xoai/ux-plan-tasks
tools/sage-claude-plugin/skills/ux-plan-tasks/SKILL.md
Adds UX-specific tasks to the development plan — usability testing, review checkpoints, design validation
$ install --global
skillsauthnpx skillsauth add xoai/sage ux-plan-tasksInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 25, 2026, 2:09 PM119.6s1 file scanned
SKILL.md
- name:
- ux-plan-tasks
- description:
- Adds UX-specific tasks to the development plan — usability testing, review checkpoints, design validation
- version:
- 1.0.0
- modes:
- [architect]
- category:
- planning
- activation:
- auto
- cost-tier:
- haiku
- playbook:
- ux-design
- inputs:
- [plan, ux-requirements, persona-profiles, journey-maps]
- outputs:
- [ux-tasks]
UX Plan Tasks
Adds UX-specific tasks to the development plan. Runs AFTER the core plan
skill completes. Only activates in ARCHITECT mode — BUILD mode plans are
lightweight and don't need separate UX tasks.
Mode: ARCHITECT (full)
Review the plan and add these UX tasks at appropriate points in the task sequence.
Pre-Implementation UX Tasks
Add before the first implementation task:
Usability test the design (before code):
- Task: "Conduct paper prototype / wireframe walkthrough with 3-5 users"
- Inputs: journey map, persona profiles, wireframes (if available)
- Method: Give users the core tasks from the journey map. Watch where they get stuck. Note confusion, hesitation, wrong turns.
- Output: Top 3 usability issues, prioritized by severity
- Time: 2-4 hours (including setup and debrief)
- Dependency: Blocks implementation of user-facing components
If real user testing isn't feasible, substitute:
- Expert walkthrough using the persona + journey map as evaluation lens
- Cognitive walkthrough: step through each task as the primary persona
Mid-Implementation UX Checkpoints
Insert after every user-facing component is implemented:
Heuristic spot-check:
- Task: "Review [component] against the Critical Four heuristics"
- Check: feedback, user control, error prevention, error messages
- Time: 15-30 minutes per major component
- Dependency: Must complete before next component builds on this one
Post-Implementation UX Tasks
Add after the final implementation task, before merge:
Usability test the implementation (after code):
- Task: "Conduct usability test on the implemented feature with 3-5 users"
- Method: Same core tasks as pre-implementation test
- Compare: Did we fix the issues found in the prototype test?
- New issues: Anything the real implementation reveals that the prototype didn't?
- Output: Findings report, prioritized fixes
- Time: 2-4 hours
Accessibility audit:
- Task: "Run automated accessibility checks + manual keyboard navigation test"
- Tools: axe-core, Lighthouse accessibility, manual tab-through
- Check: All interactive elements keyboard-reachable, ARIA labels present, contrast ratios met, screen reader announcements work
- Time: 1-2 hours
Task Ordering
existing plan tasks...
+ [UX] Prototype usability test (before implementation)
existing implementation tasks...
+ [UX] Heuristic spot-check on [component A]
+ [UX] Heuristic spot-check on [component B]
existing implementation tasks...
+ [UX] Implementation usability test (after implementation)
+ [UX] Accessibility audit
existing verification tasks...
References
usability-testing.md— Krug's one-morning test protocol, key metricsheuristic-evaluation.md— The 10 heuristics and Critical Four subset
Related Skills
xoai/sage-self-learning
tools
VerifiedTrustedCommunity
Captures agent mistakes, corrections, and discovered gotchas so they are not repeated. Use when: (1) a command or operation fails unexpectedly, (2) the user corrects the agent, (3) the agent discovers non-obvious behavior through debugging, (4) an API or tool behaves differently than expected, (5) a better approach is found for a recurring task. Also searches past learnings before starting tasks to avoid known pitfalls. Activate alongside the sage-memory skill — they share the same MCP backend but serve different purposes (sage-memory = codebase knowledge, sage-self-learning = agent mistakes and gotchas).
17SKILL.mdUpdated May 20, 2026
xoai/sage-ontology
development
VerifiedTrustedCommunity
Typed knowledge graph stored in sage-memory. Use when creating or querying structured entities (Person, Project, Task, Event, Document), linking related objects, checking dependencies, planning multi-step actions as graph transformations, or when skills need to share structured state. Trigger on "remember that X is Y", "what do I know about", "link X to Y", "show dependencies", "what blocks X", entity CRUD, cross-skill data access, or any request involving structured relationships between things.
17SKILL.mdUpdated May 20, 2026
xoai/sage-memory
tools
VerifiedTrustedCommunity
Integrates sage-memory into Sage workflows. Teaches the agent when to remember (store findings during work), when to recall (search memory at session start and task start), and how to learn (structured knowledge capture via sage learn). Use when the user mentions memory, remember, recall, learn, capture knowledge, onboard to codebase, or when starting any session where sage-memory MCP tools are available.
17SKILL.mdUpdated May 20, 2026
xoai/sage-self-learning
tools
VerifiedTrustedCommunity
Captures agent mistakes, corrections, and discovered gotchas so they are not repeated. Use when: (1) a command or operation fails unexpectedly, (2) the user corrects the agent, (3) the agent discovers non-obvious behavior through debugging, (4) an API or tool behaves differently than expected, (5) a better approach is found for a recurring task. Also searches past learnings before starting tasks to avoid known pitfalls. Activate alongside the sage-memory skill — they share the same MCP backend but serve different purposes (sage-memory = codebase knowledge, sage-self-learning = agent mistakes and gotchas).
17SKILL.mdUpdated May 20, 2026