agentleFS
ddddjaakddddjaak/ae-skills/skills/source-driven-development/SKILL.md

source-driven-development

Skill4 starsChanged 5 months agoMITView on GitHub

Grounds every implementation decision in official documentation. Use when you want authoritative, source-cited code free from outdated patterns. Use when building with any framework or library where correctness matters.

71 other projects use a version of this, 53 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use constraint-driven-development, verification-before-completion and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MrCipherSmithSkill

    constraint-driven-development

    Use when a project needs a persistent, measurable quality bar — starting a project without documented standards, 'set up constraints', or when coverage/perf/a11y thresholds get re-debated per-PR. Produces CONSTRAINTS.md with enforceable numbers, ratchets, and a guard against silent weakening. NOT for throwaway prototypes or a one-off CI setup.

    Also in 13 projects that use this

  • OpenAISkill

    verification-before-completion

    Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

    Also in 6 projects that use this

  • ElasticSkill

    accessibility

    Accessibility guidance for Kibana. Use this skill when working with or reviewing EUI components, resolving a11y-related (@elastic/eui) ESLint issues, and ensuring proper use of ARIA attributes, focus management, keyboard interactions, and accessible naming conventions.

    Also in 3 projects that use this

  • PostHogSkill

    karpathy-guidelines

    Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria. Based on https://github.com/multica-ai/andrej-karpathy-skills.

    Also in 3 projects that use this

  • OpenAISkill

    brainstorming

    You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

    Also in 5 projects that use this

  • CloudflareSkill

    receiving-code-review

    Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

    Also in 3 projects that use this

  • +3 more from openai

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. 11 are common, 2 are distinctive, and 1 is very specific to this project.

  • 11

    Common

    Most of the 64 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the project's build files to identify exact versions and target:

    line 40
  2. Common:

    If versions are missing or ambiguous, ask the user.

    line 61
  3. Common:

    After fetching, extract the key patterns and note any deprecation warnings or migration guidance.

    line 93
  4. Common:

    When official sources conflict with each other (e.g.

    line 95
  5. Common:

    Write code that matches what the documentation shows:

    line 99
  6. Common:

    Use the API signatures from the docs, not from memory

    line 101
  7. Common:

    If the docs show a new way to do something, use the new way

    line 102
  8. Common:

    If the docs deprecate a pattern, don't use the deprecated version

    line 103
  9. Common:

    If the docs don't cover something, flag it as unverified

    line 104
  10. Common:

    Every framework-specific pattern gets a citation.

    line 124
  11. Very specific:

    Prefer deep links with anchors where possible (e.g.

    line 151
  12. Common:

    If you cannot find documentation for a pattern, say so explicitly:

    line 154
  13. Distinctive:

    Not reading build system files / Kconfig before implementing

    line 181
  14. Common:

    After implementing with source-driven development:

    line 187

“Common” is measured: kept by at least 6 in 10 of the 64 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Source-Driven Development

Overview

Every framework-specific code decision must be backed by official documentation. Don't implement from memory — verify, cite, and let the user see your sources. Training data goes stale, APIs get deprecated, best practices evolve. This skill ensures the user gets code they can trust because every pattern traces back to an authoritative source they can check.

When to Use

  • The user wants code that follows current best practices for a given framework
  • Building boilerplate, starter code, or patterns that will be copied across a project
  • The user explicitly asks for documented, verified, or "correct" implementation
  • Implementing features where the framework's recommended approach matters (forms, routing, data fetching, state management, auth)
  • Reviewing or improving code that uses framework-specific patterns
  • Any time you are about to write framework-specific code from memory

When NOT to use:

  • Correctness does not depend on a specific version (renaming variables, fixing typos, moving files)
  • Pure logic that works the same across all versions (loops, conditionals, data structures)
  • The user explicitly wants speed over verification ("just do it quickly")

The Process

DETECT ──→ FETCH ──→ IMPLEMENT ──→ CITE
  │          │           │            │
  ▼          ▼           ▼            ▼
 What       Get the    Follow the   Show your
 stack?     relevant   documented   sources
            docs       patterns

Step 1: Detect Stack and Versions

Read the project's build files to identify exact versions and target:

CMakeLists.txt / Makefile  → Compiler, RTOS, MCU SDK
Kconfig / .config           → Zephyr configuration and version
package.json                → Node/web projects (JavaScript/TypeScript ecosystem)
go.mod / Cargo.toml         → Go / Rust
Linker script (.ld)         → MCU target and memory layout

State what you found explicitly:

STACK DETECTED:
- Zephyr RTOS 3.6.0 (from west.yml)
- Arm GNU Toolchain 13.2 (from CMakeLists.txt)
- nRF Connect SDK 2.6.0
- Target: nrf52840dk_nrf52840
→ Fetching official docs for the relevant APIs.

If versions are missing or ambiguous, ask the user. Don't guess — the version determines which patterns are correct.

Step 2: Fetch Official Documentation

Fetch the specific documentation page for the feature you're implementing. Not the homepage, not the full docs — the relevant page.

