Agent skill

Cwng Impact Map

by new-usemame in new-usemame/Calibre-Web-NextGen

Query Calibre-Web-NextGen's static cps impact map before changing a Python file, symbol, or Flask route, including confidence and blind-spot data.

GPL-3.0Auto-check passedBackend & APIs

Install Cwng Impact Map

skills CLI
$ npx skills add new-usemame/Calibre-Web-NextGen --skill cwng-impact-map -a claude-code

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

GitHub CLI
$ gh skill install new-usemame/Calibre-Web-NextGen cwng-impact-map --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/new-usemame/Calibre-Web-NextGen.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/cwng-impact-map .claude/skills/cwng-impact-map && 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
cwng-impact-map
GitHub stars
276
Token cost
~1.1k tokens
SKILL.md length
553 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
GPL-3.0

At a glance

Query Calibre-Web-NextGen's static cps impact map before changing a Python file, symbol, or Flask route, including confidence and blind-spot data.

  • Works in 4 steps: reached_by sites, especially… → downstream reaches sites; → confidence on every cited hop; and → …
  • Backend & APIs work in your project
  • Calls python3 and git

What it does

Cwng Impact Map is an agent skill from new-usemame/Calibre-Web-NextGen. Query Calibre-Web-NextGen's static cps impact map before changing a Python file, symbol, or Flask route, including confidence and blind-spot data.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Backend & APIs. It works with Flask and Python. The repository describes itself as: Community continuation of Calibre-Web-Automated. Attempting to maintain with rapid iteration. Please feel free to help out by filing Issues, Feature Requests, PRs, and chatting… The licence is GPL-3.0.

When your agent uses it

  • Backend & APIs work in your project

Example prompts

  • “/cwng-impact-map”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. reached_by sites, especially live_routes_reaching_target;
  2. downstream reaches sites;
  3. confidence on every cited hop; and
  4. blind_spots.count, the leading reasons, and relevant file:line records.

What it can do on your machine

Read from SKILL.md and the folder at commit d2844f7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python3
    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Cwng Impact Map loads about 1.1k tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 553 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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 passed

The automated check found no risky patterns in SKILL.md.

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 new-usemame/Calibre-Web-NextGen at commit d2844f7, republished under its GPL-3.0 licence (© new-usemame). 553 words, ~1,124 tokens.

Download SKILL.mdSave it as .claude/skills/cwng-impact-map/SKILL.md (or your agent's skills folder).
name
cwng-impact-map
description
Query Calibre-Web-NextGen's static cps impact map before changing a Python file, symbol, or Flask route, including confidence and blind-spot data.

CWNG impact map

Use this skill when a change under cps/ needs a fast, evidence-linked impact survey. The map is a recall-oriented hint, not an authority.

From the repository root, query the most specific target available:

bash
python3 scripts/impact_map.py query 'cps/module.py:module_level_symbol'
python3 scripts/impact_map.py query 'blueprint.endpoint'
python3 scripts/impact_map.py query '/literal/or/<converter:rule>'

Use --format json when another tool will consume the result, and increase --depth only when the direct neighborhood is insufficient.

Report these together:

  1. reached_by sites, especially live_routes_reaching_target;
  2. downstream reaches sites;
  3. confidence on every cited hop; and
  4. blind_spots.count, the leading reasons, and relevant file:line records.

Treat exact_local_symbol, exact_import_symbol, exact_import_module_attribute, and route_reconciled as high-confidence static evidence. Treat class_member_coarse and attribute_name_guess as leads that require source inspection. Never turn absence from the result into a claim of no impact.

