Claude Skills by jikig-ai

Use this agent when you need to evaluate test quality using Dave Farley's 8 properties of good tests. It produces a weighted Test Quality Score (1-10 per property) with letter grades and prioritized improvement recommendations.

Classifies and routes GitHub issues by severity and domain. Assigns priority (P1/P2/P3) and routes to the correct domain via gh CLI. Use the triage skill for triaging internal code review findings into the CLI todo system. For automated daily triage via GitHub Actions, see scheduled-daily-triage.yml.

Use this agent when you need to create visual designs, wireframes, high-fidelity screens, and component designs. Handles UX audits, wireframe-to-implementation handoffs, and design-implementation sync. Use business-validator for pre-build idea validation; use cpo for cross-cutting product strategy.

The Pencil MCP server (Go binary inside `highagency.pencildev` IDE extension) couldn't be bundled in plugin.json. The previous solution (see `2026-02-14-pencil-mcp-local-binary-constraint.md`) was "degrade gracefully and link to docs." But users still had to manually install, locate the binary, and register it — with registration going stale on every extension update.

When designing the community skill with a `post` sub-command, the initial plan had it "delegate to discord-content skill." During plan review, this was identified as architecturally impossible -- skills are user-invoked entry points discovered by the plugin loader. There is no API for one skill to call another.

This skill should be used to refresh the prod SSH allowlist (Doppler ADMIN_IPS) after operator IP rotation. Detects drift, mutates Doppler with explicit ack.

This skill should be used when automating browser interactions via Vercel's agent-browser CLI. It handles web page navigation, form filling, screenshots, and data scraping using ref-based element selection.

This skill should be used when designing agent-native applications where agents are first-class citizens: architecting autonomous agents, creating MCP tools, building apps where features are agent-driven outcomes.

This skill should be used when conducting a scored agent-native architecture review. It launches 8 parallel sub-agents to audit action parity, context injection, CRUD completeness, capability discovery, and prompt-native features.

This skill should be used when writing Ruby gems following Andrew Kane's patterns. It applies when creating new gems, refactoring existing gems, or designing gem APIs with clean, minimal, production-ready code.

This skill should be used when managing Architecture Decision Records or C4 diagrams.

This skill should be used when archiving completed knowledge-base artifacts (brainstorms, plans, specs) to their archive/ subdirectories with timestamp prefixes and git history preservation.

This skill should be used when implementing features using Acceptance Test Driven Development. It guides through the RED/GREEN/REFACTOR cycle with explicit permission gates between phases.

This skill should be used before implementing features or making changes. It guides exploring user intent, approaches, and design decisions when a request has multiple valid interpretations or ambiguous requirements needing clarification.

This skill should be used when exploring requirements and approaches through collaborative dialogue before planning implementation.

This skill should be used when generating or refreshing the rolling campaign calendar. Scans knowledge-base/marketing/distribution-content/ markdown frontmatter, groups by status (overdue/upcoming/draft/published), writes a calendar view.

This skill should be used when creating changelogs for recent merges. Analyzes PR labels, issues, and descriptions to generate formatted summaries.

This skill should be used when generating a PRD from a Next.js codebase for buyer/investor/agent handoff. Walks tracked files, redacts secrets, writes structured markdown to knowledge-base/product/prd/.

This skill should be used when managing community presence across platforms (Discord, GitHub, X/Twitter, Bluesky, LinkedIn, Hacker News). It provides sub-commands for generating digests, checking health metrics, and listing enabled platforms.

This skill should be used when running competitive intelligence scans against tracked competitors, or auditing a peer skill-library repo via peer-plugin-audit. Produces structured knowledge-base reports.

This skill should be used when capturing solved problems as categorized documentation with YAML frontmatter for fast lookup. It auto-documents solutions after confirmation and builds searchable institutional knowledge.

This skill should be used when documenting a recently solved problem to compound your team's knowledge.

This skill should be used when generating full article drafts with brand-consistent voice, Eleventy frontmatter, and structured data. It requires a brand guide and existing blog infrastructure.

This skill should be used when enhancing an existing plan with parallel research agents for each section.

This skill should be used when validating the documentation build and preparing for GitHub Pages deployment. It runs the Eleventy build, validates output, checks component counts, and provides deployment instructions.

This skill should be used when deploying containerized applications to remote servers. It builds Docker images, pushes to GHCR, and deploys via SSH with health verification.

This skill should be used when writing Ruby and Rails code in DHH's 37signals style: REST purity, fat models, thin controllers, Current attributes, Hotwire patterns.

This skill should be used when creating and posting community content to Discord. Generates brand-consistent posts and posts via webhook after approval.

This skill should be used when scaffolding a Markdown-based documentation site using Eleventy. It generates a complete docs setup with base layout, data files, GitHub Pages deployment workflow, and passthrough copy configuration.

This skill should be used when draining a labeled issue backlog (deferred-scope-out, code-review, type/security) in one cleanup PR. Groups by code area and delegates to /soleur:one-shot.

This skill should be used when working with DSPy.rb, a Ruby framework for type-safe, composable LLM applications.

This skill should be used when reviewing or editing copy for adherence to Every's style guide. It provides systematic line-by-line review for grammar, punctuation, mechanics, and style compliance.

This skill should be used to record video walkthroughs of features for PR descriptions. Captures browser interactions via agent-browser CLI; optional GIF/MP4 via ffmpeg and upload via rclone.

This skill should be used when managing the file-based todo tracking system in the todos/ directory. It provides workflows for creating todos, managing status and dependencies, conducting triage, and integrating with code review.

This skill should be used to attempt an automated single-file fix for a GitHub issue. Creates a branch, fixes, tests, opens a PR, and labels for auto-merge or human review.

This skill should be used to create a runtime feature flag end-to-end across Flagsmith, server.ts, .env.example, and Doppler.

This skill should be used to flip a flag's per-role or per-org state in Flagsmith, mirroring prd flips to Doppler.

This skill should be used when auditing React/Next.js source for Hallmark-adapted anti-AI-slop patterns via a deterministic Tailwind/JSX scanner.

This skill should be used when creating distinctive, production-grade frontend interfaces. It generates creative, polished web components, pages, or applications that avoid generic AI aesthetics with high design quality.

This skill should be used when auditing diffs or plans for GDPR/CCPA/HIPAA compliance gaps.

This skill should be used when generating or editing images via the Gemini API: text-to-image, edits, multi-turn refinement, style transfer, mockups.

This skill should be used when managing Git worktrees for isolated parallel development. It handles creating, listing, switching, and cleaning up worktrees with a simple interactive interface.

This skill should be used when performing content strategy analysis, keyword research, content auditing, content gap analysis, or AI agent consumability auditing. Sub-commands: auditing, planning, applying fixes.

This skill should be used when a skill has incorrect instructions, outdated API references, or wrong parameters. Detects, diffs, applies after approval.

This skill should be used when scaffolding a redaction-gated post-incident report (PIR) after a production incident.

This skill should be used when searching the knowledge base for files matching keywords or YAML frontmatter facets (tag, category) across domains.

This skill should be used when auditing existing legal documents for compliance gaps, outdated clauses, missing disclosures, and cross-document consistency. It scans a project for legal documents and displays findings inline.

This skill should be used when generating draft legal documents for a project or company. It gathers company context interactively, invokes the legal-document-generator agent, and writes markdown output.

This skill should be used when a user input contains a Linear issue reference (e.g., SOL-39 or linear.app/.../issue/<ID>) and the downstream agent needs the screenshots embedded in the issue as visual context.

This skill should be used when merging a feature branch to main with automatic conflict resolution and cleanup.