Skill UI

This skill enables investigation of shipped applications, binaries, and packages by tracing features with evidence. It supports decompilation, version comparison, and reconstruction guidance, bypassing standard source-code analysis. Requires specific analysis engines or CLI fallbacks for static and runtime analysis.

Generate a token-usage stat card from local Claude Code, Codex, Gemini CLI, and OpenCode session logs, and commit it as an SVG file to the repository. Use when you need a current usage figure for a README or a shareable summary of coding-agent activity.

Research how real apps and websites handle a screen, flow or visual style before designing. Uses UXKIN MCP tools to search iOS screens, user journeys and website design systems, compare several examples end to end, and report the shared pattern, the differences and a recommendation.

Verify a local agent API, temporary gateway tunnel, and remote sandbox callback with a tool-free task, then restore the original app connection. Use when an agent task runs in a remote sandbox that calls back to a local API through a gateway.

Runs ECC's engineering process retroactively on existing projects. Audits current state, reconstructs past decisions, and produces a four-axis gap register (thinking, coding practice, missing features, technology selection). Executes fixes forward through the plan-TDD-review pipeline. Ideal for mid-project adoption, inheriting codebases, or identifying what was missed.

Perform evidence-backed impact analysis before changing code, data, interfaces, or governance documents, and compare planned impact with actual diff after implementation. Covers call paths, data/schema, API contracts, tests, docs, ADRs, deployment, migration, and rollback. Use for cross-module or high-risk changes, database migrations, authentication, public interfaces, blast-radius questions, pre-change checks, and post-implementation alignment.

Manage stable domain terminology and separate business semantics from architecture decisions. Create CONTEXT.md for ambiguous terms or repeated explanations, and route irreversible decisions to existing Architecture Decision Records. Prevents implementation drift by clarifying language and ensuring traceability to code or business evidence.

Install and operate Everything Claude Code (ECC) on the DeepSeek Harness (DSH): native skill roots, first-party hook bridge, bare-insert patch mounting, generator usage, event-support limits, and update workflow. Use when setting up ECC on DSH, wiring hooks into a profile, or debugging missing skills/hooks.

Govern cross-module regression in large repositories with a REGRESSION.md ledger recording each module's downstream consumers and executable acceptance commands, then run affected modules and use exit codes as regression evidence.

End-to-end organization of Power BI or Analysis Services semantic models to be report-ready: table groups, display folders, Title Case naming conventions, hierarchies, sort-by columns, hiding, descriptions, format strings, perspectives, translations and security roles.

Lint ECC skills for Codex/Cursor-safe frontmatter and Claude-only substitutions before a skill PR. Ensures canonical skills are portable across Claude, Codex, and Cursor environments.

Manage a file-based epic→story→sprint development loop without requiring an external project management tool. Creates and tracks epics, breaks them into user stories, assigns them to sprints, and drives implementation story by story. Use when starting a new feature initiative or when the team has no Jira/Linear/Taiga but needs structured delivery tracking.