Before relying on a snapshot, refresh into a separate output directory. Set TARGET to the file, symbol, or route being investigated, then run from a clean checkout with the repo virtualenv:

bash
python3 scripts/impact_map.py refresh \
  --output-dir "$TMPDIR/impact-map" --summary "$TMPDIR/impact-map-summary.md"
python3 scripts/impact_map.py query "$TARGET" \
  --map "$TMPDIR/impact-map/impact-map.json"

Read the currency summary's checked commit, current/committed cps tree SHAs, drift flags, recall number, and every miss. Compare generated_from.cps_tree_sha with git rev-parse HEAD:cps; a different checkout SHA alone may only identify a tooling commit. Refresh compares complete artifacts, so matching cps SHAs do not rule out generator or oracle drift. CI publishes the same three files as the impact-map-<checked SHA> download; a PR artifact can describe a merge candidate.

Stale snapshots and misses caused by current symbols moving or disappearing are advisory results, including historical/current path mismatches. Contributors do not need to commit regenerated JSON for these results. Missing historical commits, malformed inputs, and generation errors fail refresh: resolve the reported error before using its outputs. A failed accepted attempt removes old currency metadata; a directory without impact-map-currency.json is incomplete. Use separate directories for concurrent attempts and keep summary/output paths separate from repository inputs and each other.

Refreshing the committed snapshots is a maintainer action. When that is the intended task, run:

bash
python3 scripts/impact_map.py build
python3 scripts/impact_map.py recall
Show full SKILL.md (244 more words)Show less

Two limits you must state when you use this

1. The map stops at Python. It has zero nodes outside cps/*.py — no templates, no frontend. Measured over the last 400 cps-touching commits, 35% also changed cps/templates/* (10%) or frontend/src/* (29%). So for roughly a third of real changes the map structurally cannot name a consumer that exists. If you change a serializer, a route's response shape, or anything a page renders, the React or Jinja consumer will not appear — its absence is not evidence.

2. Recall depends entirely on what you ask about. The headline historical figure is ~80%, and that is measured on caller/consumer pairs where both ends are module-level Python symbols. Raw co-change recall across all changed symbols is 12.49%, with 37% of changed symbols getting nothing named at all. The honest range is therefore [12.5%, 80%], and which end you are at depends on your target.

You do not have to guess which: every query prints the matched module's unresolved-call count and reasons, and that number is informative rather than constant — across the 168 modules with 20 or more call sites it ranges from 0.000 to 0.870 (p10 0.262, median 0.440, p90 0.658). A module reported at 87% unresolved is telling you the answer is thin; one at 15% is telling you it is solid. Read that number every time and report it alongside the result.

Read docs/impact-map.md only when updating the generator, route oracle, confidence taxonomy, or historical case set.

© new-usemame, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/cwng-impact-map of new-usemame/Calibre-Web-NextGen.

Open the folder on GitHubat commit d2844f7

Compare with similar skills

Cwng Impact Map 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.

Cwng Impact Map compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cwng Impact Map this skillnew-usemame/Calibre-Web-NextGen276—~1.1kAutomated safety check: PassGPL-3.0
Fix Slow Endpointvpcarlos/profyle123—~2.1kAutomated safety check: PassMIT
Telegram Development Guide2025Emma/vibe-coding-cn23k1 repos~3.7kAutomated safety check: PassMIT
Framework Migration AssistantArabelaTso/Skills-4-SE253—~1.9kAutomated safety check: PassApache-2.0
Sentry Python SDKgetsentry/sentry-for-ai268—~4.1kAutomated safety check: PassApache-2.0
Route To Openapizebbern/claude-code-guide4.7k—~1.1kAutomated safety check: PassMIT

Similar skills

  • Fix Slow Endpoint

    vpcarlos/profyle

    Diagnose and fix a slow endpoint or request in a Python web app (FastAPI, Flask, Django, Tornado, any ASGI/WSGI framework) using real Profyle/VizTracer traces, then prove the fix by replaying the…

    123 GitHub stars~2.1k tokensUpdated 5 days ago
    Backend & APIsAuto-check passed
  • Telegram Development Guide

    2025Emma/vibe-coding-cn

    Chinese-language guide to building on Telegram: bots through the Bot API, Mini Apps in JavaScript and custom clients through TDLib, with Python examples.

