evidence-based-development
Enforce evidence-based claims through file:line citations, P1/P2/P3 prioritization proportional to evidence, and the ASSERTION/EVIDENCE/VERIFIED pattern for behavioral claims before any recommendation. Use when gathering evidence, presenting findings, or making development decisions. This skill MUST be consulted because confidence is not evidence, and ungrounded claims cause incorrect development decisions.
What this skill does
# Evidence-Based Development Foundation skill that governs how Claude gathers, presents, and acts on evidence during development. ## Iron Law **EVIDENCE BEFORE CLAIMS, ALWAYS. If you haven't read the code, you don't know what it does.** This is non-negotiable. No recommendation without a citation. No behavioral claim without verification. Confidence is not evidence. ## Show Before Decide Never propose a change without first showing the current state. Read the file, cite the line, then suggest. **Pattern**: "Here's what I found at `file.rb:42` → here's what I recommend → here's why." ## Citation Requirements Every claim about code must include a file:line reference. No exceptions. - Use `file_path:line_number` format in all findings - When reviewing diffs, cite both the file and the specific hunk - When reporting issues, show the exact code snippet as evidence ## Finding Prioritization All findings, review comments, and issues use P1/P2/P3 classification. This priority system operationalizes the organizational hard boundary **"No Ungrounded Claims"** — every finding must carry evidence (file:line citation, test output, runtime observation) proportional to its priority, and no recommendation may be made without verification against current sources. | Priority | Meaning | Action | |----------|---------|--------| | **P1** | Must fix — blocks merge, security issue, data loss risk, broken functionality | Fix before proceeding | | **P2** | Should fix — logic error, missing edge case, test gap, convention violation | Fix in this PR | | **P3** | Consider — style preference, optimization opportunity | Fix in-PR by default. Cosmetic P3 in untouched files: fix-if-bounded or document inline (default) / follow-up issue (`minimalScope` mode only). Finding triage is NEVER a valid escalation trigger — see `skills/llm-operator-principles/SKILL.md`. | ## ASSERTION/EVIDENCE/VERIFIED Pattern For any non-trivial claim about code behavior: 1. **ASSERTION**: State what you believe to be true 2. **EVIDENCE**: Show the code/output/test that supports it 3. **VERIFIED**: Confirm by running a test, reading the actual code, or checking behavior Skip this pattern for obvious facts (e.g., "this file exists"). Use it for behavioral claims, security assessments, and performance analysis. ## Finding-First Display Always display findings BEFORE recommendations or actions: 1. Show the finding table (sorted P1 → P2 → P3) 2. Show affected files with citations 3. Then propose actions 4. Then ask for decisions (if needed) Never bury findings after a long narrative. The human should see issues immediately. ## Deduplication When synthesizing findings from multiple sources (agents, reviews, tools): - Deduplicate by `file:line` — same location means same finding - Keep the highest priority version - Merge descriptions if they add different context - Note the source of each finding for traceability ## Verification Methods Every skill should include a verification step. Common patterns: | Method | When to Use | |--------|-------------| | Run tests | After code changes | | Read code / check git diff | Before behavioral claims or after edits | | Parallel Bash | Run independent checks simultaneously | | Agent(Explore) | Investigate unfamiliar code in separate context | ## Stop Conditions Stop and reassess when: - You've made 2+ claims without file:line citations in this session - You're about to recommend a change to a file you haven't read - Evidence contradicts your initial assumption — update the assumption, don't explain away the evidence - You find yourself writing "should" or "probably" about code behavior — go verify ## Graceful Degradation When evidence is unavailable: - State what you couldn't verify and why - Proceed with reduced confidence, flagging assumptions - Never fabricate evidence or cite files you haven't read ## Rationalization Prevention | Excuse | Response | |--------|----------| | "I'm pretty sure this is how it works" | Pretty sure is not evidence. Read the file. | | "I already checked earlier" | Earlier is stale. Show fresh evidence. | | "This is obvious from the pattern" | Obvious claims need obvious proof. Cite file:line. | | "Checking would take too long" | Unchecked claims waste more time when wrong. | | "The user already knows this" | The citation is for accuracy, not the audience. |
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.