postmortem
Error review and recovery workflow. This skill should be used when the user points out a mistake, requests a review, pastes error logs, or asks "what went wrong". Triggers on phrases like "this is wrong", "you made a mistake", "do a postmortem", "can you review this", or when stack traces/CLI errors are provided.
prompt-engineering
Prompt engineering reference and workflow for creating, refining, and reviewing high-quality prompts for AI tools, agents, and skills.
charm-stack
Build terminal UIs with Bubbletea, Bubbles, Lipgloss, and Huh. Use when creating TUI applications, interactive forms, styled terminal output, or when user mentions Bubbletea, Bubbles, Lipgloss, Huh, Charm, or TUI development.
python-script
Creates standalone Python scripts using uv with PEP 723 inline script metadata.
agent-tests
Agent-runnable e2e tests that validate workflows with real commands
ag:checkpoint
Session checkpoint — saves context, outputs summary + changelog. Three-in-one wrap-up command.
ag:changelog
Generates and updates project CHANGELOG.md from git commits, conversation decisions, and architectural changes. Auto-invoke this skill when new features are added, features are removed, or architecture changes occur.
vectorcode
Semantic code search using RAG and vector embeddings. Use when you need to find code by concept/functionality rather than exact text match, discover implementation examples, or understand where specific concepts are used across projects.
ag:backlog-backtrack
Generate BACKLOG.md from Claude Code conversation history. Summarizes recent sessions grouped by project and date. Idempotent — safe to re-run.
python
Python development with uv and PEP 723 inline dependencies
add-module
Create new demo or utility modules following CLY project patterns. Use when adding TUI demonstration modules to modules/demo/ or utility modules to modules/, following Bubbletea/Bubbles conventions with proper Cobra CLI integration.
write-skill
Create Claude Code skills with proper structure and documentation. Use when building custom skills, writing SKILL.md files, or when user asks "write a skill" or "create Claude skill".
skill-creation
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
testing
Write tests using TDD principles with integration tests as default and minimal mocking. Use when writing code, fixing bugs, or when user mentions tests, TDD, unit tests, integration tests, or testing strategy.
slack-message-formatter
This skill should be used when the user asks to parse, format, organize, or work with a message. It asks if the message is for Slack and formats using Slack's minimal markdown with natural conversational flow.
slack-chat
communicate via slack-chat channels and direct messages with users
prompt-optimizer
This skill should be used when users request help optimizing, improving, or refining their prompts or instructions for AI models. Use this skill when users provide vague, unclear, or poorly structured prompts and need assistance transforming them into clear, effective, and well-structured instructions that AI models can better understand and execute. This skill applies comprehensive prompt engineering best practices to enhance prompt quality, clarity, and effectiveness.
receiving-feedback
Use when receiving feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
writing-clearly-and-concisely
Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Makes your writing clearer, stronger, and more professional.
cooklang-formatting
Format recipes using Cooklang markup syntax. Use when creating, editing, or converting recipes to Cooklang format. Covers ingredients, equipment, timers, metadata, and file organization.
refactor
Analyse Python code for refactoring opportunities using functional programming principles, code quality checks, and manual refactoring guidance. Use when user wants to improve code quality, check for code smells, or refactor to functional style.
social-value-report
Generate the social value report from CSV inputs by detecting CSVs, anonymising them, and producing a month-by-month markdown report.
design_documents
Co-author design docs and propose section-by-section requirement edits
debug
Add traceable debug logs that can be auto-removed with a single command. Use when debugging issues - logs follow a strict format for clean removal.
scalardb-sizing-estimator
|
mmi-analyzer
>
physics-simulation
MCP-SIM（KAIST-M4）の6エージェントパイプラインを基にした物理シミュレーション自動化スキル。自然言語の要件からFEniCSシミュレーションコードを生成・実行・検証し、教育向けレポートまで出力します。線形弾性、熱伝導、流体流動、熱機械結合、圧電変形、相場破壊力学などに対応。参照: https://github.com/KAIST-M4/MCP-SIM
kc-docs
Generate intelligent Python project documentation with UML class diagrams, architecture diagrams, and code analysis. Analyzes codebase structure to recommend and create appropriate visualizations for project overview.
test-primitives
Test CAT LAB safe primitives including file locking, atomic writes, and task validation
terminal-bridge
Unified terminal bridge for AGS. Supports two distinct servers: (1) AGS PowerShell Bridge for Google Antigravity MCP command execution, and (2) VSCode Antigravity Bridge for spawning terminals inside VSCode.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
research-cache
Access and manage the persistent research cache to avoid redundant browsing
ant-worker
Distributed task executor for CATALYTIC-DPT swarm.
workspace-isolation
Enforces disciplined git workflow for agents to prevent commit bloat and ensure human approval before permanent repository changes.
commit-manager
Unified manager for commit-related operations including commit queue management, commit summary logging, and artifact escape hatch validation.
cortex-toolkit
Unified toolkit for CORTEX operations including CAS integrity verification, summary generation, and LLM packer smoke testing.
admission-control
Validate the ags admit admission control gate using deterministic fixtures.
adr-create
Create a new Architecture Decision Record with auto-numbering and template
canon-governance-check
Enforces changelog updates for significant changes to CANON/, TOOLS/, schemas, and ADRs
canon-migration
This skill handles migrations when breaking changes occur to the canon or system structure.
canonical-doc-enforcer
Enforce canonical filename and metadata standards for ALL markdown documentation across the repository.
ci-trigger-policy
Run when a policy check is required for CI triggers.
commit-ceremony
Run failsafe checks and return ceremony checklist with staged files
critic-run
Run TOOLS/governance/critic.py to verify governance compliance before making changes
intent-guard
|
invariant freeze
Verifies that all core invariants (INV-001 through INV-008) exist in CANON/INVARIANTS.md. This ensures that invariants are not removed without a major version bump, maintaining the v1.0 stability g...
master-override
Audit logging and gated access for MASTER_OVERRIDE usage.
repo-contract-alignment
Align the repository with its stated governance by scanning contract docs, extracting explicit rules, running checks, and implementing the smallest compliant fixes with enforcement.
inbox-report-writer
Use when generating INBOX ledgers, updating INBOX.md indexes, validating INBOX content hashes, or writing canonical reports to INBOX.
Page 1500 of 1542 · 77075 results
