Skip to content

Dianel555/DSkills / skills/ace-tool

ace-tool

Verified

Semantic codebase search, code indexing, and prompt enhancement via standalone CLI. Use when: (1) Semantic code search with natural language queries, (2) Code indexing for remote codebase retrieval, (3) Prompt enhancement with codebase context, (4) Before grep/find/glob operations for better accuracy, (5) Complex requirements clarification, (6) Large codebase navigation. Triggers: "search context", "enhance prompt", "find code that", "index project", "clarify requirements". IMPORTANT: Always use ace-tool BEFORE grep/find/glob for semantic-level code location.

.env.example

View on GitHub
# ACE-Tool Environment Configuration

# ============================================================================
# Authentication Configuration (Priority Order)
# ============================================================================
# 1. Constructor parameters (highest priority, programmatic use only)
# 2. ~/.augment/session.json (recommended, created by `auggie login`)
# 3. AUGMENT_SESSION_AUTH environment variable (CI/CD, headless environments)
# 4. Legacy ACE_API_* variables (deprecated, backward compatibility only)

# --- New Authentication Format (Recommended) ---
# Option A: Use ~/.augment/session.json file (created by `auggie login`)
# session.json format:
# {
#   "accessToken": "your-token-here",
#   "tenantURL": "https://api.example.com/",
#   "scopes": ["email"]
# }

# Option B: Set AUGMENT_SESSION_AUTH environment variable (for CI/CD)
# AUGMENT_SESSION_AUTH='{"accessToken":"your-token","tenantURL":"https://api.example.com/"}'

# --- Legacy Authentication (Deprecated but still supported) ---
# ACE_API_URL=https://api.example.com
# ACE_API_TOKEN=your-api-token-here

# ============================================================================
# Upload Configuration
# ============================================================================

# Response read inactivity timeout in seconds (not a total request deadline)
# ACE_UPLOAD_READ_TIMEOUT_SECONDS=300

# Maximum blobs per batch (1–30)
# ACE_UPLOAD_BATCH_COUNT=30

# Maximum UTF-8 content bytes per batch (1–1048576; excludes JSON/HTTP overhead)
# ACE_UPLOAD_BATCH_BYTES=1048576

# ============================================================================
# Prompt Enhancer Configuration
# ============================================================================

# Endpoint type: new, old, claude, openai, gemini, codex
# PROMPT_ENHANCER_ENDPOINT=new

# Legacy endpoint variable (fallback if PROMPT_ENHANCER_ENDPOINT not set)
# ACE_ENHANCER_ENDPOINT=new

# Third-party LLM configuration (required for claude/openai/gemini/codex endpoints)
# PROMPT_ENHANCER_BASE_URL=https://api.anthropic.com
# PROMPT_ENHANCER_TOKEN=sk-ant-your-key-here
# PROMPT_ENHANCER_MODEL=claude-sonnet-4.6  # Optional, overrides default model

# Enable search context injection for third-party endpoints
# PROMPT_ENHANCER_INCLUDE_SEARCH_CONTEXT=1

# Reasoning effort for third-party endpoints (default: none; empty string omits the parameter)
# none/minimal/low/medium/high/xhigh/max — claude maps to thinking disabled/adaptive, gemini none->minimal
# PROMPT_ENHANCER_REASONING_EFFORT=none

# ============================================================================
# Notes
# ============================================================================
# - Legacy ACE_API_URL/ACE_API_TOKEN are deprecated but supported for backward compatibility
# - New authentication format (session.json or AUGMENT_SESSION_AUTH) is recommended
# - Use `python scripts/ace_cli.py get_config` to verify current configuration
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall