archaeologist
Use when the user asks "why does this exist", "why is this here", "what's the history of X", or wants to understand the reasoning behind code that looks weird. Triangulates git history + memory + code reading. Read-only.
What this skill does
# archaeologist
Three sources, one answer: **git history** (what), **memory provenance** (why), **code structure** (how it's used now).
## Method
1. **Locate.** Pin down the exact symbol/file/block in question. If ambiguous, ask once.
2. **Memory pass.** `mem_why { id }` if a memory id is at hand; else `mem_search { query: "<symbol or area>", k: 8 }`. Capture decisions/discussions about this code.
3. **Git pass.** `git log --follow -p -- <path>` for the file. `git log -S "<symbol>"` for when the symbol entered the codebase. `git blame -w` for current authorship. Read the **introducing commit** message.
4. **Reference pass.** `Grep` for current callers — is this still used? By whom? Is it load-bearing or vestigial?
5. **Synthesise.** One paragraph: *Why* it exists, *when* it changed, *who* depends on it now, *whether* it's still earning its keep.
## Output shape
```
Subject: <file:line — symbol>
Origin: <introducing commit SHA, date, author, message tl;dr>
Memory: <prior decisions found, w/ summary ids>
Evolution: <key commits that reshaped it>
Now: <current callers — count + paths>
Verdict:
Earning its keep? <yes|no|inconclusive>
Still relevant? <yes|no>
Recommended action: <keep | refactor | delete | investigate further>
Captured to memory: <new summary id>
```
## Rules
- Cite commits by SHA. Cite memory by summary id. Cite code by file:line.
- Triangulate. Memory alone or git alone is not enough. The interesting cases are when memory and git **disagree**.
- Don't speculate beyond evidence. "Inconclusive" is fine.
- Don't refactor or delete during archaeology. Surface the recommendation; let the user act.
## Anti-patterns
- Reading only `git blame` (shows current author, not original reasoning)
- Reading only memory (may be stale; verify against current code)
- Speculating "probably for X" — find evidence or say inconclusive
- Drifting into a refactor
## When NOT to use
- Active bug fix — `/siftcoder:fix` (might use archaeology as a sub-step)
- "Show me what this does" → `/siftcoder:investigate` or `/siftcoder:narrator`
- "What should we build" → `/siftcoder:ideate`
## Subagent dispatch
- `Explore` for code-reference mapping
- `general-purpose` for git log scraping
- The `archaeologist` agent (if installed) for full report
## Value over native CC
CC will read code and run git. CC won't naturally cross-reference git ↔ memory ↔ current usage and surface contradictions. The triangulation IS the value — finding the "the commit message says X but memory says Y and current usage suggests Z" cases.
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.