | ---------- | --------- | | 1 | Authentication & Role | CRITICAL | Verify correct user context | | 2 | Sidebar Integrity | CRITICAL | Verify menu visibility | | 3 | Route Access | HIGH | Verify navigation works | | 4 | CRUD Operations | HIGH | Verify all actions work | | 5 | Protected Entities | CRITICAL | Verify security rules | | 6 | Code Comparison | MEDIUM | Verify UI matches code | | 7 | Regression Scan | MEDIUM | Verify no regressions |
| Condition | Action | | ----------- | -------- | | Verification failed | STOP | | Restriction flag detected | FIX immediately | | UI ≠ code | FIX UI | | API denied | FIX backend | | Fix applied | RE-VERIFY | | Re-verify fails | LOOP | | Re-verify passes | CONTINUE |
These conditions BLOCK progress:
Always capture screenshots:
See BROWSER_TESTING_PROMPT_GUIDE.md in the same directory for:
## Task: Verify Teachers Module
Using STO workflow:
1. STO 3: Navigate to /users/teachers
2. STO 4: Verify CRUD operations
- [ ] List loads
- [ ] Row click navigates
- [ ] Action menu works
- [ ] Create form works
- [ ] Edit form works
- [ ] Delete works
3. Take screenshots at each step
4. Report any restriction flags
testing
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
testing
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).
testing
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
testing
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).