File Analysis
- 118 installs
- 325 repo stars
- Updated August 2, 2026
- athola/claude-night-market
File-analysis is an agent skill that maps file structure and module organization before architecture reviews, refactoring, or migration planning.
About
File-analysis is a workspace-ops skill from Claude Night Market that gives solo builders a disciplined first pass over an unfamiliar codebase. Instead of ad-hoc grepping, it walks through identifying the analysis root and monorepo boundaries, inferring language and framework from manifests like package.json or Cargo.toml, mapping directory structure at controlled depth, detecting organizational patterns, and noting hotspots worth deeper review. The skill integrates TodoWrite checkpoints so you can see progress across root identification, structure mapping, pattern detection, and hotspot notes—making it ideal input before architecture reviews, refactor roadmaps, or migration scope estimates. It deliberately defers broad exploration to a dedicated Explore agent and exact pattern hunts to Grep, which keeps the skill focused on structural cartography. Complexity is medium (intermediate): you need a repo on disk and comfort with shell tree/find commands. Dependencies referenced in metadata include sanctum:shared and imbue:proof-of-work for ecosystems that use those packages.
- Four tracked TodoWrite steps: root-identified, structure-mapped, patterns-detected, hotspots-noted
- Confirms analysis root, monorepo boundaries, and project type from manifest files
- Maps top-level layout with tree or find capped at depth 2 before deeper dives
- Explicit When NOT To Use: general exploration → Explore agent; pattern search → Grep
- Frontmatter tags: files, structure, analysis, codebase, exploration; medium complexity (~800 tokens estimated)
File Analysis by the numbers
- 118 all-time installs (skills.sh)
- Ranked #1,296 of 3,282 Productivity & Planning skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/athola/claude-night-market --skill file-analysisAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 118 |
|---|---|
| repo stars | ★ 325 |
| Security audit | 3 / 3 scanners passed |
| Last updated | August 2, 2026 |
| Repository | athola/claude-night-market ↗ |
What it does
Map directories, modules, and hotspots in an unfamiliar repo before architecture review, refactor planning, or migration estimates.
Who is it for?
Best when you're onboarding to a legacy or monorepo repo and need planning-grade structure notes in one session.
Skip if: Finding a specific symbol or string across the repo—use Grep or an Explore agent instead, as the skill itself directs.
When should I use this skill?
Before architecture reviews, refactoring planning, or migration scope estimation—to map file structure and module organization.
What you get
You get a structured layout map with patterns and hotspots noted, ready for architecture review, refactor tasks, or migration scope estimates.
- Identified analysis root and monorepo/workspace boundaries
- Top-level structure map with detected patterns
- Hotspot notes for areas needing deeper review
By the numbers
- 4 required TodoWrite steps from root-identified through hotspots-noted
- Top-level mapping uses tree -L 2 -d or find with maxdepth 2
- Estimated_tokens: 800 in skill frontmatter
Files
File Analysis
When To Use
- Before architecture reviews to understand module boundaries and file organization.
- When exploring unfamiliar codebases to map structure before making changes.
- As input to scope estimation for refactoring or migration work.
When NOT To Use
- General code exploration - use the Explore agent
- Searching for specific patterns - use Grep directly
Required TodoWrite Items
1. file-analysis:root-identified 2. file-analysis:structure-mapped 3. file-analysis:patterns-detected 4. file-analysis:hotspots-noted
Mark each item as complete as you finish the corresponding step.
Step 1: Identify Root (file-analysis:root-identified)
- Confirm the analysis root directory with
pwd. - Note any monorepo boundaries, workspace roots, or subproject paths.
- Capture the project type (language, framework) from manifest files (
package.json,Cargo.toml,pyproject.toml, etc.).
Step 2: Map Structure (file-analysis:structure-mapped)
- Run
tree -L 2 -dorfind . -type d -maxdepth 2to capture the top-level directory layout. - Identify standard directories:
src/,lib/,tests/,docs/,scripts/,configs/. - Note any non-standard organization patterns that may affect downstream analysis.
Step 3: Detect Patterns (file-analysis:patterns-detected)
- Use
find . -name "*.ext" -not -path "*/.venv/*" -not -path "*/__pycache__/*" -not -path "*/node_modules/*" -not -path "*/.git/*" | wc -lto count files by extension. - Identify dominant languages and their file distributions.
- Note configuration files, generated files, and vendored dependencies.
- Run
wc -l $(find . -not -path "*/.venv/*" -not -path "*/__pycache__/*" -not -path "*/node_modules/*" -not -path "*/.git/*" -name "*.py" -o -name "*.rs" | head -20)to sample file sizes.
Step 4: Note Hotspots (file-analysis:hotspots-noted)
- Identify large files (potential "god objects"):
find . -type f -exec wc -l {} + | sort -rn | head -10. - Flag deeply nested directories that may indicate complexity.
- Note files with unusual naming conventions or placement.
Exit Criteria
TodoWriteitems are completed with concrete observations.- Downstream workflows (architecture review, refactoring) have structural context.
- File counts, directory layout, and hotspots are documented for reference.
Related skills
Grill MeHave an agent relentlessly pressure-test their plan or design until every decision branch is resolved and shared understanding is reached.691k196kGrill With DocsPressure-test architecture decisions against their live codebase and living documentation before writing production code.585k196k
Lark CalendarLet their coding agents read, create, and manage events inside Lark (Feishu) Calendar directly from natural language instructions.493kLark ImLet their coding agent send instant notifications, post updates, and receive commands directly inside Lark (Feishu) workspaces.493kLark ContactLet their AI coding agents read and write contacts, send messages, and manage user data inside Lark (Feishu).493kLark AttendanceAutomatically fetch and report daily attendance data from Lark (Feishu) into their own tools or agents.493kHow it compares
Structural planning snapshot, not deep semantic code search or automated refactoring execution.
FAQ
Who is file-analysis for?
Developers and tech leads who need module boundaries and directory conventions documented before planning refactors or reviews.
When should I use file-analysis?
Before Build/pm refactor plans, Validate/scope migration estimates, or Ship/review architecture passes on unfamiliar trees.
Is file-analysis safe to install?
It reads repository structure locally; check Security Audits on this Prism page and avoid pointing it at directories with secrets you do not want summarized in agent output.