source-driven-development
Skill6 starsChanged 8 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 Use when you want authoritative, source-cited code free from outdated patterns.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.
We split this skill into the rules it gives an agent
14 rules. 7 are common, 5 are distinctive, and 2 are very specific to this project.
7
Common
Most of the 38 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 40
Read the project's dependency file to identify exact versions:
- Distinctive: line 61
If versions are missing or ambiguous, ask the user.
- Distinctive: line 93
After fetching, extract the key patterns and note any deprecation warnings or migration guidance.
- Distinctive: line 95
When official sources conflict with each other (e.g.
- Common: line 99
Write code that matches what the documentation shows:
- Common: line 101
Use the API signatures from the docs, not from memory
- Common: line 102
If the docs show a new way to do something, use the new way
- Common: line 103
If the docs deprecate a pattern, don't use the deprecated version
- Common: line 104
If the docs don't cover something, flag it as unverified
- Distinctive: line 124
Every framework-specific pattern gets a citation.
- Very specific: line 149
Prefer deep links with anchors where possible (e.g.
- Common: line 152
If you cannot find documentation for a pattern, say so explicitly:
- Very specific: line 179
Not reading package.json / dependency files before implementing
- Common: line 185
After implementing with source-driven development:
“Common” is measured: kept by at least 6 in 10 of the 38 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.
Files
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 patternsStep 1: Detect Stack and Versions
Read the project's dependency file to identify exact versions:
package.json → Node/React/Vue/Angular/Svelte
composer.json → PHP/Symfony/Laravel
requirements.txt / pyproject.toml → Python/Django/Flask
go.mod → Go
Cargo.toml → Rust
Gemfile → Ruby/RailsState what you found explicitly:
STACK DETECTED:
- React 19.1.0 (from package.json)
- Vite 6.2.0
- Tailwind CSS 4.0.3
→ Fetching official docs for the relevant patterns.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):
| Priority | Source | Example |
| 1 | Official documentation | react.dev, docs.djangoproject.com, symfony.com/doc |
| 2 | Official blog / changelog | react.dev/blog, nextjs.org/blog |
| 3 | Web standards references | MDN, web.dev, html.spec.whatwg.org |
| 4 | Browser/runtime compatibility | caniuse.com, node.green |
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 React homepage
GOOD: Fetch react.dev/reference/react/useActionState
BAD: Search "django authentication best practices"
GOOD: Fetch docs.djangoproject.com/en/6.0/topics/auth/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 React 19 docs recommend useActionState 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:
// React 19 form handling with useActionState
// Source: https://react.dev/reference/react/useActionState#usage
const [state, formAction, isPending] = useActionState(submitOrder, initialState);In conversation:
I'm using useActionState instead of manual useState for the
form submission state. React 19 replaced the manual
isPending/setIsPending pattern with this hook.
Source: https://react.dev/blog/2024/12/05/react-19#actions
"useTransition now supports async functions [...] to handle
pending states automatically"Citation rules:
- Full URLs, not shortened
- Prefer deep links with anchors where possible (e.g.
/useActionState#usageover/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
| Rationalization | Reality |
| "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
package.json/ dependency files 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
Other versions65 projects use a version of this.
Word for word · 22
- shashankswe2020-ux/whoop-mcp★ 174100% same
- HiAi-gg/hiai-opencode★ 18100% same
- PenceZHR/stagepass★ 4100% same
- Adhamxon/claude-code-skills★ 2100% same
- cubxxw/agent-kit★ 2100% same
- huangzida/skills★ 2100% same
- Minghou-Lei/codex-skills★ 2100% same
- Puen2001/aether-os★ 2100% same
- skytiger6724/qwen-skills★ 2100% same
- FuSheng-MG/Pi-Agent-skills★ 1100% same
- ZeroTokenClaw/agents-skills★ 1100% same
11 more not listed
Edited · 26
- addyosmani/agent-skills★ 112k78% same
- rizqinrr/viserys-agent★ 55680% same
- vinvcn/addyosmani-agent-skills-zh★ 4639% same
- sampleXbro/agentsmesh★ 24100% same
- ddddjaak/ae-skills★ 475% same
- dzevs/zynk★ 457% same
- Marvellbrazil/my-agentic-skills★ 480% same
- Ghosteken/agent-harness★ 298% same
- jacksonwilliamsva/kiro-skills-library★ 223% same
- Adarshukumar/skills★ 180% same
16 more not listed
Wrote their own version · 17
- tranhieutt/software_development_department★ 71same name
- drvoss/everything-copilot-cli★ 49same name
- jmxt3/gitscape.ai★ 33same name
- galando/temper★ 18same name
- acgs-ai/ACGS★ 2same name
- bnalwalid/walidforge-skills★ 2same name
- codexskills/agent-forge★ 2same name
- GuillemRoca/agent-skills-android★ 2same name
- Aleksandr-Litvinenko/agent-skills-ru★ 1same name
- GodMaking/makecrew★ 1same name
7 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use constraint-driven-development, incremental-implementation and 10 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.
MrCipherSmithSkillconstraint-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 11 projects that use this
LLl0k0laDSkillincremental-implementation
Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.
Also in 34 projects that use this
barisariburnuSkillperformance-optimization
Complete performance optimization guide for Next.js applications including frontend, backend, database, caching, and general optimization strategies. Use when improving performance, reducing bundle size, optimizing queries, or implementing caching.
Also in 36 projects that use this
OpenAISkillverification-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 7 projects that use this
OpenAISkillfinishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work
Also in 4 projects that use this
PostHogSkillkarpathy-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
- +6 more from openai
In this repository281 other files it gives its agents.
- redis-development/AGENTS.mdAGENTS.md
- video-podcast-maker/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- imagenCN/CLAUDE.mdCLAUDE.md
- adaptSkill
- Add Admin API EndpointSkill
- agent-browserSkill
- agent-developmentSkill
- Agent DevelopmentSkill
- agent-native-designSkill
- aihotSkill
- algorithmic-artSkill
- alipay-payment-integrationSkill
- animateSkill
- api-and-interface-designSkill
- api-designerSkill
- api-design-principlesSkill
- api-designSkill
- archifySkill
- architecture-designerSkill
- architecture-patternsSkill
- arrangeSkill
- asta-skillSkill
- auditSkill
- auth-implementation-patternsSkill
- awesome-design-mdSkill
- ax-auditSkill
- backend-patternsSkill
- bangumi-framesSkill
- bolderSkill
- brand-guidelinesSkill
- brandkitSkill
- browser-skillSkill
- browser-testing-with-devtoolsSkill
- build-mcp-appSkill
- build-mcpbSkill
- build-mcp-serverSkill
- byted-seedance-video-generateSkill
- byted-seedream-image-generateSkill
- canvas-designSkill
- chart-visualizationSkill
- chrome-cdpSkill
- ci-cd-and-automationSkill
- clarifySkill
- claude-apiSkill
- claude-automation-recommenderSkill
- claude-md-improverSkill
- cli-developerSkill
- code-review-and-qualitySkill
- code-reviewerSkill
- code-simplificationSkill
- colorizeSkill
- command-developmentSkill
- computer-useSkill
- consulting-analysisSkill
- context-engineeringSkill
- cqrs-implementationSkill
- creating-mermaid-diagramsSkill
- critiqueSkill
- data-analysisSkill
- The first 60 shown.
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
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.

