oracle
Use when the user wants predictive intent inference — "what am I about to do", "what would I likely want next", "predict the next step". Mines memory patterns to forecast the next action.
What this skill does
# oracle
Predictive intent. Looks at recent activity + memory patterns + current cursor/file/branch state. Suggests the next 1-3 likely actions before the user asks.
## Method
1. **Recent state.** Read the last ~10 turns of conversation, current open file (if any), current branch, last few commits.
2. **Memory pattern mine.** `mem_search` for similar contexts in the past. What did the user do **after** being in this state historically?
3. **Generate hypotheses.** Top 3 likely next actions. For each:
- Confidence (low | med | high)
- Evidence (which past context this echoes)
- Suggested invocation
4. **Surface, don't act.** Output is a list of suggestions. Wait for user direction.
## Output shape
```
Current state:
Branch: <branch>
Recent: <last 3 actions, compressed>
Open: <file or area>
Memory: <similar past contexts found, w/ ids>
Predicted next actions:
H1 [high] <action> — <suggested invocation, e.g. "/siftcoder:fix">
Why: <evidence from past pattern>
H2 [med] <action>
Why: ...
H3 [low] <action>
Why: ...
User: pick one (1/2/3) or describe alternative.
```
## Rules
- **Predict only — never execute.** Oracle is read-only and surface-only.
- 3 hypotheses max. More dilutes signal.
- Confidence-rank by memory match strength + recency.
- If the state is novel (no memory matches), say so. Don't fabricate predictions.
## Anti-patterns
- Predicting based on heuristics without checking memory
- Acting on your own prediction without user confirm
- Predicting 7 things (analysis paralysis)
- Hedging every prediction as "low confidence" — useless
## When NOT to use
- User has stated their intent — just do it, don't predict
- Memory is empty (no prior sessions) — predictions will be guesses
- High-stakes irreversible action ahead — verify, don't predict
## Subagent dispatch
- None — oracle is a fast inference, not a delegated task
- Optional: `Explore` if state requires reading more files to ground the prediction
## Value over native CC
CC responds to what you ask. Oracle proactively names what you'd likely ask next, grounded in your own history. Useful for: "I'm about to do something but not sure what to start with" or "what's the obvious next step here".
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.