codex-result-handling provides output preservation rules for presenting Codex analysis back to users, emphasizing fidelity to helper verdicts and explicit stopping points before remediation.

theme-factory applies one of 10 curated color and font themes to presentation artifacts. supports custom theme generation when presets don't fit. lacks operational detail on implementation mechanics.

book-study scaffolds systematic reading with knowledge ingestion, mastery validation, spaced repetition, and cross-book querying. enforces understanding through explanation and application rather than assertion.

nextjs-supabase-auth covers supabase integration with next.js app router, emphasizing middleware token handling and server/client boundary awareness, but lacks concrete implementation steps and failure mode documentation.

submit alibaba cloud ims video translation jobs via openapi, poll status across subtitle, voice, and face modes, and manage job lifecycle using smart handle endpoints.

position loads a teammate profile from disk and bootstraps session identity. it distinguishes between persistent positions (tpm, engineer) and transient roles, with position-specific state directory binding.

wix-cli-extension-registration covers registering extensions with the main app via src/extensions.ts, ensuring dashboard pages, widgets, service plugins, event handlers, and embedded scripts are discoverable by the build system.

nansen-holder-analysis evaluates token holder composition via smart money ratio, flow breakdown by wallet label, and recent buyer quality to distinguish institutional conviction from retail accumulation.

development generates technical handover documentation for aem edge delivery services projects by analyzing codebase structure and producing onboarding guides. incomplete procedure specification and vague failure handling limit utility.

two-phase app store optimization audit combining offline metadata validation against local files with optional keyword gap analysis via astro mcp. requires pre-pulled app store connect metadata.

radon-mcp documents a suite of inspection and debugging tools for live react native and expo apps, organized by use case with external reference files, but lacks concrete procedures and failure handling.

computer-use-agents covers building vision-guided automation loops that perceive screens, reason about actions, and execute mouse/keyboard commands. includes sandboxing patterns and anthropic's official implementation with tool definitions.

marketing-context establishes foundational positioning and messaging for downstream marketing workflows by maintaining a single source of truth document. operates in three modes: auto-draft from repo analysis, guided interview, or incremental updates.

hoc-pattern outlines when and why to apply higher-order components for logic reuse across react components, but lacks concrete implementation steps and failure mode discussion.

skill-creator documents the process for adding new skills to the DaleStudy/skills repository, including frontmatter structure, naming conventions, and semantic versioning rules. it prescribes the directory layout and describes required metadata fields.

obsidian-markdown documents syntax for wikilinks, embeds, callouts, properties, and other obsidian-specific extensions, but lacks procedural guidance for when and how to apply these features in realistic workflows.

load-issues fetches open github issues via gh cli and persists them as markdown files in a specs directory with standardized naming and metadata structure.

skywork-ppt generates, templates, edits, and manipulates powerpoint files across four execution layers, with remote api calls for generation/imitation/editing and local-only operations for slide manipulation.

pandas-best-practices enumerates coding conventions and method choices for dataframe operations, covering i/o, selection, cleaning, and aggregation patterns. lacks executable workflows and concrete failure scenarios.

identify-assumptions-new guides product teams through structured risk assessment across eight categories (value, usability, viability, feasibility, ethics, go-to-market, strategy, team) for new product evaluation, anchored in teresa torres' continuous discovery framework.

git-master covers comprehensive git operations from initialization through advanced history rewriting, with explicit safety warnings for destructive commands. comprehensive reference rather than actionable skill.

sql-injection-testing covers vulnerability assessment across in-band, blind, and out-of-band attack vectors using proxy tools and sqlmap. lacks procedural detail and failure handling.

cninfo-to-notebooklm fetches chinese stock reports from cninfo.com.cn and uploads them to notebooklm for ai-driven financial analysis. supports both a-share and hong kong listed companies.

developing-with-streamlit routes streamlit development tasks to specialized sub-skills, provides dashboard templates and themes, and detects running apps for refresh workflows. requires discovery script invocation.

