stevefeldman/directory-deepdive
skills/directory-deepdive/SKILL.md
Investigate a directory's architecture and create/update a CLAUDE.md file capturing implementation knowledge
$ install --global
skillsauthnpx skillsauth add stevefeldman/agents-skills directory-deepdiveInstall 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 28, 2026, 8:07 AM146.8s1 file scanned
SKILL.md
- name:
- directory-deepdive
- description:
- Investigate a directory's architecture and create/update a CLAUDE.md file capturing implementation knowledge
Directory Deep Dive
Investigate and document directory architecture to build context from code when starting work in a new area.
Instructions
-
Target Directory
- Focus on the specified directory
$ARGUMENTSor the current working directory
- Focus on the specified directory
-
Check for Existing Documentation
- If a CLAUDE.md already exists in the target directory, read it first
- Note what is already documented so you can update rather than overwrite
- Preserve any existing information that is still accurate
-
Investigate Architecture
- Analyze the implementation principles and architecture of the code in this directory and its subdirectories
- Look for:
- Design patterns being used
- Dependencies and their purposes
- Key abstractions and interfaces
- Naming conventions and code organization
-
Create or Update Documentation
- If no CLAUDE.md exists, create one capturing the knowledge discovered
- If one already exists, update it with newly discovered information while preserving existing accurate content
- Include:
- Purpose and responsibility of this module
- Key architectural decisions
- Important implementation details
- Common patterns used throughout the code
- Any gotchas or non-obvious behaviors
-
Ensure Proper Placement
- Place the CLAUDE.md file in the directory being analyzed
- This ensures the context is loaded when working in that specific area
Credit
This command is based on the work of Thomas Landgraf: https://thomaslandgraf.substack.com/p/claude-codes-memory-working-with
Related Skills
stevefeldman/dependency-security-audit
development
VerifiedTrustedCommunity
Use when reviewing Dependabot alerts, npm audit findings, govulncheck output, or CVE reports on a JavaScript/Node.js or Go project — especially when triaging multiple alerts across direct and transitive dependencies to assess real-world risk and produce a remediation plan.
3SKILL.mdUpdated May 28, 2026
stevefeldman/pr-evidence
development
VerifiedTrustedCommunity
Use when a code review finding needs proof — write a focused test in JavaScript or Go that either confirms the issue is real or exposes it as over-engineering hyperbole. Trigger after code-review or code-review-skill findings are presented and evidence is requested.
3SKILL.mdUpdated May 22, 2026
stevefeldman/software-estimation
development
VerifiedTrustedCommunity
Produce data-driven software delivery estimates by analyzing historical JIRA tickets, git activity, and engineer track records, then matching the new work against the most similar past tickets. Use this skill whenever the user asks "how long will this take", wants to estimate a piece of work, scope an epic, plan a sprint, or estimate delivery for JIRA stories or a Figma design. Also use whenever the user wants developer-to-work assignment recommendations based on history, wants to optimize an estimate by adding or reallocating engineers, or asks "what's the fastest way to ship this" or "who should work on this". Especially trigger when the user provides JIRA ticket IDs, JIRA story links, or Figma designs together with any indication of a team that will execute the work.
3SKILL.mdUpdated May 16, 2026
stevefeldman/automation-rubric
tools
VerifiedTrustedCommunity
Use when auditing an existing test suite for quality and coverage gaps, evaluating Playwright migration readiness, scoring automation against a world-class e-commerce standard, or guiding the creation of new tests. Applicable to Selenium, WebdriverIO, and Playwright suites.
3SKILL.mdUpdated May 12, 2026