Skills Directory
Claude Skills by Smart-AI-Memory
github.com/Smart-AI-MemoryProgressive help for any topic. Repeat to go deeper: concept -> procedural -> reference.
Stage, commit, push, and create PR in one command
One-shot second-opinion review of a real diff by a DIFFERENT model (Codex or Antigravity) — advisory only, board-recorded. Triggers on: cross review, second opinion, ask another model to review, pre-merge check from codex.
Multi-pass deep code review — security, quality, and test gaps
Developer tools (commits, reviews, refactoring)
Documentation generation and explanation
Auto-diagnose and fix failing tests
Fix Receipts — outcome-first fixing: guided intake picks scope and probes, previews the contract, runs with a verified receipt. Triggers on: attune fix, fix receipts, scoped fix, fix with receipt, outcome fix, fix intake.
Help and navigation
[Retired] Use /spec instead — spec-driven development with approval loop
Development planning and architecture
Run tests on recently changed files
Release preparation and publishing
Convene the multi-LLM round table — Claude, Antigravity, and Codex deliberate a question; the user chairs promotion. Triggers on: roundtable, round table, convene the table, ask the table, what do the other models think, deliberate.
Run code simplification on a target path
Run tests affected by recent changes
Spec Ladders — goal-driven spec development: brainstorm, plan, review, and execute a gated task ladder with recorded approvals. Triggers on: spec, spec ladders, brainstorm and build, plan and execute, idea to code, build from scratch.
Test runner, generation, and coverage analysis
Authentication and provider management
Guided multi-step wizards with XML task decomposition
AI-powered analysis workflows
Developer workflow hub — routes to the right skill based on what you need. Triggers on: attune, what can attune do, what can you do, capabilities, where do I start, get started.
Author a single-source feature page — a code-verified master that projects to .help kinds + docs pages, no API credits. Triggers on: author a feature page, single-source doc, new feature master, draft docs without an api.
Predict likely bug locations from code patterns and complexity. Triggers on: predict bugs, find bugs, risky code, code risk, what might break, likely bugs, bug hotspots.
Batch API processing for 50% cost savings on non-urgent bulk analysis. Triggers on: batch, bulk process, batch API, cheap bulk, process many, overnight analysis, 50% savings.
Enumerate everything attune offers — every workflow, wizard, and tool, read live from the registries. Triggers on: catalog, list capabilities, browse, show all, what can attune do, list workflows, list wizards, what tools are there.
Progressive help for any topic. Repeat to go deeper: concept -> procedural -> reference. Triggers on: coach, learn, explain, teach me, tell me more, how does, what is, go deeper.
Code review to find quality issues, style violations, and code smells. Triggers on: review, code review, quality, lint, code smell, analyze code.
One-shot second-opinion review of a real diff by a DIFFERENT model (Codex or Antigravity) — advisory only, board-recorded. Triggers on: cross review, second opinion, ask another model to review, pre-merge check from codex.
Run every audit at once and triage the findings into act-now / needs-a-look / dismissed buckets. Triggers on: run all audits, full sweep, audit everything, what should I fix, triage findings, discovery sweep, sweep the codebase.
Generate documentation from source code — docstrings, READMEs, API references. Triggers on: generate docs, write documentation, document this, create README, API docs, doc-gen.
Sweep the docs outbox — dedupe, lint, and digest pending small docs (lessons, reports, drafts), then chair-approve via chip into ONE batched PR. Triggers on: docs outbox, outbox sweep, sweep the outbox, pending docs, outbox status, approve digest.
Form-driven Socratic discovery — batch independent decision dimensions into one multi-select-capable form instead of N button-turns. Triggers on: scope this, discovery form, ask me everything at once, multi-select question.
Auto-diagnose and fix failing tests — up to 3 attempts with re-runs. Triggers on: fix test, failing test, broken test, test error, why is this test failing, debug test.
Fix Receipts — outcome-first fixing: guided intake picks scope and probes, previews the contract, runs with a verified receipt. Triggers on: attune fix, fix receipts, scoped fix, fix with receipt, outcome fix, fix intake.
Analyze an image — screenshot, diagram, UI mockup, or chart — with Claude's vision. Triggers on: analyze this image, look at this screenshot, what's in this diagram, read this mockup, describe this picture, analyze image.
Store, retrieve, search, and manage persistent memory across sessions. Triggers on: store memory, save this, retrieve, forget, manage memory, context, pattern.
Capture and recall curated cross-session personal memory — decisions, preferences, findings by topic. Triggers on: remember this for me, capture this decision, save to personal memory, my saved topics, forget topic, personal memory.
High-level development planning — features, TDD, architecture review. Triggers on: plan, feature, architecture, design, TDD, strategy.
RAG-grounded code generation with source citations. Triggers on: grounded code, ground this, cite sources, show me with sources, how do I with attune, reference attune docs, grounded against attune docs.
Pull relevant findings stashed from past sessions — on demand. Triggers on: recall, remember, what did I learn, prior session, past findings, did I hit this before, what do we know about.
Code-level refactoring analysis and roadmap. Detects duplication and complexity. Triggers on: refactor, tech debt, simplify, clean up, modularize, DRY, restructure.
Pre-release preparation with health checks, security audit, changelog validation, version bumps, and dependency audits. Triggers on: release, publish, ship, deploy, version bump, changelog.
Convene the multi-LLM round table — Claude, Antigravity, and Codex deliberate a question; the user chairs promotion. Triggers on: roundtable, round table, convene the table, ask the table, what do the other models think, deliberate.
Scan code for security vulnerabilities including eval/exec usage, path traversal, hardcoded secrets, and injection risks. Triggers on: security, vulnerability, audit, scan, CVE, CWE, secrets, injection, eval, exec, OWASP.
Find test gaps and generate tests for uncovered code. Triggers on: generate tests, write tests, test coverage, find untested code, test gaps, smart test, what needs testing.
Spec Ladders — goal-driven spec development: brainstorm, plan, review, and execute a gated task ladder with recorded approvals. Triggers on: spec, spec ladders, brainstorm and build, plan and execute, idea to code, build from scratch.
Fact-check LLM-generated content against source-of-truth — confirm imports import, CLI flags are real, links resolve, counts match. Triggers on: verify docs, fact-check, did the model hallucinate, check generated content, are these claims real.
Run several analysis workflows together in one sweep. Triggers on: run all workflows, run multiple workflows, full analysis sweep, workflow orchestration.
List all available help topics, optionally filtered by tag. Use to browse what's in the bundled templates or the project's .help/ directory. Triggers on: list topics, what's available, browse help, show topics.