Frontend reconnaissance — map the component tree, routing, state management, build config, and assess quality.

MITAuto-check: notesFrontend & Design

Install Prism Recon

skills CLI
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill prism-recon -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jeremylongshore/tons-of-skills-marketplace prism-recon --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/ai-agency/tonone/skills/prism-recon .claude/skills/prism-recon && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
prism-recon
GitHub stars
2.8k
Token cost
~1.2k tokens
SKILL.md length
398 words
Files
2
Skills in repo
3,342
Repo updated
First seen
Licence
MIT

At a glance

Frontend reconnaissance — map the component tree, routing, state management, build config, and assess quality.

  • Works in 5 steps: Detect Environment → Map Component Tree → Map Architecture → …
  • Asked to understand this frontend
  • SKILL.md covers Steps and Delivery
  • Calls bundle

What it does

Prism Recon is an agent skill from jeremylongshore/tons-of-skills-marketplace. Frontend reconnaissance — map the component tree, routing, state management, build config, and assess quality. Use when asked to "understand this frontend", "frontend assessment", or "what's the UI built with".

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `.claude-plugin/plugin.json`).

It sits in Frontend & Design, covering State management. The repository describes itself as: Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. The licence is MIT.

When your agent uses it

  • Asked to understand this frontend
  • Frontend assessment
  • Whats the UI built with

Example prompts

  • “understand this frontend”
  • “frontend assessment”
  • “s the UI built with”
  • “/prism-recon”

Requirements

  • Pre-approved tools (allowed-tools): Read, Bash, Glob, Grep, WebFetch, WebSearch, AskUserQuestion

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Detect Environment
  2. Map Component Tree
  3. Map Architecture
  4. Assess Quality Metrics
  5. Present Assessment

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Bash
    • Glob
    • Grep
    • WebFetch
    • WebSearch
    • AskUserQuestion

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • bundle

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Prism Recon loads about 1.2k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 398 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Bash, Glob, Grep, WebFetch, WebSearch, AskUserQuestion

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 398 words, ~1,210 tokens.

Download SKILL.mdSave it as .claude/skills/prism-recon/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
prism-recon
description
Frontend reconnaissance — map the component tree, routing, state management, build config, and assess quality. Use when asked to "understand this frontend", "frontend assessment", or "what's the UI built with".
allowed-tools
Read, Bash, Glob, Grep, WebFetch, WebSearch, AskUserQuestion
version
0.6.4
author
tonone-ai <hello@tonone.ai>
license
MIT

Frontend Reconnaissance

You are Prism — the frontend and developer experience engineer from the Engineering Team.

Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.

Steps

Step 0: Detect Environment

Scan the project to identify the complete frontend stack:

  • Check for framework: next.config.*, nuxt.config.*, svelte.config.*, astro.config.*, vite.config.*, remix.config.*
  • Check package.json for: all dependencies, scripts, engines
  • Check for TypeScript: tsconfig.json — note strictness level
  • Check for monorepo: pnpm-workspace.yaml, turbo.json, nx.json, lerna.json
  • Check deployment: vercel.json, netlify.toml, fly.toml, Dockerfile, CI/CD configs

This is a read-only reconnaissance — do not modify anything.

Step 1: Map Component Tree

Understand how the UI is organized:

  • Pages/routes: scan the routing structure (app/, pages/, routes/, src/routes/)
  • Components: map the component hierarchy — shared components, page-specific components, layout components
  • Component count: total components, average size, largest components
  • Composition patterns: are components composed via children/slots, or configured via props
  • Shared vs. page-specific: ratio of reusable to one-off components
Step 2: Map Architecture

Understand the technical architecture:

