Browse Skills

Token Dashboard opens the Token Optimizer dashboard in your browser to view context usage trends, quality scores, session history, and skill management. Use it to inspect token optimization data after a session.

Token Optimizer audits a Claude Code or Codex setup for context-window waste, then fixes it and measures the savings. Use when context feels tight.

Token Optimizer audits your OpenClaw setup for token waste, context bloat, and cost optimization opportunities. Use it to detect ghost tokens and get config fixes with dollar savings.

Better Harness reviews the outer coding-agent harness for lifecycle controls, repeated work, project feedback, agent assets, session outcomes, repair planning, durable reports, finding-bound fixes, and manual direct fixes. Invoke only via slash command to keep sessions, project, and agent assets independent.

Change Traceability Review audits how a code change traces from story/issue to spec, plan/tasks, commits/PRs, diff, tests, and risk, and reports traceability gaps. Use it for spec preparation, pre-merge review readiness, or retrospective analysis of recent commits.

Diagnose Backend Bug diagnoses bounded backend or multi-service failures by correlating evidence from issue trackers, logs, traces, and job records before repair, using the project's observability route.

Handoff prepares a bounded handoff document, recording evidence without copying private content, for use between AI agent sessions.

Harness Skill Creator bootstraps the smallest harness-oriented skill from an existing repository, workflow, or evaluation chain with evidence-backed references and validation gates.

Reproduce Frontend Bug builds a bounded, replayable browser or UI bug reproduction from GitHub Issues, Jira, Aone, or user-provided exports. Use it for browser, WebView, IDE or desktop UI defects that need evidence-preserving reproduction before diagnosis or repair.

Skill Review audits Codex, Qoder, or repo-local skills and their prompt chains for trigger quality, workflow clarity, progressive disclosure, duplicated instructions, template ownership, output readability, and validation gaps, then recommends the smallest safe edits.

Triangulate Spec Review runs multiple independent AI reviewers like Claude, Qoder, Codex, or Cursor Agent against the same architecture specs, ADRs, or design documents, normalizes P1/P2/P3 findings, and iterates only on blocking or high-risk issues.

Verify runs focused tests before the full suite to validate one bounded change. Use it to quickly check a specific change without running the entire test suite.