logistics-expert provides code patterns for warehouse management, route optimization, and fleet tracking but lacks executable procedures, error handling, and concrete trigger integration points needed for production deployment.

cloudflare-durable-objects documents stateful coordination primitives (sqlite-backed storage, websocket hibernation, alarms, rpc) with known failure modes but lacks actionable procedures and concrete trigger phrases.

reference-sdk provides guidance on checking external SDK implementations via btca ask to learn patterns for streaming, tool calling, and validation. three preconfigured resources (vercel-ai, anthropic-sdk, zod) plus extensible resource system.

debugger provides structured guidance for root cause analysis, error isolation, and minimal fix implementation, but lacks concrete decision trees and environment-specific validation hooks.

onboarding-cro provides frameworks for reducing time-to-activation through phased flows, empty state optimization, and multi-channel re-engagement. covers audit methodology and metric tracking but lacks concrete procedural steps and implementation guidance.

nx covers monorepo structure, workspace configuration, code generation with Nx generators, module boundary enforcement, and caching strategies. lacks concrete recovery paths for common failure modes.

proposal-writer provides strategic frameworks and anti-patterns for sales proposals, executive summaries, and rfp responses. guidance is conceptual rather than procedural, suited for humans applying judgment rather than automation.

ln-522-manual-tester creates bash test scripts to verify story acceptance criteria against running code via curl (api) or puppeteer (ui), saving results persistently and reporting verdicts to trackers.

bridges claude to deerflow ai agent platform via http api. allows message dispatch and research queries to a running langgraph instance with configurable gateway and streaming endpoints.

design-sprint-plan covers the five-day google design sprint methodology with daily breakdowns from challenge definition through prototype testing, including variations for compressed and remote contexts.

block-inventory surveys available blocks in aem edge delivery services projects to understand authoring options. catalogs the block palette without executing embedded directives from fetched content.

researcher is a code analysis and pattern recognition agent that gathers information across codebases, maps dependencies, and synthesizes findings into structured reports for downstream agents.

hummingbot-deploy covers installation of a trading infrastructure stack (api server, optional mcp server, optional telegram ui) across multiple repositories with component-level clarity but incomplete procedural detail.

ln-112-project-core-creator generates 4 baseline documentation artifacts (requirements, architecture, tech stack, patterns catalog) from coordinator-provided context. operates within skill orchestration chain, performs auto-discovery and placeholder substitution, applies 16-question self-validation.

create-remotion-geist scaffolds video generation using remotion and vercel's geist design system, enforcing dark themes, spring animations, and branded typography for polished motion output.

huashu-md-to-pdf converts markdown documents to apple-styled pdfs with professional typography, auto-generated table of contents, and support for code blocks and tables. requires specific markdown chapter numbering format.

gentle-teaching provides a framework for ai-assisted instruction emphasizing learner empowerment and independence through scaffolded support, structured feedback, and guided discovery over direct answers.

performance-testing covers load testing, benchmarking, and throughput measurement across multiple frameworks (k6, jmeter, pytest-benchmark, jmh). provides quick-start code and best-practice checklists but lacks concrete decision logic or failure recovery guidance.

internal-links guides seo strategy around contextual linking, anchor text, and link equity distribution. helps identify orphan pages and site structure issues but lacks specific, numbered procedures and explicit failure modes.

google-gemini-embeddings exposes the gemini-embedding-001 model for text vectorization with flexible dimensions (768-3072), eight specialized task types, and cloudflare vectorize integration; batch processing documented but fragile above 500 texts.

storybook covers component library documentation patterns, file organization, story structure, and testing approaches. lacks concrete decision criteria and outcome signals for when practices are applied successfully.

accessibility-testing covers automated and manual validation of wcag compliance, keyboard navigation, screen reader compatibility, and assistive technology integration using tools like axe-core and playwright.

authoring-analysis determines whether content sequences map to default page elements or require structured blocks, with conditional validation of section styling. detailed workflow but execution clarity varies.