Spike Morelli
Community@spikelab · San Francisco
Spike Morelli's spikelab registry provides 45 Claude Code skills spanning codebase analysis, GCP DevOps, memory systems, product management, and media processing.
Agent Skills by Spike Morelli
Showing 45 vetted skills indexed across 1 GitHub repositories.
spikelabcodebase-walkthrough
Generates interactive Markdown and HTML walkthroughs that explain a codebase step by step.
spikelabthink
Audits conversations for assumptions, biases, unchecked facts, and premature convergence.
spikelabdevops-gcp
Provides operational guidance for Google Cloud Platform DevOps tasks including Cloud Run, IAM, and Terraform.
spikelabplan
Writes self-contained implementation plans with verifiable completion criteria and explicit constraints.
spikelabdeepen
Identifies shallow modules in a codebase and proposes deepening refactors rendered as an HTML report.
spikelabanalyze-context-router
Analyzes memory retrieval logs to measure routing accuracy, token cost, and false negatives.
spikelabskill-creator
Guides creation, validation, and packaging of Claude Code skill directories.
spikelabbuildme
Orchestrates idea-to-code builds via a deterministic Python pipeline with TDD and spec generation.
spikelablearn-stack
Generates an interactive HTML framework learning guide from a codebase's actual usage.
spikelabe2e-test
Validates web applications by executing end-to-end user journeys in browsers and via HTTP APIs.
spikelabpropose-skill
Detects repeating session workflows and drafts new skill proposals for approval.
spikelabexcalidraw
Generate and iteratively refine Excalidraw diagram JSON files for architecture and flow visualization.
spikelabscreen-demo
Convert raw screen recordings into edited 1-3 minute product demo videos using ffmpeg and mlx_whisper.
spikelabhost-browser
Drive the user's real logged-in Chrome on macOS via the agent-browser CDP bridge.
spikelabtranscribe
Transcribe audio files to text using mlx-whisper on Apple Silicon macOS.
spikelabyoutube-transcript
Download YouTube transcripts via subtitles with mlx-whisper audio transcription fallback.
spikelabcosts
Reports API-equivalent costs for Claude Code usage from session transcripts and a cost ledger.
spikelablog-doctor
Analyzes multiplai runtime logs to diagnose failures and produce verified fix-recommendation reports.
spikelabhealth
Audits memory files, routing quality, and plugin configuration for completeness and staleness.
spikelabsetup
Onboards users by populating memory files from starter templates via a guided interview.
spikelabmemory-health-audit
Audits memory system health by cross-correlating retrieval logs, diary, learnings, and memory files.
spikelabrefresh-catalogs
Regenerate memory, diary, and skills catalog indexes via a dispatcher script.
spikelabbackfill
Reconstruct learnings and diary entries from existing Claude Code session transcripts.
spikelabmemory-bank
Manage shared git-based memory banks with sync, collision checks, and pull-request contributions.
Frequently Asked Questions About Spike Morelli
FAQPage SchemaWhat tasks can I accomplish using spikelab's skills?▼
The 45 skills cover codebase walkthroughs and architecture refactoring, end-to-end web testing, GCP DevOps operations, memory system audits and backfills, product discovery artifacts (JTBD, personas, PR/FAQs, strategy memos), Slack/Gmail/Fireflies access, transcription, demo video editing, and landing page copy.
Who are these skills designed for?▼
Software engineers onboarding onto codebases, DevOps operators working in Google Cloud, product managers running discovery synthesis and drafting executive memos, and power users of Claude Code who maintain persistent memory, cost ledgers, and multi-project session fleets.
How do the skills run in practice?▼
Each skill is a folder with native frontmatter declaring name, description, model (mostly opus), and trigger phrases. Claude Code loads a skill when the user's request matches its triggers; some skills disable model invocation and run deterministic pipelines, while others orchestrate interviews, research, and TDD implementation.
Are spikelab's skills open source and what do they cost?▼
The skill-creator entry references complete terms in LICENSE.txt; no per-skill pricing is stated. Runtime cost depends on Claude model usage, and the included costs skill reports API-equivalent spend per chat, skill, project, branch, or PR from session transcripts.
What prerequisites or dependencies do these skills require?▼
Dependencies vary per skill: swift-build requires macOS with xcodebuild, screen-demo uses ffmpeg, PySceneDetect, and mlx_whisper, slack needs an xoxp user token, fireflies needs a GraphQL bearer token, gmail accesses inbox only, and deep-research uses Brave, Tavily, Exa, Serper, or You.com search keys.