    23k GitHub starsUsed in 1 repo~3.7k tokens
    Backend & APIsAuto-check passed
  • Framework Migration Assistant

    ArabelaTso/Skills-4-SE

    Automatically migrate Python web applications between frameworks (Flask → FastAPI, Django → FastAPI).

    253 GitHub stars~1.9k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed
  • Sentry Python SDK

    getsentry/sentry-for-ai

    Official

    Full Sentry SDK setup for Python. An agent skill from getsentry/sentry-for-ai.

    268 GitHub stars~4.1k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Route To Openapi

    zebbern/claude-code-guide

    Generates RESTful API documentation (OpenAPI 3.0 / Swagger spec) by scanning route definitions in code for Flask, FastAPI, Express, Gin, and other frameworks.

    4.7k GitHub stars~1.1k tokensUpdated today
    Backend & APIsAuto-check passed
  • Fishjam Python Server SDK

    software-mansion-labs/skills

    Python server SDK for Fishjam — backends that create rooms, mint peer tokens, receive server notifications, and run voice agents.

    291 GitHub stars~1.3k tokensUpdated 12 days ago
    Backend & APIsAuto-check passed

Works with

Categories

Questions about Cwng Impact Map

What does Cwng Impact Map do?

Query Calibre-Web-NextGen's static cps impact map before changing a Python file, symbol, or Flask route, including confidence and blind-spot data. Cwng Impact Map is an agent skill from new-usemame/Calibre-Web-NextGen. Query Calibre-Web-NextGen's static cps impact map before changing a Python file, symbol, or Flask route, including confidence and blind-spot data.

When should I use Cwng Impact Map?

Cwng Impact Map fits situations like: backend & APIs work in your project.

How do I install Cwng Impact Map in Claude Code?

Run `npx skills add new-usemame/Calibre-Web-NextGen --skill cwng-impact-map -a claude-code`. Or copy the skill folder (.agents/skills/cwng-impact-map in new-usemame/Calibre-Web-NextGen) into .claude/skills/cwng-impact-map in your project. Claude Code loads it when a task matches its description.

How do I install Cwng Impact Map in Codex?

Run `npx skills add new-usemame/Calibre-Web-NextGen --skill cwng-impact-map -a codex`. Or copy the skill folder (.agents/skills/cwng-impact-map in new-usemame/Calibre-Web-NextGen) into .agents/skills/cwng-impact-map in your project. Codex loads it when a task matches its description.

Can I use Cwng Impact Map 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 new-usemame/Calibre-Web-NextGen --skill cwng-impact-map -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cwng-impact-map, .gemini/skills/cwng-impact-map, .github/skills/cwng-impact-map and .opencode/skills/cwng-impact-map in your project.

What does Cwng Impact Map need to run?

Going by SKILL.md and its folder, Cwng Impact Map needs the command-line tools its instructions call (python3 and git). Our summary lists: Python 3.

Does Cwng Impact Map access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Cwng Impact Map safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Cwng Impact Map use?

Cwng Impact Map is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cwng Impact Map use?

About 1.1k tokens (SKILL.md is roughly 4.5k 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 Cwng Impact Map?

Skills that share tags, products or a category with Cwng Impact Map: Fix Slow Endpoint (vpcarlos/profyle, 123 stars), Telegram Development Guide (2025Emma/vibe-coding-cn, 23k stars), Framework Migration Assistant (ArabelaTso/Skills-4-SE, 253 stars) and Sentry Python SDK (getsentry/sentry-for-ai, 268 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cwng Impact Map?

new-usemame (a GitHub user) maintains it in new-usemame/Calibre-Web-NextGen, which has 276 GitHub stars. The repository was last updated on October 10, 2026.

Source: new-usemame/Calibre-Web-NextGen on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.