  • Routing: file-based, config-based, or library-based — nested routes, dynamic routes, catch-all routes
  • State management: what library (Zustand, Redux, Pinia, Svelte stores, React Context), how is state organized, is there a clear pattern
  • Data fetching: server components, loaders, API routes, client-side fetching, tRPC, GraphQL — what patterns are used
  • API integration: how does the frontend talk to the backend — REST, GraphQL, tRPC, direct DB access
  • Styling: Tailwind, CSS Modules, styled-components, vanilla CSS — is there a design system or token system
  • Build config: Vite, webpack, Turbopack — any custom plugins, aliases, or unusual configuration
Show full SKILL.md (149 more words)Show less
Step 3: Assess Quality Metrics

Measure the current state:

  • Bundle size: check build output if available, or estimate from dependencies
  • Dependency count: total deps, heavy deps, potentially unused deps
  • Dependency freshness: how many major versions behind on key dependencies (framework, React, etc.)
  • Test coverage: check for test files, test config, coverage reports — what percentage of components are tested
  • TypeScript strictness: strict mode enabled, percentage of any usage, untyped areas
  • Accessibility baseline: quick scan for semantic HTML, ARIA usage, keyboard handlers, focus management
  • Performance patterns: SSR vs. CSR split, code splitting usage, image optimization
Step 4: Present Assessment
## Frontend Reconnaissance

### Stack
- **Framework:** [name + version]
- **Language:** [TypeScript/JavaScript — strictness level]
- **Styling:** [approach]
- **State management:** [library/pattern]
- **Build tool:** [name + config notes]
- **Hosting:** [platform]
- **Testing:** [framework — coverage level]

### Architecture
- **Pages:** [count] routes — [routing pattern]
- **Components:** [count] total — [count] shared, [count] page-specific
- **Data fetching:** [pattern] — [server/client split]
- **API integration:** [approach]

### Health Indicators
| Metric | Status | Notes |
|--------|--------|-------|
| Bundle size | [size or unknown] | [assessment] |
| Dependencies | [count] | [freshness, issues] |
| Test coverage | [percentage or unknown] | [what's tested] |
| TypeScript | [strict/loose/none] | [any usage level] |
| Accessibility | [baseline assessment] | [key gaps] |
| Performance | [assessment] | [SSR/CSR, code splitting] |

### Strengths
- [what's well done]

### Risks
- [what could cause problems]

### Modernization Recommendations
1. [highest value improvement] — [effort] — [impact]
2. [next improvement] — [effort] — [impact]
3. [next improvement] — [effort] — [impact]

Reconnaissance report — present facts, highlight risks, recommend improvements. Do not make changes.

Delivery

If output exceeds the 40-line CLI budget, invoke /atlas-report with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in plugins/ai-agency/tonone/skills/prism-recon of jeremylongshore/tons-of-skills-marketplace.

  • SKILL.md
  • .claude-plugin/plugin.json

Open the folder on GitHubat commit cfae287

Compare with similar skills

Prism Recon next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Prism Recon compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prism Recon this skilljeremylongshore/tons-of-skills-marketplace2.8k—~1.2kAutomated safety check: NotesMIT
Svelte Core Best Practicesrilldata/rill2.9k4 repos~1.8kAutomated safety check: PassApache-2.0
Dify Component Writing Guidelanggenius/dify158k—~626Automated safety check: PassCustom licence
React State Managementinvolvex/youtube-music-cli45613 repos~3kAutomated safety check: PassMIT
Pierre Theming Librarypierrecomputer/pierre6.3k—~661Automated safety check: PassApache-2.0
Frontend Patternskurealnum/dotfiles29019 repos~3.7kAutomated safety check: PassNone

Similar skills

  • Rules for writing idiomatic Svelte 5 code: when to reach for runes like state, derived and effect, and how to handle props, attachments and bindings.

    2.9k GitHub starsUsed in 4 repos~1.8k tokens
    Frontend & DesignAuto-check passed
  • Use when implementing or refactoring React/TypeScript components and the task requires decisions about component ownership, feature boundaries, state, data…

    158k GitHub stars~626 tokensUpdated today
    Frontend & DesignAuto-check passed
  • React State Management

    involvex/youtube-music-cli

    Master modern React state management with Redux Toolkit, Zustand, Jotai, and React Query.

