Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
thread-spawner
Spawn threads on running claude-threads orchestrator
martin-janci/claude-threads
-
nextjs-knowledge-skill
Skill providing structured Next.js knowledge: App Router patterns, RSC usage, rendering/data strategies, and modern Next.js best practices.
adilkalam/orca 2
-
debugging-first
Enforces an evidence-first approach to bug investigation. Requires agents to gather debugging evidence (console logs, network requests, application state) before examining or modifying source code.
adilkalam/orca 2
-
elements-of-style
High-impact writing rules from Strunk's Elements of Style (1918, public domain). Focused on active voice, conciseness, specificity, and positive form. Use when editing prose for clarity and force.
adilkalam/orca 2
-
ui-image-rules
Mandatory image rendering rules: dimensions, object-fit, optimization, alt text. Always applies regardless of design-dna.
adilkalam/orca 2
-
youtube-transcript
Download YouTube video transcripts when user provides a YouTube URL or asks to download/get/fetch a transcript from YouTube. Also use when user wants to transcribe or get captions/subtitles from a YouTube video.
adilkalam/orca 2
-
ios-testing-skill
Skill describing modern iOS testing patterns: Swift Testing vs XCTest, XCUITest best practices, and OS 7.0 expectations for coverage and flakiness.
adilkalam/orca 2
-
security-basics
Essential security checklist and patterns for web applications. Use when reviewing code for security issues, implementing authentication, or hardening an application. Covers OWASP top 10, input validation, and secure coding practices.
adilkalam/orca 2
-
adversarial-analysis
Six-phase framework for stress-testing proposals before commitment. Covers pre-mortem, assumption audit, edge case storm, counter-arguments, failure mode catalog, and synthesis with GO/NO-GO verdicts.
adilkalam/orca 2
-
precision-discipline
Reusable behavioral constraint layer for precision execution work. Prevents performative reasoning depth, lazy approximation, and skipped verification. Uses cognition-mcp checkpoint chain (same mechanism as /deepthink escape hatch detection). Apply when a command or workflow requires measurable precision -- STL replication, layout measurement, print settings verification, dimension-critical work.
adilkalam/orca 2
-
design-dna-skill
Skill describing how to interpret, enforce, and evolve design-dna.json across projects. Used by design-system-architect, builders, and gate agents.
adilkalam/orca 2
-
tapestry
Unified content extraction and action planning. Use when user says "tapestry <URL>", "weave <URL>", "help me plan <URL>", "extract and plan <URL>", "make this actionable <URL>", or similar phrases indicating they want to extract content and create an action plan. Automatically detects content type (YouTube video, article, PDF) and processes accordingly.
adilkalam/orca 2
-
os-dev-knowledge-skill
adilkalam/orca 2
-
print-prep
Interaction-aware print settings oracle for Bambu Studio on P2S and X1C. Encodes setting coupling relationships, filament profiles with confidence levels, calibration gating, and VFA zone math. Forces pre-flight assessment before any recommendation and distinguishes empirical data from research consensus.
adilkalam/orca 2
-
article-extractor
Extract clean article content from URLs (blog posts, articles, tutorials) and save as readable text. Use when user wants to download, extract, or save an article/blog post from a URL without ads, navigation, or clutter.
adilkalam/orca 2
-
alignment-verification
Zero-tolerance alignment verification protocol. Alignment is binary - elements are either in line or they're not. Report exact measurements, no tolerances, no "close enough."
adilkalam/orca 2
-
web-interface-guidelines
Web UI quality rules: interactions, forms, loading, animations, layout, content, performance, accessibility, design. Apply to all web UI work. Adapted from Vercel Design Guidelines.
adilkalam/orca 2
-
react-performance
React/Next.js performance patterns with wrong/right code examples. Apply when building or reviewing React components. Adapted from Vercel React Best Practices by @shuding.
adilkalam/orca 2
-
stripe-integration
Payment integration patterns for Stripe. Covers checkout sessions, subscriptions, webhooks, idempotency, and the sharp edges that cause real-money bugs. Backend-agnostic with examples for Next.js App Router and Django REST Framework.
adilkalam/orca 2
-
testing-strategy
Testing strategies and best practices for unit, integration, and end-to-end tests. Use when setting up test infrastructure, writing test cases, or deciding what to test. Covers test pyramid, mocking strategies, and coverage guidelines.
adilkalam/orca 2
-
frontend-aesthetics
Global frontend aesthetics skill that helps Claude avoid generic "AI slop" UI and make bold, intentional visual decisions while still honoring each project's design-dna, tokens, and architecture.
adilkalam/orca 2
-
pg-style-editor
Edit writing to adopt Paul Graham's exceptionally clear style for research and long-form content - concrete language, varied sentence rhythm, accessible formality, specific evidence. Use when user wants to rewrite content in PG's style or asks to "make this clearer" or "simplify research writing."
adilkalam/orca 2
-
lovable-pitfalls
Catalog of critical mistakes to avoid: re-reading context files, writing without reading, sequential tool calls, premature coding, overengineering, scope creep, and monolithic files.
adilkalam/orca 2
-
linter-loop-limits
Enforces a 3-strike rule for linter error fixes. Prevents agents from entering infinite loops on persistent lint errors by requiring escalation to the user after three failed attempts.
adilkalam/orca 2