source-driven-development

Included with Lifetime

$97 forever

Ground every framework decision in official documentation. Use when you want authoritative, source-cited code for any framework or library.

General

What this skill does


# Source-Driven Development

## Overview

Verify every framework or library decision against official documentation before implementing. Flag any decision that lacks a source. This skill prevents the agent from relying on outdated patterns, hallucinated APIs, or assumptions about library behavior.

## When to Use

- Working with a framework or library you have not used recently
- When API surface area is large or frequently changing
- When the cost of a wrong assumption is high (auth, data, security)
- When documentation lookup tools are available

## Process

### Step 1: Identify Framework Decisions

Before writing code that depends on a library:
- List every API call, configuration option, or pattern you plan to use
- Note which ones you are confident about and which are assumptions

### Step 2: Verify Against Official Sources

For each decision:
- Look up the current documentation
- Confirm the API exists and behaves as expected
- Note the version the docs target
- If you cannot find a source, flag it explicitly

### Step 3: Cite Sources

In comments or design docs:
- Reference the official doc URL or section
- Note the library version
- Flag anything that could not be verified

### Step 4: Flag Unverified Decisions

Explicitly mark decisions that lack source confirmation:
- `// UNVERIFIED: assuming X based on Y pattern`
- These flags must be resolved before production use

## Source Quality Hierarchy

1. Official documentation (highest)
2. Official examples and repositories
3. Well-maintained community guides with dates
4. Stack Overflow with accepted answers and recent dates
5. AI-generated suggestions (lowest, must be verified)

## Common Rationalizations

| Rationalization | Reality |
|---|---|
| "I know this library well enough" | Libraries change between versions. Confidence is not accuracy. |
| "Looking up docs slows me down" | Debugging a wrong assumption is slower than verifying upfront. |
| "The AI already knows the right API" | AI training data has a cutoff date. APIs change. |

## Verification

- [ ] Every framework API call is verified against current docs
- [ ] Unverified decisions are explicitly flagged
- [ ] Library versions are documented
- [ ] No code depends on hallucinated or outdated API behavior

## Anti-Rationalization Table

| Excuse | Counter |
|--------|---------|
| "I know this library well enough" | Libraries change between versions. Confidence is not accuracy. |
| "Looking up docs slows me down" | Debugging a wrong assumption is slower than verifying upfront. |
| "The AI already knows the right API" | AI training data has a cutoff date. APIs change. Verify against current docs. |
| "I'll verify after the implementation works" | If the API does not exist, the implementation will not work. Verify first. |
| "Stack Overflow has the answer" | Stack Overflow answers may be outdated. Official docs are the source of truth. |

Files: 2

Size: 4.8 KB

Complexity: 9/100

Category: General

Source: https://github.com/v1truv1us/ai-eng-system/tree/main/plugins/ai-eng-core/skills/source-driven-development

Related in General

modeling-omnistudio-epc-catalog

Included

Salesforce 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).

Generalscripts

relationship-science-coach

Included

Use 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.

Generalscripts

building-sf-integrations

Included

Salesforce 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).

Generalscripts

venue-templates

Included

Access 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.

Generalscripts

let-fate-decide

Included

Draws 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.

Generalscripts

net-ops

Included

Cross-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.

Generalscripts