session-eval
Use post-session to evaluate what worked, extract reusable patterns, capture lessons. Feeds knowledge base. "What did we learn", "evaluate this session".
What this skill does
# session-eval Post-session retrospective. Mines patterns + lessons + anti-patterns observed. Feeds the memory knowledge base. ## Method 1. **Span.** This session, last N hours, since last eval. 2. **Pull data.** - Conversation transcript distilled - Tools called + outcomes - Errors encountered + how resolved - Memory captures during session - Files touched 3. **Categorise observations:** - **Patterns observed** — approaches that worked → candidates for `/pattern-learn` - **Anti-patterns observed** — approaches that didn't → captured to avoid repeats - **Tool gaps** — places where existing tools fell short - **Skill gaps** — places where a skill would have helped - **Memory hits** — past memory that was useful - **Memory misses** — questions answered that should have been retrievable from memory but weren't 4. **Recommendations.** - New skills to author - New patterns to capture - Memory gaps to fill (e.g. document a decision that wasn't pinned) ## Output shape ``` # Session eval: <timestamp> ## Span <from> → <to> ## Headline <one-line summary of what happened this session> ## Patterns observed - <name> — <observed in: file:line> → recommend /pattern-learn - ... ## Anti-patterns observed - <name> — <where> → captured for future-avoidance - ... ## Tool gaps - <tool> would have helped at <moment> — recommend authoring or finding ## Skill gaps - <topic> — no skill covers this; recommend new skill ## Memory hits / misses - Hit: <query> → relevance high - Miss: <query> → answered from current code, but should be in memory ## Recommendations 1. /pattern-learn <name> 2. New skill: <name> 3. Pin this decision to memory: <decision> ``` ## Rules - **Concrete observations only.** "Things went well" is not data. - **Pattern observations need ≥ 1 occurrence in this session.** Single observation flagged for follow-up. - **Memory misses are gold.** They reveal what should be captured but isn't. - **Recommend, don't auto-execute.** User curates the knowledge base. ## Anti-patterns - Generic "improve documentation" suggestions - Patterns claimed without source citation - Listing every error as anti-pattern (some are just transient) - Long preamble before actionable observations ## When NOT to use - Mid-session — `/pause` or `/handoff` - Sessions of < 30 minutes — overkill - Daily (it's a retrospective; not every session needs one) ## Subagent dispatch - None — uses transcript + memory + git directly - Memory MCP for hit/miss analysis ## Value over native CC CC won't naturally retrospect on a session, distinguish pattern from one-off, or surface memory gaps. The retrospection discipline IS the value — feeds the knowledge flywheel.
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.