self-evaluating
This skill should be used when creating or editing documents, diagrams, handover docs, PEPs, or any substantial written output. Also activates when the user says "evaluate this", "run in a loop until good", "rate this out of 10", "is this 10/10", "loop until fixed", "keep improving", or asks for iterative quality improvement on any output.
What this skill does
# Self-Evaluating Output Run a quality check on documents, diagrams, and written output before presenting. Iterate when the result is not good enough. ## When to Evaluate - After drafting or significantly editing a document - After creating or modifying a diagram - When the user explicitly asks for evaluation - When the user says "loop until it's good" or similar ## Evaluation Criteria Score each dimension 1-10: | Dimension | What to check | |-----------|--------------| | **Accuracy** | Everything factually correct based on the code? No guesses stated as facts. | | **Clarity** | Someone with basic context can follow without re-reading? | | **Completeness** | Obvious gaps or missing pieces? | | **Natural voice** | Reads like a human wrote it? No line numbers, no full file paths sprinkled inline, no AI vocabulary. | For **diagrams only**, add: | Dimension | What to check | |-----------|--------------| | **Visual flow** | Clear start and end points? No spaghetti? | | **Labels** | Every arrow and connection labelled? | | **Accessibility** | Someone with no system knowledge can follow the flow? | ## Process 1. Draft the output 2. Evaluate against the criteria above 3. If any dimension scores below 7, fix those areas 4. Re-evaluate after fixes 5. Present when all dimensions hit 7+ When the user asks to "loop until 10/10" or similar, keep iterating until all scores hit 8+. State what improved between iterations. ## For Diagrams - Follow C4 framework conventions (context, container, component levels) when applicable - Group related elements visually - Avoid scattered layouts -- proximity implies relationship - Test readability: could someone unfamiliar with the system understand the flow? ## Anti-Patterns - Do not present a draft and say "let me know if you want changes" without self-evaluating first - Do not rate something 9/10 to avoid iterating -- be honest - Do not describe what you improved without actually improving it
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.