source-driven-development
Use when implementing or reviewing framework-specific code that should be verified against current official docs, versioned guidance, or source-cited examples…
Skill by Threat-Vector-Security
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/threat-vector-security-source-driven-development
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/source-driven-development
What's inside
- Skill name
source-driven-development- Description
- Use when implementing or reviewing framework-specific code that should be verified against current official docs, versioned guidance, or source-cited examples rather than memory.
- License
- Apache-2.0
- Instructions
- 70 lines in SKILL.md · view on GitHub
Files (4)
- SKILL.md
- THIRD_PARTY_NOTICES.md
- source-verification-checklist.md · references/
- skill.json
SKILL.md (first lines)
# Source-Driven Development ## Overview / When to Use Ground framework-specific decisions in authoritative sources. Do not rely on model memory for APIs, recommended patterns, deprecations, or migration guidance when the code depends on a specific library or version. Use this when: - a request depends on the current best practice for a framework or library - the user asks for official docs, current guidance, citations, or a documented pattern - you are writing boilerplate or patterns likely to be copied elsewhere - the repo version matters for the correctness of the implementation Do not use this for pure logic, file moves, naming changes, or other work that is stable across versions. ## Process 1. Detect the stack and exact version from the repo before making framework-specific claims. - Read `package.json`, `pyproject.toml`, `Cargo.toml`, `go.mod`, or the equivalent dependency source. - State the version you found when it affects the answer. 2. Fetch the narrow official source for the exact feature or API. - Prefer official docs, official migration guides, official changelogs, MDN, or runtime compatibility sources. - Fetch the specific page for the feature, not the whole documentation site. 3. Compare the docs with the current repo conventions before editing. - If the docs and the codebase disagree, surface the conflict instead of silently choosing one. - If the version is ambiguous, stop and clarify before writing the pattern. 4. Implement only what you can verify. - Follow the documented API shape and recommended pattern. - If the docs do not support the pattern, label it `UNVERIFIED` instead of guessing. 5. Cite the source for non-obvious framework decisions. - Include the exact URL in the response. - Prefer deep links or anchors when available. 6. Verify the real proof surface after the change. - Run the strongest relevant repo checks, not just the smallest local assertion. ## Common Rationalizations | Rationalization | Reality | |---|---| | "I know this API already." | Framework memory goes stale. One signature or lifecycle change is enough to make the implementation wrong. | | "Docs lookup is overkill for a small change." | Small framework mistakes become copy-paste templates. They are cheap to prevent and expensive to unwind later. | | "I'll just hedge and say it might be outdated." | Hedging is not verification. Either cite the official source or mark the pattern unverified. | | "The repo already does it this way, so I'll follow that." | Existing code can be outdated. Compare the repo pattern with the current official guidance before reinforcing it. | ## Red Flags - Writing framework-specific code before reading the dependency version - Citing blogs, tutorials, Stack Overflow, or memory as the primary source - Using "I think" or "I believe" for an API that could be checked - Fetching a whole docs site when only one page is needed - Delivering a version-sensitive change without a source URL - Silently ignoring a conflict between the docs and the existing codebase ## Verification - [ ] The relevant framework or library version was identified from the repo or explicitly confirmed. - [ ] The implementation was checked against a narrow official source for that feature. - [ ] Non-trivial framework decisions are accompanied by a source URL in the response. - [ ] Any unresolved or unsupported pattern is explicitly marked `UNVERIFIED`. - [ ] The real proof surface for the repo change was run after the implementation. ## Supporting References - Read [references/source-verification-checklist.md](./references/source-verification-checklist.md) when you need the source hierarchy, citation rules, or a compact version-detection checklist. ## Related Skills - Use `coding-workspace` to stay anchored to the active repo while gathering sources. - Use `web-research` when you need disciplined public-web lookup to fetch the authoritative source pages.
From Threat-Vector-Security/guardian-agent, Apache-2.0.
