PRPM manifests are easy to misconfigure across packages, collections, and target formats. This skill guides consistent structure, metadata, paths, tags, scripts, and validation.

Command palettes often develop keyboard, scrolling, filtering, and render-loop defects. This skill provides focused React patterns for reliable interactions and stable command registration.

Combining GitHub login and repository permissions creates identity-linking and webhook complexity. This skill provides a two-connection Nango pattern with routes, storage, reconciliation, and sync guidance.

WebSocket frame errors can hide conflicts between upgrade handlers or compression settings. This skill explains how to inspect frames, route upgrades, and verify fixes.

Incorrect rule frontmatter can prevent project instructions from loading as intended. This skill guides valid paths syntax, glob patterns, global rules, and Cursor migrations.

Claude Code hooks are easy to misconfigure or expose to unsafe input. This skill provides practical patterns for hook structure, validation, testing, and PRPM publishing.

Claude Code agent files require precise frontmatter, tool permissions, personas, and structure. This skill provides templates, validation rules, examples, and troubleshooting guidance for reliable agent creation.

Manual UI checks are slow and difficult to document. This skill guides Chrome navigation, interaction, inspection, and local screenshot capture for repeatable visual testing.

Removing or replacing a video region across frames can cause visual drift and broken motion. This skill selects a suitable RunComfy route and provides focused prompts for consistent edits.

Changing image lighting usually requires a new shoot or manual editing. This skill helps Claude, Codex, or Claude Code route still-image relighting requests through RunComfy models.

Choosing a lip-sync model and request format can be difficult across different input types. This skill selects a suitable RunComfy route and prepares the CLI invocation.

Cropped images often need a wider canvas for banners, social posts, or product layouts. This skill guides Claude, Codex, and Claude Code to outpaint images with RunComfy models while preserving the original subject.

Precise image edits need clear model routing and focused prompts. This skill helps Claude, Codex, and Claude Code call Flux 1 Kontext Pro through RunComfy with practical prompt patterns.

Creative teams need fast image drafts without losing control over prompt structure and model settings. This skill guides Claude, Codex, and Claude Code to use RunComfy Flux 2 Klein variants for rapid concepts and polished outputs.

Finding the right agent skill is hard when each registry has different coverage and ranking signals. This skill searches major registries together, compares native metrics, and highlights safety signals before a recommendation.

Local agent artifacts are difficult to review from another device or with teammates. Agentspace uploads a selected path and returns a browser link for viewing, comments, or editing.

Manual SQL injection testing is slow and inconsistent. This skill provides structured SQLMap commands, authorization checks, validation steps, and reporting guidance for approved assessments.

Web teams need a repeatable way to identify server weaknesses before attackers find them. This skill guides authorized Nikto scans and structured remediation reporting.

Security skill authors need consistent workflows, references, and validation patterns. This template provides reusable structures for security guidance, rules, and CI scanning.

Hardcoded credentials can expose systems and fail compliance checks. This skill guides Gitleaks scans, configurations, hooks, CI pipelines, triage, and remediation.