search
Use for codebase-wide search across code + memory + docs simultaneously. Different from mem_search (memory-only) and Grep (code-only). One query, three sources, deduplicated ranking.
What this skill does
# search
Unified search across code, memory, and docs. One query, three sources, ranked results.
## When this differs from native Grep / `mem_search`
- `Grep` — code only, regex, exact match
- `mem_search` (MCP) — memory only, BM25 + vector + decay
- `search` (this skill) — federates Grep + mem_search + docs grep, dedups, ranks by relevance × source-type
## Method
1. **Parse query.** Extract: keyword(s), optional file-glob filter, optional source filter (`--code`, `--memory`, `--docs`).
2. **Parallel dispatch:**
- **Code:** `Grep` over project; rank by file path × hit density
- **Memory:** `mem_search { query, k: 10 }`
- **Docs:** `Grep` over `docs/` and root markdown files
3. **Merge + rank.** RRF (reciprocal rank fusion) across the three result sets. Recency boost for memory hits.
4. **Output.** Top 10 unified hits with source label.
## Output shape
```
Query: <text>
Sources: code | memory | docs (or filtered)
Hits (ranked):
[code] src/auth/middleware.ts:42 — match line snippet
[mem] summary:142 (2026-04-12) — captured note about caching
[code] src/payment/processor.ts:18
[docs] docs/MEMORY.md:88 — describes mem_why
[mem] summary:201 (2026-04-30) — incident
...
Source mix: 4 code, 3 memory, 3 docs
```
## Rules
- **Federate, don't pick one source.** If user wanted code-only they'd `Grep`.
- **Dedupe by content fingerprint.** Same passage in code + memory = single hit.
- **Cite source kind explicitly.** Reader needs to know if it's live code, captured decision, or doc.
- **Recency-aware for memory only.** Code rank doesn't decay.
## Anti-patterns
- Returning > 10 hits (dilutes signal)
- Mixing exact + fuzzy matches without separation
- Skipping memory pass (memory is half the value)
- Treating doc hits as authoritative when code says otherwise
## When NOT to use
- Single-file search — use `Grep` directly
- Pure memory query — use `mem_search` MCP tool
- Reference lookup with known path — open the file
## Subagent dispatch
- `Grep` for code + docs
- `mem_search` MCP tool for memory
- `Explore` if results need follow-up reading
## Value over native CC
CC will Grep on request. CC won't naturally federate code + memory + docs in one query with RRF + source labels. The federation IS the value.
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.