More from Threat-Vector-Security/guardian-agent
- 0.601score
context-engineering
Threat-Vector-Security
Use when starting a repo-grounded task, switching subsystems, or when output quality drops and the agent needs tighter project context from rules, specs…
SkillBFreshness: B★ 13Claude Code +9 - 0.601score
security-triage
Threat-Vector-Security
Use when the user is reviewing a security alert, posture change, suspicious network behavior, firewall issue, or combined monitoring output.
SkillBFreshness: B★ 13Claude Code +9 - 0.600score
systematic-debugging
Threat-Vector-Security
Use when encountering a bug, failing test, broken integration, or unexpected behavior, before proposing fixes.
SkillBFreshness: B★ 13Claude Code +9 - 0.598score
mcp-builder
Threat-Vector-Security
Guide for building high-quality MCP (Model Context Protocol) servers and tool suites.
SkillBFreshness: B★ 13Claude Code +9 - 0.598score
skill-creator
Threat-Vector-Security
Guide for creating new skills, improving existing skills, and evaluating skill quality.
SkillBFreshness: B★ 13Claude Code +9 - 0.596score
receiving-code-review
Threat-Vector-Security
Use when addressing code review or QA feedback, especially when the feedback is unclear, broad, or technically questionable.
SkillBFreshness: B★ 13Claude Code +9 - 0.596score
deep-research
Threat-Vector-Security
Use when the task needs investigation first, especially to compare code paths, trace behavior, or synthesize findings before implementation.
SkillBFreshness: B★ 13Claude Code +9 - 0.596score
code-review
Threat-Vector-Security
Use when reviewing a diff, PR, or patch for bugs, regressions, missing tests, architecture risk, security risk, or reviewability concerns before merge.
SkillBFreshness: B★ 13Claude Code +9 - 0.596score
coding-workspace
Threat-Vector-Security
Use when the request is about a repo, codebase, implementation, bugfix, or backend-owned coding session that should stay anchored to the active workspace.
SkillBFreshness: B★ 13Claude Code +9 - 0.571score
verification-before-completion
Threat-Vector-Security
Use when about to claim work is complete, fixed, or passing, or before committing or handing off results.
SkillBFreshness: B★ 13Claude Code +9 - 0.571score
coding-backend-orchestration
Threat-Vector-Security
Use when the user explicitly asks Guardian to launch or check an external coding assistant such as Codex, Claude Code, Gemini CLI, or Aider.
SkillBFreshness: B★ 13Claude Code +9 - 0.570score
test-driven-development
Threat-Vector-Security
Use when implementing or changing code behavior, before writing production code.
SkillBFreshness: B★ 13Claude Code +9
Signals
- Stars
- 13
- Forks
- 3
- Open issues
- 0
- Last commit (this folder)
- Apr 13, 2026 (6 months ago)
- Last release
- Sep 9, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Threat-Vector-Security
- 0.601score
context-engineering
Threat-Vector-Security
Use when starting a repo-grounded task, switching subsystems, or when output quality drops and the agent needs tighter project context from rules, specs…
SkillBFreshness: B★ 13Claude Code +9 - 0.601score
security-triage
Threat-Vector-Security
Use when the user is reviewing a security alert, posture change, suspicious network behavior, firewall issue, or combined monitoring output.
SkillBFreshness: B★ 13Claude Code +9 - 0.600score
systematic-debugging
Threat-Vector-Security
Use when encountering a bug, failing test, broken integration, or unexpected behavior, before proposing fixes.
SkillBFreshness: B★ 13Claude Code +9 - 0.598score
mcp-builder
Threat-Vector-Security
Guide for building high-quality MCP (Model Context Protocol) servers and tool suites.
SkillBFreshness: B★ 13Claude Code +9 - 0.598score
skill-creator
Threat-Vector-Security
Guide for creating new skills, improving existing skills, and evaluating skill quality.
SkillBFreshness: B★ 13Claude Code +9 - 0.596score
receiving-code-review
Threat-Vector-Security
Use when addressing code review or QA feedback, especially when the feedback is unclear, broad, or technically questionable.
SkillBFreshness: B★ 13Claude Code +9
Cite this page
source-driven-development skill. Agent Mart. https://agentmart.dev/skills/threat-vector-security-source-driven-development (last updated 2026-10-24)