pyramidheadshark

pyramidheadshark/claude-scaffold

Agent Claude Code

Reviews code for architectural consistency, adherence to project standards, and correctness with prioritized findings.

pyramidheadshark/claude-scaffold

Agent Claude Code

Diagnoses errors, tracebacks, and unexpected behaviour systematically. Produces root cause analysis and concrete fix.

pyramidheadshark/claude-scaffold

Agent Claude Code

Creates complete design-doc.md from raw inputs (client description, documents, partial requirements) following project template.

pyramidheadshark/claude-scaffold

Agent Claude Code

Provisions project infrastructure — writes Terraform, Packer, and Docker Compose configurations from design-doc.md.

pyramidheadshark/claude-scaffold

Agent Claude Code

Analyzes multimodal inputs (PDF, Word, Excel, images, audio, video) to extract structured requirements via Gemini Flash.

pyramidheadshark/claude-scaffold

Agent Claude Code

Generates comprehensive project status report from code, tests, git history, and dev/status.md.

pyramidheadshark/claude-scaffold

Agent Claude Code

Plans and executes refactoring to align code with Hexagonal Architecture, type safety, and test coverage standards.

pyramidheadshark/claude-scaffold

Agent Claude Code

Updates dev/status.md, backlog items, and session notes. Use for administrative record-keeping tasks.

pyramidheadshark/claude-scaffold

Agent Claude Code

Generates complete test suite skeleton (.feature files + pytest stubs) from approved design-doc.md before any implementation.

pyramidheadshark/claude-scaffold

Command Claude Code

Updates dev/status.md to reflect the current state of the project.

pyramidheadshark/claude-scaffold

Command Claude Code

Reads and displays the full INFRA.yaml manifest for this project.

pyramidheadshark/claude-scaffold

Command Claude Code

An interactive command that creates a design-doc.md file, a document describing a project's goals, inputs, users, and planned implementation.

pyramidheadshark/claude-scaffold

Command Claude Code

Switch claude-scaffold model routing mode across all registered repos.

pyramidheadshark/claude-scaffold

Command Claude Code

Initializes a new project from the claude-scaffold template.

pyramidheadshark/claude-scaffold

Command Claude Code

Runs the code-reviewer agent on the current branch or specified files.

pyramidheadshark/claude-scaffold

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, executing session-safety.js and bash-output-filter.js via node (2 commands). From pyramidheadshark/claude-scaffold.

pyramidheadshark/claude-scaffold

Hook Claude Code

Runs when a session starts, executing session-start.js via node. From pyramidheadshark/claude-scaffold.

pyramidheadshark/claude-scaffold

Hook Claude Code

Runs when you submit a prompt, before the agent sees it, executing skill-activation-prompt.js via node. From pyramidheadshark/claude-scaffold.

pyramidheadshark/claude-scaffold

Hook Claude Code

Runs after a tool call finishes for Bash, Edit and Write tool calls, executing post-tool-use-tracker.js and session-checkpoint.js via node (2 commands). From pyramidheadshark/claude-scaffold.

pyramidheadshark/claude-scaffold

Hook Claude Code

Runs when the agent finishes a response, executing python-quality-check.js via node. From pyramidheadshark/claude-scaffold.

pyramidheadshark/claude-scaffold

Settings file Claude Code

Agent settings declaring 5 hook events (PreToolUse, SessionStart, UserPromptSubmit, PostToolUse).

pyramidheadshark/claude-scaffold

Skill Claude CodeCodex

Load when working with: Anthropic SDK, anthropic package, Claude API, tool use, streaming responses, message batches, MessageCreate, @anthropic-ai/sdk.

pyramidheadshark/claude-scaffold

Skill Claude CodeCodex

Multi-role critique system for ML experiments and architecture decisions. Based on: Solo Performance Prompting (NAACL 2024), CrewAI role taxonomy, Bermingham 13-agent DA-as-gate, De Bono Six Thinking Hats (Black Hat gating).

pyramidheadshark/claude-scaffold

Skill Claude CodeCodex

Load when working with: Pandera DataFrame schemas, Great Expectations suites, data quality checks, input validation for ML pipelines, data contracts between pipeline stages.