minghinmatthewlam/agent-guards
19 skills
$npx skills add minghinmatthewlam/agent-guardsSkillInstalls
audit-loopLightweight read-only audit. Use host-appropriate review coverage for evidence and findings. Iterate on disagreement or low confidence. No code changes.autoreviewRun OpenClaw structured code review as the default closeout check for local changes, branches, commits, and PR work. Uses Codex by default; Claude is optional for explicit second-model review.codex-reviewRun Codex's built-in `codex review` command as a fallback or explicit compatibility check for local changes, branches, commits, and PR work.concise-reportAgent response format, respond concisely while keeping the human oriented, informed, and able to learn how the project works to keep in loop for future work. Applies to all complex agent coding work rexplain-diffCreate a focused self-contained HTML explanation of a code change, diff, branch, commit, PR, or worker implementation. Use when the user asks to understand code changes, needs an important implementatexplain-reportCreate a focused, self-contained HTML report that helps the user understand, retain, and act on important information. Use when the user requests an HTML report or visual explanation; when substantialfix-ciCheck GitHub Actions status on the current PR, wait for checks to finish, analyze failures and review comments, fix issues, and repeat until CI passes. Use when a user asks to fix failing CI, check PRios-devDevelop iOS apps with a fast simulator-first loop using the xcodebuildmcp CLI: discover project/schemes, build/test/run, capture logs, and triage failures. Use when: (1) normal iOS development, (2) siios-releaseRun a preflight-gated iOS release workflow with asc for TestFlight and App Store: auth check, ID resolution, validation, blocker triage, then controlled publish/submit commands. Use when: (1) shippingmcporterCLI access to MCP servers without loading them into agent context (saves tokens). Use when: (1) calling MCP tools on-demand, (2) want to avoid MCP context overhead.new-taskIteratively clarify requirements for a new task until reaching 90%+ confidence, then auto-invoke plan-loop.oracleUse the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.orchestratorCoordinate complex work across workers while keeping product context and final judgment in the main session. Use when the user asks to orchestrate, delegate, parallelize, supervise workers, or coordinplan-loopUse for complex or high-risk implementation work that needs plan-first execution, explicit verification design, pre-code review, and autonomous post-implementation hardening through self-test, simplifreview-loopPost-implementation review/fix loop. Use host-appropriate review coverage on your implementation, fix issues, iterate until highly confident, then commit.self-testProve the requested goal works on the highest-signal affected surface before closing. Default closing behavior for every implementation task — not just when explicitly asked. Also triggers on: 'make ssimplifyReview changed code for reuse, quality, and efficiency, then fix any issues found.skills-auditAudit agent skills in a repo against best practices — checks .claude/skills/ and .agents/skills/ for quality, structure, and coverage gaps. Use when the user wants to review, improve, or evaluate theiuse-loopDefault workflow for implementation and product goals: identify the verifiable goal, check tool/self-test access, start a real /goal continuation loop, iterate until verified, report blockers or decis