kainakamura/plan
claude/skills/plan/SKILL.md
Create a detailed implementation plan based on the chosen concept
$ install --global
skillsauthnpx skillsauth add kainakamura/dotfiles planInstall 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: Apr 17, 2026, 10:43 AM5.6s2 files scanned
SKILL.md
- name:
- plan
- description:
- Create a detailed implementation plan based on the chosen concept
Your task is to create an implementation plan based on the user's request. The plan will be provided to another agent for implementation. Your job is only to plan, you should not make any code changes.
Expect some back-and-forth conversation with the user as they ask questions about proposed plan and shape it into a final version. Your plan should start out at a rough high-level and become more detailed as the user helps fill in more details. Be sure to let the user make the important decisions, your job is to present options and recommendations but let the user shape the plan as they see fit.
Structure your output following template.md.
Steps
- Determine the current iteration (highest
iteration-NN/directory) - Read these thoughts:
problem.md: Problem statement- The most recent understanding file (highest NN) matching
iteration-NN/understanding/understanding-*.md - The most recent concepts file (highest NN) matching
iteration-NN/concepts/concepts-*.md - Any thoughts explicitly specified by the user via
$ARGUMENTS - If your task requires context beyond these files, consult
log.mdto identify other relevant artifacts by their descriptions and slugs
- Do NOT spawn agents by default. Work directly unless the user explicitly requests it via natural language (e.g., 'agent team of 3', 'use an agent team'). When spawning agents, planning benefits from code-searchers (implementation details), web-searchers (best practices), and critics (risks and gaps). Include repo paths and context from the hub file body so agents know where source code lives.
- Create a new
iteration-NN/plan/plan-NN-topic.mdfile at the next version number (include a short kebab-case topic in the filename) - Append a one-line entry to
iteration-NN/log.mddescribing what was planned and linking to the artifact
Success Criteria
iteration-NN/plan/plan-NN-topic.mdcreated in current iteration- No code files have been changed
Guidelines
- Read relevant documentation and resources online to understand what may be the best way to approach the problem
- Start out with high-level ideas and let the user guide you to fill out specifics
- Always let the user make the decisions, your job is to assist
Related Skills
kainakamura/auto-engineer
content-media
VerifiedTrustedCommunity
Run the engineering design process autonomously across multiple iterations
1SKILL.mdUpdated Apr 29, 2026
kainakamura/vault-health
testing
VerifiedTrustedCommunity
Audit the Obsidian thoughts vault for orphans, unresolved links, isolated hubs, and structural issues
1SKILL.mdUpdated Apr 17, 2026
kainakamura/new-project
tools
VerifiedTrustedCommunity
Create a new project in the Obsidian thoughts vault
1SKILL.mdUpdated Apr 17, 2026
kainakamura/understand
development
VerifiedTrustedCommunity
Research the codebase to build understanding of the problem, writing findings to an understanding artifact
1SKILL.mdUpdated Apr 16, 2026