ghost
Use when the user wants to explore "what if we did X instead" — alternative implementations, parallel approaches, counterfactual designs. Generates scratch-branch explorations without committing to main.
What this skill does
# ghost
Parallel-universe code exploration. "What if we wrote this differently" — explored in scratch branches/files, never main.
## Method
1. **Crystallise the alternative.** State the variant in one sentence: "What if we used X instead of Y."
2. **Cost estimate.** Time to implement variant. Files affected. Risk. **State explicitly that this is exploration, not a real change.**
3. **Isolate.** Either:
- Worktree: create a temporary git worktree (`git worktree add ../ghost-<topic>`)
- Branch: `git switch -c ghost/<topic>` (less ideal — pollutes main repo state)
- Files: `<filename>.ghost.<ext>` placeholders (lightest)
4. **Implement the variant** within isolation.
5. **Compare.** Side-by-side:
- Lines changed
- Test outcome
- Performance (if measurable)
- Readability (subjective but call it)
6. **Verdict.** Worth the merge? Or scratch the ghost?
7. **Cleanup.** If scratched: remove worktree/branch/files. If kept: surface to user as a real PR proposal.
## Output shape
```
Variant: <one-sentence what-if>
Isolation: <worktree | branch | ghost files> at <path>
Comparison:
Main Ghost
LOC N M
Tests N pass M pass
Perf <metric> <metric or n/a>
Readability baseline <better|worse|equal — reasoning>
Verdict: <merge candidate | scratch>
Cleanup: <command to remove ghost>
Or merge: <command to materialise as a real PR>
```
## Rules
- **Never touch main.** All work in isolation. If you find yourself editing main files, stop.
- **Always have a cleanup path.** Ghost work that lingers becomes confusion.
- Explore one variant per ghost. Multiple variants = multiple ghosts.
- Compare honestly. Don't bias toward the variant just because it's new.
## Anti-patterns
- "Quick experiment" that ends up half-merged into main
- Ghost branches that live for weeks
- Comparing main (incomplete feature) vs ghost (complete feature) — apples to oranges
- Falling in love with the ghost; merging without honest comparison
## When NOT to use
- You're sure the variant is better — just do it via `/siftcoder:refactor` or `/siftcoder:add-feature`
- The current code is fine — ghost is for genuine uncertainty
- Deadline pressure — explorations take time
## Subagent dispatch
- `general-purpose` to implement the ghost variant
- `Plan` to design the variant before implementing
- Use isolation: `Agent` with `isolation: "worktree"` is the cleanest tool for this
## Value over native CC
CC will write the alternative if asked. CC won't naturally enforce isolation, structured comparison, or cleanup. Ghost provides the discipline so explorations don't pollute the main repo.
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.