fortune
Use to predict where tech debt will hurt. "Which of these will become a problem", "what's about to bite us", "tech debt forecast". Severity decay model — older debt is heavier; recently touched debt is hotter.
What this skill does
# fortune
Tech-debt forecasting. Names which pieces of debt will most likely cause pain, ranked by predicted impact × probability × time-to-pain.
## Method
1. **Inventory.** Walk the repo or named area for debt signals:
- TODO / FIXME / HACK / XXX comments
- Long functions (> 50 LOC)
- Files modified by > 5 distinct authors
- Files with low test coverage and high churn
- Deprecation warnings unhandled
- Pinned old dep versions (semver-major behind)
- Commented-out code
- Commented "remove once X" without follow-up
2. **Score each.** For every debt item:
- **Severity** (1-5): how bad if it bites
- **Probability** (1-5): how likely to bite in next 6 months — based on churn, blast radius, deprecation deadlines
- **Time-to-pain** (weeks): when it'll likely matter
3. **Decay weight.** Recent commits to the area = hotter. Untouched-for-2-years and isolated = colder.
4. **Rank.** Top 10 by `severity × probability / time_to_pain`.
5. **Fix-cost estimate** for each top item: hours/days to address.
## Output shape
```
Area: <repo or path>
Inventory: <N debt items found>
Top 10 fortune-tellings:
#1 [SxP] <severity>x<probability> ETA: <weeks> Cost: <hours/days>
<one-line description>
Where: <file:line>
Why it'll bite: <evidence>
#2 ...
...
Cold list (debt that's probably fine to leave):
- <count> items
```
## Rules
- Predictions cite evidence. "Will probably break" → "will probably break because <churn metric / dep version / deprecation deadline>".
- Don't recommend fixing all — that's not the point. The point is **prioritising**.
- Cold list matters too — naming what's safe to leave is half the value.
- Capture the report to memory; future fortune calls compare against it (did predictions hold?).
## Anti-patterns
- Listing every TODO without ranking
- Generic "could be a problem" without timing or evidence
- Recommending immediate rewrite of top-1 (often not warranted; just flag)
- Ignoring cold-list items (they need a name too)
## When NOT to use
- After a fix — debt forecast right after fixing isn't useful
- For a single file — overkill; just scan it manually
- Pre-launch crunch — fortune-telling is a strategic exercise, not tactical
## Subagent dispatch
- `Explore` for the inventory pass
- `Bash` for `git log --shortstat` / churn analysis
- Built-in `/security-review` may overlap on security-related debt — combine reports
## Value over native CC
CC will list debt if asked. CC won't naturally rank by impact × probability × time-to-pain or maintain cold-list discipline. The ranking 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.