Analyze

What it does

When your agent uses it

• The user invokes /analyze with a feature request
• Change description

Example prompts

• “/analyze”

Workflow steps

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

1. 1Read CLAUDE.md first — it contains the architecture overview and conventions.
2. 2Use Grep and Read to confirm every claim before writing it down. Don't speculate about file contents.
3. 3For scraping/CLI/markdown/badge changes, trace the path through github_dependents_info/gh_dependents_info.py (the class is ~1000 LOC and…
4. 4For CLI flag changes, check both github_dependents_info/main.py AND action.yml — they must stay in sync.
5. 5If tests already cover the area, list the relevant test files in Affected surface.

What it can do on your machine

Read from SKILL.md and the folder at commit 74aece1. 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

  No scripts in the folder and no shell commands in SKILL.md.

  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

Analyze loads about 879 tokens when it runs. Until then it costs about 105 tokens; SKILL.md has 353 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~105

When it runs · the whole SKILL.md, loaded when a task matches

~879

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

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 nvuillam/github-dependents-info at commit 74aece1, republished under its MIT licence (© nvuillam). 353 words, ~879 tokens.

name

analyze

description

Phase 1 of the SDLC pipeline (also usable standalone). Use when the user invokes /analyze with a feature request, bug report, or change description. Gathers requirements and maps the affected code surface, then presents the analysis inline in the conversation for the next phase to consume. Do NOT propose solutions or write code in this phase. Do NOT save the analysis to disk unless the user explicitly asks.

# Analysis: <one-line problem statement>

## Goal
<2-3 sentences: what the user wants and why>

## Current behavior
<How the relevant code behaves today. Cite specific files and line numbers using `path:line` format.>

## Affected surface
<Bulleted list of files/functions/classes that will likely need to change, with one-line justification each.>

## Constraints & invariants
<What must NOT break. Public API contracts, marker strings like `<!-- gh-dependents-info-used-by-start -->`, CLI flags, env vars, on-disk CSV format, the action.yml input names, doctests in package docstrings, etc.>

## Open questions
<Anything that a design phase or the user needs to resolve. Empty list if none.>

## Out of scope
<Things deliberately excluded.>

© nvuillam, MIT. 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 .claude/skills/analyze of nvuillam/github-dependents-info.

Open the folder on GitHubat commit 74aece1