deepinit
Index full codebase recursively with hierarchical AGENTS.md files
What this skill does
Target: $ARGUMENTS
## Argument Parsing
Parse the arguments for flags and path:
- `--update` or `-u`: Update mode only (skip directories without existing AGENTS.md)
- `--dry-run`: Show what would be created without writing files
- `[path]`: Target directory (defaults to current directory if not specified)
Examples:
- `/deepinit` → Initialize current directory
- `/deepinit ./src` → Initialize ./src directory
- `/deepinit --update` → Update existing AGENTS.md files only
- `/deepinit ./src --update` → Update existing AGENTS.md in ./src
## Deep Initialization Task
You are performing a **deep codebase initialization** - creating hierarchical AGENTS.md files that document every directory in the project.
### What This Does
1. **Recursively Analyzes** every directory in the codebase
2. **Creates AGENTS.md** files that describe each directory's purpose and contents
3. **Hierarchical Tagging** - lower-level files reference their parent AGENTS.md
4. **Smart Updates** - if AGENTS.md exists, compares and merges changes
### Execution Strategy
Use **parallel exploration** with the explore agent to analyze directories, then use **olympian** agents to create the AGENTS.md files.
#### Phase 1: Discovery
```
Task(subagent_type="olympus:explore", prompt="Map the directory structure of this codebase. List all directories recursively (excluding node_modules, .git, dist, build, __pycache__, .venv). Return as a tree structure.")
```
#### Phase 2: Hierarchical Generation
Start from the root and work down:
1. **Root Level First** - Create `/AGENTS.md` for the entire project
2. **First-Level Directories** - Create `src/AGENTS.md`, `lib/AGENTS.md`, etc.
3. **Deeper Levels** - Continue recursively, each referencing parent
#### Phase 3: Content Generation Per Directory
For each directory, the AGENTS.md should contain:
```markdown
<!-- Parent: ../AGENTS.md -->
# {Directory Name}
## Purpose
[What this directory contains and its role in the project]
## Key Files
- `file1.ts` - [description]
- `file2.ts` - [description]
## Subdirectories
- `subdir1/` - [brief purpose, see subdir1/AGENTS.md]
- `subdir2/` - [brief purpose, see subdir2/AGENTS.md]
## For AI Agents
[Special instructions for AI agents working in this directory]
## Dependencies
[Key dependencies or relationships with other parts of the codebase]
```
#### Phase 4: Compare and Update (if exists)
If an AGENTS.md already exists:
1. Read the existing file
2. Compare with the new analysis
3. Preserve any manual annotations (look for `<!-- MANUAL -->` tags)
4. Merge new discoveries while keeping existing documentation
5. Update outdated information
**Update Mode (`--update` flag)**:
When `--update` is specified in arguments:
- **Only process directories that already have AGENTS.md**
- Skip directories without existing documentation
- Focus on refreshing existing docs rather than creating new ones
- Use this for maintaining documentation as codebase evolves
**Dry Run Mode (`--dry-run` flag)**:
When `--dry-run` is specified:
- List all directories that would be processed
- Show which files would be created/updated
- Do NOT write any files
- Report summary of planned changes
### Parallelization Strategy
- **Batch Processing**: Process directories at the same level in parallel
- **Level Order**: Complete one level before starting the next (ensures parent references exist)
- **Use Multiple Agents**: Spawn olympian agents for parallel file creation
### Quality Checks
After generation:
- [ ] Every non-empty directory has an AGENTS.md
- [ ] Parent references are correct (`<!-- Parent: ../AGENTS.md -->`)
- [ ] File descriptions are accurate
- [ ] No broken references to subdirectories
### Begin Execution
Start now. Create a todo list tracking each directory, then systematically generate AGENTS.md files from root to leaves.Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.