index
Build, query, inspect dependencies, and report statistics for the searchable index of SDLC artifacts in .aiwg/
Best use case
index is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
It is a strong fit for teams already working in Codex.
Build, query, inspect dependencies, and report statistics for the searchable index of SDLC artifacts in .aiwg/
Teams using index should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/index/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How index Compares
| Feature / Agent | index | Standard Approach |
|---|---|---|
| Platform Support | Codex | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Build, query, inspect dependencies, and report statistics for the searchable index of SDLC artifacts in .aiwg/
Which AI agents support this skill?
This skill is designed for Codex.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
SKILL.md Source
# Artifact Index You manage the AIWG artifact index — building or rebuilding the searchable index of all SDLC artifacts in `.aiwg/`, querying it by text, inspecting dependency graphs, and reporting index statistics. ## Triggers Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description): - "index my artifacts" → build - "find requirements about authentication" → query "authentication" - "what depends on UC-001" → deps .aiwg/requirements/UC-001.md - "how many artifacts are indexed" → stats - "refresh the index" → build --force ## Trigger Patterns Reference | Pattern | Example | Action | |---------|---------|--------| | Build index | "build the artifact index" | Run `aiwg index build` | | Force rebuild | "rebuild the index from scratch" | Run `aiwg index build --force --verbose` | | Text search | "search artifacts for authentication" | Run `aiwg index query "authentication"` | | Dependency graph | "show dependencies for the SAD" | Run `aiwg index deps .aiwg/architecture/software-architecture-doc.md` | | Statistics | "how many artifacts are indexed?" | Run `aiwg index stats` | | JSON output | "get index stats as JSON" | Run `aiwg index stats --json` | ## Behavior When triggered: 1. **Identify the subcommand**: - Is the user building, searching, inspecting dependencies, or checking stats? - Is a specific artifact path or query mentioned? - Is `--force`, `--verbose`, or `--json` appropriate? 2. **Run the appropriate command**: ```bash # Build or rebuild the index aiwg index build # Full rebuild with progress output aiwg index build --force --verbose # Semantic search across all artifacts aiwg index query "<text>" # Machine-readable search results aiwg index query "<text>" --json # Show dependency graph for an artifact aiwg index deps <artifact-path> # Machine-readable dependency graph aiwg index deps <artifact-path> --json # Show index statistics aiwg index stats # Machine-readable statistics aiwg index stats --json ``` 3. **Report the result** — surface the relevant matches, dependencies, or counts. ## Examples ### Example 1: Build the index **User**: "Build the artifact index" **Extraction**: Build subcommand, no flags **Action**: ```bash aiwg index build ``` **Response**: "Index built. Indexed 47 artifacts across 8 categories in .aiwg/. Run `aiwg index query` to search." ### Example 2: Force rebuild with progress **User**: "Rebuild the index from scratch" **Extraction**: Build subcommand, --force --verbose **Action**: ```bash aiwg index build --force --verbose ``` **Response**: "Full rebuild complete. Scanned 52 files, indexed 47 artifacts (5 skipped: working/). Categories: requirements (12), architecture (8), testing (7), security (5), deployment (4), planning (6), risks (5)." ### Example 3: Text search **User**: "Search artifacts for anything about authentication" **Extraction**: Query subcommand, text = authentication **Action**: ```bash aiwg index query "authentication" ``` **Response**: "5 artifacts match 'authentication': UC-003-user-authentication.md (requirements), SAD section 4.2 (architecture), threat-model-v1.md (security), test-plan-auth.md (testing), deployment-runbook.md (deployment)." ### Example 4: Dependency inspection **User**: "What does UC-001 depend on, and what depends on it?" **Extraction**: Deps subcommand, artifact = .aiwg/requirements/UC-001.md **Action**: ```bash aiwg index deps .aiwg/requirements/UC-001.md ``` **Response**: "UC-001 (User Registration) dependencies: none (root artifact). Dependents: UC-003-user-authentication.md, test-plan-registration.md, SAD section 3.1, deployment-runbook.md." ### Example 5: Index statistics **User**: "How many artifacts are indexed?" **Extraction**: Stats subcommand **Action**: ```bash aiwg index stats ``` **Response**: "Index contains 47 artifacts. Coverage: 90% (5 unindexed files in working/). Last built: 2026-04-01T14:22:00Z. Categories with highest artifact count: requirements (12), architecture (8), testing (7)." ## Clarification Prompts If the user's intent is ambiguous: - "Are you looking to search for existing artifacts, or rebuild the index so new artifacts are discoverable?" - "Do you want to see what an artifact depends on, or what other artifacts depend on it? (I can show both)" ## References - @$AIWG_ROOT/src/cli/handlers/subcommands.ts — Index subcommand handler - @$AIWG_ROOT/docs/cli-reference.md — CLI reference (index section) - @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/README.md — SDLC artifact structure
Related Skills
corpus-index-build
Build graph indices (by-topic, by-year, authors, citation-network) from corpus state using definitions in .aiwg/config.yaml. Replaces manual 3-agent dispatch with a single command.
build-artifact-index
Build or rebuild the SDLC artifact index for agent-navigable discovery
aiwg-orchestrate
Route structured artifact work to AIWG workflows via MCP with zero parent context cost
venv-manager
Create, manage, and validate Python virtual environments. Use for project isolation and dependency management.
pytest-runner
Execute Python tests with pytest, supporting fixtures, markers, coverage, and parallel execution. Use for Python test automation.
vitest-runner
Execute JavaScript/TypeScript tests with Vitest, supporting coverage, watch mode, and parallel execution. Use for JS/TS test automation.
eslint-checker
Run ESLint for JavaScript/TypeScript code quality and style enforcement. Use for static analysis and auto-fixing.
repo-analyzer
Analyze GitHub repositories for structure, documentation, dependencies, and contribution patterns. Use for codebase understanding and health assessment.
pr-reviewer
Review GitHub pull requests for code quality, security, and best practices. Use for automated PR feedback and approval workflows.
YouTube Acquisition
yt-dlp patterns for acquiring content from YouTube and video platforms
Quality Filtering
Accept/reject logic and quality scoring heuristics for media content
Provenance Tracking
W3C PROV-O patterns for tracking media derivation chains and production history