investigate
Use when the user wants to understand a bug, behaviour, performance issue, or codebase area without making changes yet. READ-ONLY mode. Produces an evidence ledger and a hypothesis tree.
What this skill does
# investigate
Read-only diagnosis. Hypothesis-driven. Evidence-cited. Produces a written report — does NOT touch the code.
## Method
1. **Question.** State the question in one line. Without a precise question, you'll wander.
2. **Memory pass.** Has this been investigated before? If so, surface that report and ask whether to re-run or update.
3. **Hypothesis tree.** List 3-5 hypotheses, ordered by likelihood. Each gets:
- Statement
- Evidence-needed-to-confirm
- Evidence-needed-to-rule-out
4. **Evidence collection.** For each hypothesis, gather evidence in order. Stop when one is confirmed or all are ruled out.
5. **Report.** Findings + remaining unknowns + recommended next action.
## Output shape
```
Question: <one line>
Method: <brief — what was checked>
Hypotheses:
H1 [confirmed|ruled-out|inconclusive] — <statement>
Evidence: <bullets, file:line citations>
H2 [...] — ...
H3 [...] — ...
Conclusion: <one paragraph>
Next: <recommended action, OR another investigation needed>
Captured: <summary written to memory>
```
## Rules
- **Read-only. No `Edit`, no `Write`.** If you find yourself wanting to change code, stop and surface the recommendation — don't do it.
- Every hypothesis claim cites evidence (file:line, log line, command output).
- Inconclusive is a valid result. Say so.
- No "could be" or "might be" without follow-up. Either confirm or rule out, or mark as needs-more-data.
## Anti-patterns
- Investigation that drifts into a fix (separate workflows)
- Hypothesis-free wandering ("let me just look around")
- "I think" without "because <evidence>"
- One hypothesis tested → declared root cause without ruling out others
## When NOT to use
- You already know the cause and just need to fix — `/siftcoder:fix`
- You need to add a feature — `/siftcoder:add-feature`
- You want a generated story-shape explanation — `/siftcoder:narrator`
## Subagent dispatch
- `investigator` agent (read-only, hypothesis-tracking)
- `Explore` for codebase mapping
- `archaeologist` skill if the question is "why does this exist"
## Memory capture
The report itself is captured as a summary with provenance edges to the files and symbols referenced. Future "did we investigate X" queries return this.
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.