Source hierarchy (in order of authority):

PrioritySourceExample
1MCU datasheet / reference manualChapter 28: SPI, Section 12.3: Clock Configuration
2Official SDK / RTOS documentationdocs.zephyrproject.org, developer.nordicsemi.com
3Arm Architecture Reference ManualArmv7-M / Armv8-M Architecture Reference Manual
4Vendor application notes / errataSTM32F4xx Errata Sheet, nRF52 Migration Guide

Not authoritative — never cite as primary sources:

  • Stack Overflow answers
  • Blog posts or tutorials (even popular ones)
  • AI-generated documentation or summaries
  • Your own training data (that is the whole point — verify it)

Be precise with what you fetch:

BAD:  Fetch the Zephyr homepage
GOOD: Fetch docs.zephyrproject.org/latest/hardware/peripherals/spi.html

BAD:  Search "STM32 UART DMA best practices"
GOOD: Fetch RM0433 Rev 7, Chapter 38: USART, Section 38.5: DMA transfers

After fetching, extract the key patterns and note any deprecation warnings or migration guidance.

When official sources conflict with each other (e.g. a migration guide contradicts the API reference), surface the discrepancy to the user and verify which pattern actually works against the detected version.

Step 3: Implement Following Documented Patterns

Write code that matches what the documentation shows:

  • Use the API signatures from the docs, not from memory
  • If the docs show a new way to do something, use the new way
  • If the docs deprecate a pattern, don't use the deprecated version
  • If the docs don't cover something, flag it as unverified

When docs conflict with existing project code:

CONFLICT DETECTED:
The existing codebase uses useState for form loading state,
but Zephyr 3.6 SPI docs recommend using the spi_config struct for this pattern.
(Source: react.dev/reference/react/useActionState)

Options:
A) Use the modern pattern (useActionState) — consistent with current docs
B) Match existing code (useState) — consistent with codebase
→ Which approach do you prefer?

Surface the conflict. Don't silently pick one.

Step 4: Cite Your Sources

Every framework-specific pattern gets a citation. The user must be able to verify every decision.

In code comments:

// I2C timeout handling per I2C-bus specification v2.1, Section 3.1.1
// Source: NXP UM10204, Section 3.1.1 "START and STOP conditions"
// SCL held low by slave for >10ms → bus reset recovery procedure
#define I2C_TIMEOUT_MS 10

In conversation:

I'm using a ring buffer for UART RX instead of a linear buffer.
Per nRF52840 Product Specification v1.7, Section 6.35.4,
the UARTE uses EasyDMA which supports linked-list scatter-gather,
making a ring buffer compatible with continuous DMA operation.

Source: infocenter.nordicsemi.com/topic/ps_nrf52840/uarte.html
"EasyDMA can read from and write to multiple buffers in RAM
through linked lists"

Citation rules:

  • Full URLs, not shortened
  • Prefer deep links with anchors where possible (e.g. /useActionState#usage over /useActionState) — anchors survive doc restructuring better than top-level pages
  • Quote the relevant passage when it supports a non-obvious decision
  • Include browser/runtime support data when recommending platform features
  • If you cannot find documentation for a pattern, say so explicitly:
UNVERIFIED: I could not find official documentation for this
pattern. This is based on training data and may be outdated.
Verify before using in production.

Honesty about what you couldn't verify is more valuable than false confidence.

Common Rationalizations

RationalizationReality
"I'm confident about this API"Confidence is not evidence. Training data contains outdated patterns that look correct but break against current versions. Verify.
"Fetching docs wastes tokens"Hallucinating an API wastes more. The user debugs for an hour, then discovers the function signature changed. One fetch prevents hours of rework.
"The docs won't have what I need"If the docs don't cover it, that's valuable information — the pattern may not be officially recommended.
"I'll just mention it might be outdated"A disclaimer doesn't help. Either verify and cite, or clearly flag it as unverified. Hedging is the worst option.
"This is a simple task, no need to check"Simple tasks with wrong patterns become templates. The user copies your deprecated form handler into ten components before discovering the modern approach exists.

Red Flags

  • Writing framework-specific code without checking the docs for that version
  • Using "I believe" or "I think" about an API instead of citing the source
  • Implementing a pattern without knowing which version it applies to
  • Citing Stack Overflow or blog posts instead of official documentation
  • Using deprecated APIs because they appear in training data
  • Not reading build system files / Kconfig before implementing
  • Delivering code without source citations for framework-specific decisions
  • Fetching an entire docs site when only one page is relevant

Verification

After implementing with source-driven development:

  • Framework and library versions were identified from the dependency file
  • Official documentation was fetched for framework-specific patterns
  • All sources are official documentation, not blog posts or training data
  • Code follows the patterns shown in the current version's documentation
  • Non-trivial decisions include source citations with full URLs
  • No deprecated APIs are used (checked against migration guides)
  • Conflicts between docs and existing code were surfaced to the user
  • Anything that could not be verified is explicitly flagged as unverified

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.