    456 GitHub starsUsed in 13 repos~3k tokens
    Frontend & DesignAuto-check passed
  • Pierre Theming Library

    pierrecomputer/pierre

    Explains how to use the @pierre/theming package to list, resolve, select, switch and persist themes, with controller, color and React references.

    6.3k GitHub stars~661 tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Frontend Patterns

    kurealnum/dotfiles

    Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.

    290 GitHub starsUsed in 19 repos~3.7k tokens
    Frontend & DesignAuto-check passed
  • Explains how LobeHub client code fetches data through services, SWR store hooks and cache keys, and when to avoid useEffect fetching or duplicated state.

    83k GitHub stars~1.8k tokensUpdated today
    Frontend & DesignAuto-check passed

More from jeremylongshore/tons-of-skills-marketplace

All 3,342 skills in this repo
  • Performing Security Code Review

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.

    2.8k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check: notes
  • Adapting Transfer Learning Models

    jeremylongshore/tons-of-skills-marketplace

    Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Agent Context Loader

    jeremylongshore/tons-of-skills-marketplace

    Execute proactive auto-loading: automatically detects and loads agents.md files.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Aggregating Performance Metrics

    jeremylongshore/tons-of-skills-marketplace

    Aggregate and centralize performance metrics from applications, systems, databases, caches, and services.

    2.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Analyzing Capacity Planning

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth.

    2.8k GitHub stars~947 tokensUpdated today
    Auto-check passed
  • Analyzing Database Indexes

    jeremylongshore/tons-of-skills-marketplace

    Process use when you need to work with database indexing. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~2k tokensUpdated today
    Auto-check passed

Questions about Prism Recon

What does Prism Recon do?

Frontend reconnaissance — map the component tree, routing, state management, build config, and assess quality. Prism Recon is an agent skill from jeremylongshore/tons-of-skills-marketplace. Frontend reconnaissance — map the component tree, routing, state management, build config, and assess quality.

When should I use Prism Recon?

Prism Recon fits situations like: asked to understand this frontend; frontend assessment; whats the UI built with.

How do I install Prism Recon in Claude Code?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill prism-recon -a claude-code`. Or copy the skill folder (plugins/ai-agency/tonone/skills/prism-recon in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/prism-recon in your project. Claude Code loads it when a task matches its description.

How do I install Prism Recon in Codex?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill prism-recon -a codex`. Or copy the skill folder (plugins/ai-agency/tonone/skills/prism-recon in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/prism-recon in your project. Codex loads it when a task matches its description.

Can I use Prism Recon in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill prism-recon -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prism-recon, .gemini/skills/prism-recon, .github/skills/prism-recon and .opencode/skills/prism-recon in your project.

What does Prism Recon need to run?

Going by SKILL.md and its folder, Prism Recon needs the command-line tools its instructions call (bundle). Its frontmatter pre-approves these tools: Read, Bash, Glob, Grep, WebFetch, WebSearch, AskUserQuestion.

Does Prism Recon access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Prism Recon safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Prism Recon use?

Prism Recon is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Prism Recon use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Prism Recon?

Skills that share tags, products or a category with Prism Recon: Svelte Core Best Practices (rilldata/rill, 2.9k stars), Dify Component Writing Guide (langgenius/dify, 158k stars), React State Management (involvex/youtube-music-cli, 456 stars) and Pierre Theming Library (pierrecomputer/pierre, 6.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prism Recon?

jeremylongshore (a GitHub user) maintains it in jeremylongshore/tons-of-skills-marketplace, which has 2,827 GitHub stars. The repository holds 3,342 skills in this directory. The repository was last updated on October 10, 2026.

Source: jeremylongshore/tons-of-skills-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.