reflect
Reflect on the current session and suggest AGENTS.md improvements based on user corrections, repeated feedback, and patterns observed during interaction. Use when ending a session to encode lessons learned. Don't use for cross-session learning from git history - use `learn` instead.
What this skill does
# Reflect
Analyze the current session and suggest improvements to AGENTS.md based on patterns, feedback, and lessons learned.
**For cross-session learning from git history and handoffs, use `Skill("learn")` instead.**
## Data Sources
| Source | What to Extract |
|--------|-----------------|
| Conversation history | User corrections, repeated feedback, preferences |
| `.agents/session_ledger.md` | Key Decisions, patterns from current work (if exists) |
## Process
### Step 1: Review Conversation History
Analyze all messages in this conversation:
- User feedback and corrections
- Moments where instructions weren't followed
- Repeated issues or preferences
- Patterns that emerged during interaction
### Step 2: Check Session Ledger (if exists)
```bash
[ -f ".agents/session_ledger.md" ] && cat ".agents/session_ledger.md"
```
Extract any Key Decisions or patterns documented there.
### Step 3: Identify Improvement Opportunities
Look for:
- Gaps in current AGENTS.md that led to misunderstandings
- User preferences that should be encoded
- Patterns that could prevent future issues
- Corrections that apply broadly (not one-off incidents)
### Step 4: Generate Specific Improvements
Create actionable, specific edits. Each suggestion should:
- Be concrete (not vague principles)
- Prevent similar issues in future
- Address patterns, not one-off incidents
### Step 5: Present Suggestions
Use this format:
```markdown
## Session Reflection
### 1. [Pattern Name]
**Gap**: What's missing or unclear in AGENTS.md
**Proposed**: Specific text to add
**Reasoning**: Evidence from this session (e.g., "You corrected this 3 times")
### 2. [Pattern Name]
...
```
### Step 6: Apply Changes (if approved)
Use `AskUserQuestion`:
- "Would you like me to apply these improvements to AGENTS.md?"
If yes:
- Use Edit tool to update AGENTS.md
- Confirm changes were applied
## Guidelines
- Only suggest improvements that genuinely enhance behavior
- Keep suggestions specific and actionable
- Don't suggest redundant rules
- Focus on patterns, not one-off incidents
- Maintain existing AGENTS.md structure and style
## Example Output
```
## Session Reflection
### 1. Error Handling Preference
**Gap**: No guidance on error handling style
**Proposed**: "Always use try-catch blocks with specific error types rather than generic catches"
**Reasoning**: You corrected this pattern 3 times during our session
### 2. Import Organization
**Gap**: No import organization rules
**Proposed**: "Group imports by: 1) External packages, 2) Internal modules, 3) Types"
**Reasoning**: You consistently reorganized imports this way
Would you like me to apply these improvements to AGENTS.md?
```
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.