wtthornton

Persistent cross-session memory + knowledge graph for AI coding agents. Use when you need to recall prior decisions before making a non-trivial choice, save the rationale behind a decision so it survives the session, share findings across agents in a project (Hive), or record an experience event / KG triple. Talk to the deployed brain at http://127.0.0.1:8080/mcp/ via MCP tools — never via raw psycopg.

Frontend work flow combining UX playbook and standard finish pipeline. Use when the task is primarily UI/UX implementation or accessibility.

Write a structured cross-session handoff and close the TAPPS session lifecycle so the next chat can continue without a long paste. Use when ending a session, handing off to a fresh chat, or the user says hand off, save session state, or continue next time.

Frontend work flow combining UX playbook and standard finish pipeline. Use when the task is primarily UI/UX implementation or accessibility.

Write a structured cross-session handoff and close the TAPPS session lifecycle so the next chat can continue without a long paste. Use when ending a session, handing off to a fresh chat, or the user says hand off, save session state, or continue next time.

Persistent cross-session memory + knowledge graph for AI coding agents. Use when you need to recall prior decisions before making a non-trivial choice, save the rationale behind a decision so it survives the session, share findings across agents in a project (Hive), or record an experience event / KG triple. Talk to the deployed brain at http://127.0.0.1:8080/mcp/ via MCP tools — never via raw psycopg.

Frontend/UX TAPPS workflow: playbook, UI library docs, and quality gate on scored files. Use when building UI components, accessibility fixes, or client-side routing changes.

Security-focused TAPPS workflow: playbook, library docs, security scan, and CVE check. Use when implementing auth, secrets, input validation, or pre-release security passes.

Simple Mode - Natural language orchestrator for TappsCodingAgents. Coordinates multiple skills (@enhancer, @planner, @architect, @designer, @implementer, @reviewer, @tester, @debugger, @improver) based on user intent.

Simple Mode - Natural language orchestrator for TappsCodingAgents. Coordinates multiple skills (@enhancer, @planner, @architect, @designer, @implementer, @reviewer, @tester, @debugger, @improver) based on user intent.

Code reviewer providing objective quality metrics, security analysis, and actionable feedback. Use for code reviews with scoring, linting, type checking, and duplication detection.

Write production-quality code following project patterns. Use when implementing features, fixing bugs, or creating new files.

Generate and run tests for code. Use when creating unit tests, integration tests, or running test suites.

Design system and security architecture. Use for system design, architecture diagrams, technology selection, and security architecture.

Investigate and fix bugs. Use when debugging errors, analyzing stack traces, or tracing code execution. Includes Context7 error pattern knowledge and library documentation lookup.

Design API contracts, data models, and UI/UX specifications. Use for API design, data modeling, UI wireframes, and design systems.

Manage shared project memory for cross-session knowledge persistence. 23 actions: save, search, consolidate, federation, and more.

Manage shared project memory for cross-session knowledge persistence. 23 actions: save, search, consolidate, federation, and more.

Apply file operations from a TappsMCP content-return response. Used when the MCP server runs in Docker and cannot write files directly.

Change the TappsMCP enforcement intensity (high, medium, or low). Controls which quality tools are mandatory vs optional.

Run a quality gate check and report pass/fail with blocking issues.

Bootstrap TappsMCP in a project. Creates AGENTS.md, TECH_STACK.md, platform rules, hooks, agents, skills, and MCP config.

Generate a quality report across Python files in the project. Scores multiple files and presents an aggregate summary.

Research a technical question using domain experts and library docs. Combines expert consultation with docs lookup for comprehensive answers.

Ralph's per-loop execution contract — one task from fix_plan.md, the RALPH_STATUS exit block, epic-boundary QA deferral, and the dual-condition EXIT_SIGNAL gate. Invoke at the start of every Ralph loop so the response follows the contract the harness depends on.

