juanibiapina/coding
agents/skills/coding/SKILL.md
Use before starting work on any coding task: implementing a feature, fixing a bug, refactoring, or changing code. Drives the complete implementation.
$ install --global
skillsauthnpx skillsauth add juanibiapina/dotfiles codingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 13, 2026, 7:41 AM121.0s1 file scanned
SKILL.md
- name:
- coding
- description:
- Use before starting work on any coding task: implementing a feature, fixing a bug, refactoring, or changing code. Drives the complete implementation.
Coding
Drive a coding task from goal to implementation. Plan first in an isolated context, then implement once the user approves.
Workflow
1. Understand the goal
Explore enough to ask good questions. Restate the goal in your own words and confirm it with the user before planning.
2. Delegate the plan
Invoke a subagent to research and plan in an isolated context:
subagent {
model: "<model>", # optional; omit to inherit the default model
task: "Load the plan skill and produce a plan for: <confirmed goal>"
}
The subagent researches the codebase, writes the plan to a tmp file, and returns the file path plus a short summary.
3. Present
Relay the subagent's summary to the user. Communicate succinctly:
- high level steps so the user understands what is changing and why
- architectural changes if any
- public interface changes
- breaking changes
Keep it brief but complete at a conceptual level so the user can review without reading the plan file or specific code changes.
4. Iterate
On feedback, read the plan file and edit it directly. Do not re-invoke the subagent. Do not assume the user or the plan is right: re-check the code, documentation, or research online as needed.
5. Implement
When the user approves the plan, implement it:
- Follow existing patterns in the codebase; read similar code first, match conventions
- Make changes incrementally, one logical unit at a time
- Test as you go; fix failures immediately
- Do what the plan says, nothing more
Related Skills
juanibiapina/vocabulary
development
VerifiedTrustedCommunity
Use when writing code plans, architecture, or generally discussing code
28SKILL.mdUpdated Jun 11, 2026
juanibiapina/testing
testing
VerifiedTrustedCommunity
Use when writing, reviewing, or improving tests, deciding what to mock, or designing interfaces for testability.
28SKILL.mdUpdated Jun 10, 2026
juanibiapina/tdd
development
VerifiedTrustedCommunity
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
28SKILL.mdUpdated Jun 10, 2026
juanibiapina/review-architecture
development
VerifiedTrustedCommunity
Find deep-module opportunities in a codebase. Use when the user wants to improve architecture, refactor, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
28SKILL.mdUpdated Jun 10, 2026