Skills by risk · page 155
Highest-trust agent skills
9,826 skills rated SAFE with grade A or B, best score first. All are grade B today: grade A needs a sandboxed run we do not do for skills yet. Ties are broken by stars, so a repository with many skills can fill a page.
Cite
Cite this page
ModelsAtlas. “Highest-trust agent skills”. Retrieved 30 Oct 2026. https://modelsatlas.com/skills/trusted/page/155
davepoon/buildwithclaude
Remove a future phase from roadmap and renumber subsequent phases
davepoon/buildwithclaude
Remove a GSD workspace and clean up worktrees
davepoon/buildwithclaude
Research how to implement a phase (standalone - usually use /gsd:plan-phase instead)
davepoon/buildwithclaude
Schedule a future resume of work - e.g. '/gsd:resume-at 09:00', '/gsd:resume-at +2h', or '/gsd:resume-at 04:00 --cmd /gsd:execute-phase 9
davepoon/buildwithclaude
Resume work from previous session with full context restoration
davepoon/buildwithclaude
Request cross-AI peer review of phase plans from external AI CLIs
davepoon/buildwithclaude
Review and promote backlog items to active milestone
davepoon/buildwithclaude
Rapid codebase assessment — lightweight alternative to /gsd:map-codebase
davepoon/buildwithclaude
Retroactively verify threat mitigations for a completed phase
davepoon/buildwithclaude
Adversarial defense layer for the mortgage plugin — protects against prompt injection, system prompt extraction, PII leakage, workflow bypass, and social engineering attacks.
davepoon/buildwithclaude
Generate a session report with token usage estimates, work summary, and outcomes
davepoon/buildwithclaude
Switch model profile for GSD agents (quality/balanced/budget/inherit)
davepoon/buildwithclaude
Configure GSD workflow toggles and model profile
davepoon/buildwithclaude
Create PR, run review, and prepare for merge after verification passes
davepoon/buildwithclaude
Sketch UI/design ideas with throwaway HTML mockups, or propose what to sketch next (frontier mode)
davepoon/buildwithclaude
Package sketch design findings into a persistent project skill for future build conversations
davepoon/buildwithclaude
Trigger when you would normally reach for pytest, gh, mypy, black, or other raw repo tooling. Redirect to `sm swab`, `sm scour`, `sm buff`, `sm sail`, `sm refit`, or `sm doctor` so remediation follows the established…
davepoon/buildwithclaude
Activate for ANY startup evaluation, investment screening, or company assessment. Triggers include: "evaluate this startup", "screen this company", "should I invest in X", "is this a good investment", "what do you think…
davepoon/buildwithclaude
Socratic spec refinement — clarify WHAT a phase delivers with ambiguity scoring before discuss-phase. Produces a SPEC.md with falsifiable requirements locked before implementation decisions begin.
davepoon/buildwithclaude
Spike an idea through experiential exploration, or propose what to spike next (frontier mode)
davepoon/buildwithclaude
Package spike findings into a persistent project skill for future build conversations
davepoon/buildwithclaude
Display project statistics — phases, plans, requirements, git metrics, and timeline
davepoon/buildwithclaude
Manage persistent context threads for cross-session work
davepoon/buildwithclaude
A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw