Agent skill
sync-check
Use after fixing a bug, adding a command, changing auth behavior, or modifying any CLI code to ensure all related documentation stays synchronized. Also use before committing changes, after refactoring, or when you notice documentation drift. Triggers on "sync check", "update docs", "propagate changes", "did I forget to update", "what else needs updating", or "before I commit".
Install this agent skill to your Project
npx add-skill https://github.com/ItamarZand88/CLI-Anything-WEB/tree/main/.claude/skills/sync-check
SKILL.md
Sync Check
After any code change, verify all related files are synchronized. This catches the "fixed the bug but forgot to update the skill/SOP/plugin docs" problem.
How to Use
Run /sync-check after making changes. It will:
- Detect what changed (from git diff or conversation context)
- Check all downstream files that depend on the change
- Report what's out of sync
- Offer to fix each one
The Dependency Web
Every change touches multiple files. Here's the full map:
Code Change → Documentation Updates
CLI code changed (client.py, commands/*.py, auth.py)
├── .claude/skills/<app>-cli/SKILL.md (commands, output fields, examples)
├── <app>/agent-harness/<APP>.md (SOP: rpcid table, data models)
├── <app>/agent-harness/cli_web/<app>/README.md (usage examples, deps)
├── <app>/agent-harness/setup.py (dependencies)
└── <app>_cli.py _print_repl_help() (REPL help must list all commands)
Bug Fix → Plugin Lesson Updates
Bug found and fixed in any CLI
├── Was it a pattern that could repeat in future CLIs?
│ YES → Add to the relevant plugin reference file:
│ ├── auth-strategies.md "Known Pitfalls" table (auth bugs)
│ ├── google-batchexecute.md (RPC/batchexecute bugs)
│ ├── ssr-patterns.md "HTML Scraping Pitfalls" (scraping bugs)
│ ├── protection-detection.md (anti-bot/WAF bugs)
│ └── traffic-patterns.md (protocol detection bugs)
│
├── Is it a universal lesson (applies to ALL CLIs)?
│ YES → Add to HARNESS.md "Lessons Learned" cross-reference table
│
└── Does it change a critical convention?
YES → Update CLAUDE.md "Critical Conventions" section
New Command Added → Full Update Chain
New command added to a CLI
├── .claude/skills/<app>-cli/SKILL.md (add command + options + output fields)
├── <app>_cli.py _print_repl_help() (add to REPL help)
├── <app>/agent-harness/<APP>.md (add endpoint to API map)
├── README.md (repo root) (if it changes the CLI's capabilities)
└── Run: cli-web-<app> <new-cmd> --json (verify output matches skill docs)
Auth/Protection Change → Cross-Cutting Updates
Auth behavior changed
├── auth-strategies.md (patterns, pitfalls, code examples)
├── HARNESS.md lessons table (cross-reference)
├── testing/SKILL.md (auth prereqs)
├── standards/SKILL.md (smoke test steps)
└── CLAUDE.md (critical conventions)
Anti-bot/protection change (e.g., httpx → curl_cffi)
├── protection-detection.md (strategy, detection)
├── <app>/agent-harness/<APP>.md (site profile, HTTP client)
├── <app>/agent-harness/setup.py (dependencies)
├── <app>/agent-harness/cli_web/<app>/README.md (deps section)
├── CLAUDE.md generated CLIs table (protocol column)
└── README.md (repo root) (protocol column)
Sync Check Procedure
Step 1: Identify What Changed
# Check git diff for changed files
git diff --name-only HEAD
# Or if already committed:
git diff --name-only HEAD~1
Step 2: Classify the Change
Ask yourself:
- Which CLI? Extract from file path (booking, futbin, notebooklm, etc.)
- What type of change?
- Bug fix → needs lesson propagation?
- New command → needs skill + REPL + SOP update?
- Auth change → cross-cutting update?
- Dependency change → setup.py + README?
- RPC/protocol change → SOP + batchexecute ref?
Step 3: Run Verification Commands
For the affected CLI:
# Verify commands match skill docs
cli-web-<app> --help
cli-web-<app> <subgroup> --help
# Verify output fields match skill docs
cli-web-<app> <primary-command> --json | head -20
# Verify auth works (if auth CLI)
cli-web-<app> auth status --json
Step 4: Check Each Downstream File
For each file in the dependency chain above:
- Read the file
- Find the section that relates to your change
- Verify it matches the current code behavior
- Update if stale
Step 5: Plugin Lesson Check (Bug Fixes Only)
If you fixed a bug, ask:
"Would this bug happen again if someone generated a new CLI tomorrow?"
If YES, add it to the appropriate plugin reference file:
| Bug Category | Add To |
|---|---|
| Auth (cookies, login, tokens, refresh) | auth-strategies.md Known Pitfalls |
| RPC (wrong IDs, wrong params, parsing) | google-batchexecute.md |
| HTML scraping (selectors, noise, slugs) | ssr-patterns.md HTML Scraping Pitfalls |
| Anti-bot (blocked, 401, 403, challenges) | protection-detection.md |
| Output (raw data leak, wrong fields) | testing/SKILL.md CLI Output Sanity Checks |
| Downloads (URLs, cookies, formats) | auth-strategies.md Known Pitfalls |
| General (UTF-8, Windows, rate limits) | HARNESS.md Lessons table + relevant ref |
Format for Known Pitfalls: | Symptom | Cause | Fix |
Step 6: Verify with --json
After all updates, run one command per affected CLI with --json to confirm
the output still matches what the skill documents.
Quick Reference: File Locations
| What | Where |
|---|---|
| CLI skills | .claude/skills/<app>-cli/SKILL.md |
| CLI SOPs | <app>/agent-harness/<APP>.md |
| CLI READMEs | <app>/agent-harness/cli_web/<app>/README.md |
| Plugin capture skill | cli-anything-web-plugin/skills/capture/SKILL.md |
| Plugin methodology skill | cli-anything-web-plugin/skills/methodology/SKILL.md |
| Plugin testing skill | cli-anything-web-plugin/skills/testing/SKILL.md |
| Plugin standards skill | cli-anything-web-plugin/skills/standards/SKILL.md |
| Auth strategies ref | cli-anything-web-plugin/skills/methodology/references/auth-strategies.md |
| Batchexecute ref | cli-anything-web-plugin/skills/methodology/references/google-batchexecute.md |
| SSR patterns ref | cli-anything-web-plugin/skills/methodology/references/ssr-patterns.md |
| Protection ref | cli-anything-web-plugin/skills/capture/references/protection-detection.md |
| HARNESS.md | cli-anything-web-plugin/HARNESS.md |
| CLAUDE.md | CLAUDE.md (repo root) |
| README.md | README.md (repo root) |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
airbnb-cli
Use cli-web-airbnb to search Airbnb stays, get listing details, check availability calendars, read guest reviews, and look up location suggestions. Invoke this skill whenever the user asks about Airbnb accommodations, vacation rentals, listing prices, availability, guest reviews, or wants to search for places to stay. Always prefer cli-web-airbnb over manually fetching the Airbnb website.
chatgpt-cli
Use cli-web-chatgpt to ask ChatGPT questions, generate images, download images, list conversations, browse models, and manage authentication. Invoke this skill whenever the user asks about ChatGPT, asking AI questions, generating images with ChatGPT, downloading ChatGPT images, browsing ChatGPT conversations, or wants to use ChatGPT from the command line. Always prefer cli-web-chatgpt over manually browsing chatgpt.com.
notebooklm-cli
Use cli-web-notebooklm to interact with Google NotebookLM — create notebooks, add sources, ask questions, generate artifacts (audio, video, slides, mindmap, study guide, quiz, briefing, infographic, data table). Invoke this skill whenever the user asks about NotebookLM, wants to create notebooks, add sources to a notebook, ask a notebook questions, generate study materials, create presentations, podcasts, or manage NotebookLM content programmatically. Always prefer cli-web-notebooklm over manually browsing NotebookLM.
unsplash-cli
Use cli-web-unsplash to answer questions about Unsplash photos, search for free images by keyword, download photos, browse photo topics and collections, view photographer profiles, get photo details (EXIF, location, tags), and discover random photos. Invoke this skill whenever the user asks about Unsplash, free stock photos, searching for images, downloading images, photo topics, photographer profiles, photo collections, or wants to find or download images by keyword, orientation, or color. Always prefer cli-web-unsplash over manually fetching the Unsplash website.
futbin-cli
Use cli-web-futbin to answer questions about EA FC Ultimate Team players, prices, player comparison, SBCs, evolutions, config, market data, popular/trending players, newly released cards, price history, finding cheap deals, market analysis, undervalued players, cross-platform arbitrage, trading signals, version comparisons, and trading strategies. Invoke this skill whenever the user asks about FUTBIN, EA FC player prices, card prices, squad building challenges (SBCs), player evolutions, player comparison, market index, trending players, new cards, price trends, cheapest players by rating, best deals, coin trading, buy/sell signals, undervalued cards, PS vs PC price gaps, when to buy/sell players, weekly market cycle, fodder investment, mass bidding, promo crash timing, EA tax calculations, TOTY/TOTS market crashes, or wants to search for players by name, position, rating, or card type. Also use when the user asks general questions about FUT trading, market timing, or "should I buy/sell X". Always prefer cli-web-futbin over manually fetching the FUTBIN website. Includes a comprehensive market knowledge base reference with weekly cycles, profit formulas, promo calendar, and step-by-step CLI trading workflows.
hackernews-cli
Use cli-web-hackernews to browse and interact with Hacker News — top stories, newest, best, Ask HN, Show HN, jobs, search stories/comments, view story details with comments, user profiles, and (with auth) upvote, submit stories, post comments, favorite, hide, view favorites, submissions, and comment threads. Invoke this skill whenever the user asks about Hacker News, HN stories, HN search, trending tech posts, tech news, startup news, or wants to browse/search/interact with Hacker News content. Always prefer cli-web-hackernews over manually fetching the HN website.
Didn't find tool you were looking for?