Eval-first principles and cost-aware model routing for the Ralph loop. This skill should be used before committing budget to a MEDIUM+ task or when choosing a sub-agent: articulate the behavior to verify first, then route by task type (docs/tools → Haiku, code → Sonnet, arch → Opus, with an Opus escalation after repeated QA failures). Integrates with lib/complexity.sh and the optional sdk/ralph_sdk/cost.py::select_model.

Token-hygiene pass for the Ralph loop. This skill should be used before reading another large file or near the end of a Continue-As-New window: it drops stale file reads, prefers targeted Grep over full-file Read, and consolidates repeated file-scan patterns to stop the drift where each iteration re-reads the same file and burns prompt cache. Works with the SDK ContextManager (sdk/ralph_sdk/context.py) and the Continue-As-New trigger.

Run, monitor, and continuously improve Ralph (autonomous dev loop for Claude Code) against a Linear backlog. This skill should be used when the user says "run ralph", "start ralph", "ralph campaign", "monitor ralph", "restart ralph", "ralph against TAP-### / ENG-### / <ISSUE-ID>", or wants Ralph to chew through filed epics autonomously with the orchestrator filing follow-up Linear issues for the friction patterns it observes. Encodes proven startup, monitor-filter, kill-safety, and subagent-delegation patterns. Keeps the orchestrator's context window tiny by delegating Linear writes, commit verification, and bulk log analysis to subagents.

Research-before-coding workflow for the Ralph loop. This skill should be used before writing a new utility, helper, or abstraction: it searches the repo, installed libraries, and public registries for an existing solution first, delegating deep search to the ralph-explorer sub-agent (Haiku). Use it whenever the next task — a fix_plan item or a Linear issue — says "add/implement/build/wrap/integrate" something that sounds generic.

Pre-commit / epic-boundary quality pass for the Ralph loop. This skill should be used at an epic boundary to prune dead code, duplicated logic, unused imports, redundant comments, and speculative error handling introduced during the loop's Green phase. It removes, never adds — the diff should end smaller than it started.

Test-first discipline for the Ralph loop. This skill should be used when fixing a bug or adding behavior: write a failing test that reproduces the target behavior before implementing, then make it pass with the smallest change. Stack-agnostic (BATS for shell, pytest for the SDK, jest where present). Integrates with the ralph-tester sub-agent at epic boundaries.

Ralph's per-loop execution contract — one task from fix_plan.md, the RALPH_STATUS exit block, epic-boundary QA deferral, and the dual-condition EXIT_SIGNAL gate. Invoke at the start of every Ralph loop so the response follows the contract the harness depends on.

Manage shared project memory for cross-session knowledge persistence. 33 actions: save, search, federation, profiles, Hive, and more.

Manage shared project memory for cross-session knowledge persistence. 33 actions: save, search, federation, profiles, Hive, and more.

Execute one Ralph development loop iteration. Reads fix_plan.md, implements the first unchecked task, verifies, and commits.

Review open epics and create a Helm session plan with Meridian review

Create a new epic using Saga's 8-part structure

Generate a standardized evidence comment for a PR

Build a structured Intent Specification for a task

Run Meridian's 7-question review checklist on an epic or plan

Run the end-of-task TAPPS pipeline in one shot: validate changed files, verify the checklist, and optionally save learnings to memory. Use when you have finished implementing a task and want to validate, checklist, and save learnings in one shot.

Write a structured cross-session handoff and close the TAPPS session lifecycle so the next chat can continue without a long paste. Use when ending a session, handing off to a fresh chat, or the user says hand off, save session state, or continue next time.

Look up when to use each TappsMCP tool. Full tool reference with per-tool guidance for session start, scoring, validation, checklist, docs, experts. Use when you need guidance on which TappsMCP tool to call for a given situation.

Frontend work flow combining UX playbook and standard finish pipeline. Use when the task is primarily UI/UX implementation or accessibility.

Write a structured cross-session handoff and close the TAPPS session lifecycle so the next chat can continue without a long paste. Use when ending a session, handing off to a fresh chat, or the user says hand off, save session state, or continue next time.

Frontend work flow combining UX playbook and standard finish pipeline. Use when the task is primarily UI/UX implementation or accessibility.