search-memory
Search development memory using semantic understanding
What this skill does
# Search Memory (Semantic)
Search through memory episodes using Claude's semantic understanding, not just keyword matching.
## Instructions for Agent
### 1. Find All Episodes
**Get configuration path:**
```bash
Use Bash: echo $YW_CONFIG_REPO_PATH
```
If empty or not set, return error:
```
Error: YW_CONFIG_REPO_PATH not configured.
Please set in ~/.claude/settings.json:
{
"env": {
"YW_CONFIG_REPO_PATH": "C:\\Users\\username\\repos\\yoshiwatanabe-configurations" (Windows)
"YW_CONFIG_REPO_PATH": "/mnt/c/users/username/repos/yoshiwatanabe-configurations" (WSL)
}
}
```
**Find all episode files:**
Use the path from YW_CONFIG_REPO_PATH environment variable:
```
Use Glob tool with pattern: {YW_CONFIG_REPO_PATH}/domains/dev/memory/episodes/*.md
```
Examples:
- Windows: If YW_CONFIG_REPO_PATH is `C:\Users\username\repos\yoshiwatanabe-configurations`, then glob for:
`C:\Users\username\repos\yoshiwatanabe-configurations\domains\dev\memory\episodes\*.md`
- WSL/Linux: If YW_CONFIG_REPO_PATH is `/mnt/c/users/username/repos/yoshiwatanabe-configurations`, then glob for:
`/mnt/c/users/username/repos/yoshiwatanabe-configurations/domains/dev/memory/episodes/*.md`
Note: Replace "username" with your actual username. The agent will use the actual value from your YW_CONFIG_REPO_PATH environment variable.
**If Glob returns empty:**
```
Error: No episode files found.
Checked: {YW_CONFIG_REPO_PATH}/domains/dev/memory/episodes/
Directory exists but no episodes saved yet.
Use /save-memory to create your first episode.
```
Sort by filename (most recent first) and limit to 50 most recent episodes if there are many.
### 2. Read Episode Frontmatter
For each episode file:
```
Use Read tool: Read first 40 lines (YAML frontmatter + summary)
```
Extract from YAML:
- `id`: Episode ID
- `timestamp`: When created
- `machine`: Which machine
- `os`: Operating system
- `repository.name`: Repository
- `repository.branch`: Git branch
- `repository.commit`: Commit hash (show first 7 chars)
- `summary`: Episode summary
- `keywords`: Keywords list
- `context.tags`: Tags list
### 3. Semantic Analysis
**CRITICAL:** Use semantic understanding, not keyword matching!
Analyze which episodes are relevant to user's query by:
- Understanding **query intent** (what is the user really asking?)
- Considering **synonyms** and related concepts
- Looking at **context** in summary, keywords, and tags
- Weighing **recency** (recent work often more relevant)
**Examples of semantic understanding:**
- Query: "plugin development" → Match: "Claude Code extensions", "marketplace", "skills"
- Query: "authentication" → Match: "OAuth", "login flow", "security tokens", "auth"
- Query: "what did I do last week?" → Match: Recent episodes by timestamp
Don't just grep for exact words - understand meaning!
### 4. Rank Results
Select top {limit} most semantically relevant episodes.
Sort by:
1. **Relevance** to query (primary)
2. **Recency** (secondary tiebreaker)
### 5. Format Output
For each result:
```
Found {count} episodes matching "{query}":
1. {Summary first sentence} ({relative_date})
Machine: {machine} ({os})
Repository: {repo_name} ({branch})
Commit: {first_7_chars_of_commit}
{Full summary from episode}
→ Why relevant: {Explain semantic connection to query}
2. {Next episode...}
```
**Relative dates:**
- Today → "Today"
- Yesterday → "Yesterday"
- This week → "3 days ago"
- Older → "Jan 15, 2026"
**If no relevant episodes:**
```
No episodes found matching "{query}" semantically.
You have {total_count} episodes. Try:
- Broader terms: "authentication" vs "OAuth2 PKCE flow"
- Different phrasing: "API work" vs "endpoint development"
- /list-recent-repos to see recent activity
```
### 6. Explanation Quality
Always explain WHY each episode matches. Examples:
✅ Good: "Relevant because: Discusses plugin architecture and marketplace setup"
✅ Good: "Relevant because: Authentication work using OAuth, matches your query"
❌ Bad: "Relevant because: Contains keyword 'plugin'"
❌ Bad: "Relevant because: Recent"
## Advantages Over Keyword Search
✅ Understands synonyms (auth = authentication = OAuth)
✅ Contextual (knows "marketplace" relates to "plugins")
✅ Natural queries ("what did I work on?" vs keywords)
✅ Explains relevance (not just shows matches)
## Example Queries
**Broad:**
- "What did I work on this week?"
- "Show me authentication work"
**Specific:**
- "Which repo has OAuth implementation?"
- "When did I work on marketplace plugin?"
**Conceptual:**
- "Security improvements"
- "Cross-platform fixes"
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.