Week 45, updated 2 Nov 2026

AI use cases Coding agents AI documentation generation

AI documentation generation

Draft READMEs, docstrings, API docs and changelogs from your code with an AI agent. Example prompts, a review workflow and the best-scored tools.

Tools compared
4
Open source
3of 4
Reviewed
16 Oct

For: Developers

Best-scored tools for this jobscore, safety
  1. 1Gemini CLIAI tool70Caution
  2. 2Claude CodeAI tool65No dependencies scanned
  3. 3ClineAI tool65Caution
  4. 4AiderAI tool31Caution
What the score and shapes mean

Score = public maintenance, adoption and docs signals, as a percentile of 52 tools. Nobody here tested these hands-on. Shapes are the separate safety label: No issues found, No dependencies scanned, Caution.

What it does for you

Maintainers of open source or internal projects, and developers inheriting code with no docs.

  • Draft a README with install and usage steps from the repo
  • Write docstrings and comments for undocumented functions
  • Produce a changelog from commit history
  • Explain architecture in a short overview document
  • Keep examples in the docs in sync after a refactor
More about this job

Documentation is often skipped because it is tedious. An agent can read the code and draft a first version quickly. You supply the intent and check the facts.

Workflow in 5 steps

  1. Tell the agent the audience.
  2. Ask it to cite the file it got each claim from.
  3. Run every command and code sample in the draft yourself.
  4. Edit for tone and remove anything speculative.
  5. Add the docs check to your pull request checklist.
Full steps
  1. Tell the agent the audience (new user, contributor, operator).
  2. Ask it to cite the file it got each claim from.
  3. Run every command and code sample in the draft yourself.
  4. Edit for tone and remove anything speculative.
  5. Add the docs check to your pull request checklist.

Prompts to copy

Starting points we wrote, not tested results.

Read this repository and draft a README: what it does, how to install, a minimal usage example, and how to run the tests. Only state things you can see in the code.

2 more prompts

Add docstrings to every public function in utils/dates.py. Describe parameters, return values and error cases, without changing code.

Write a changelog entry for version 2.3.0 from the commits since the last tag, grouped into Added, Changed and Fixed.

Watch out for

  • AI output can be fluent and wrong.
  • Treat AI changes like a pull request from a new colleague: read the diff, run the tests and keep a human sign-off before anything ships.
  • Generated docs often describe what the code was meant to do, not what it does.
  • Licence to check before commercial use: Claude Code (Proprietary (Anthropic Commercial Terms)).
  • CautionGemini CLI9 critical-severity known vulnerabilities in runtime dependencies (OSV)
  • No dependencies scannedClaude CodeCode checks clean, no lockfile to check
  • CautionCline13 critical-severity known vulnerabilities in runtime dependencies (OSV)
  • CautionAider18 critical-severity known vulnerabilities in runtime dependencies (OSV)
Why these warnings?
  • AI output can be fluent and wrong. Check facts, code and citations yourself before you rely on them or publish them.
  • Treat AI changes like a pull request from a new colleague: read the diff, run the tests and keep a human sign-off before anything ships.
  • Generated docs often describe what the code was meant to do, not what it does. Test the examples.
  • Gemini CLI: 9 critical-severity known vulnerabilities in runtime dependencies (OSV); Skill/agent file instructs piping a remote script into a shell: .gemini/skills/agent-tui/SKILL.md — curl -fsSL https://raw.githubusercontent.com/pproenca/agent-tui/master/install.sh | sh
  • Claude Code: code and instruction-file checks found nothing, but there is no runtime lockfile or manifest, so dependencies were not checked
  • Cline: 13 critical-severity known vulnerabilities in runtime dependencies (OSV)
  • Aider: 18 critical-severity known vulnerabilities in runtime dependencies (OSV)

Recommended tools

From our ranked data, highest score first. A high score does not mean a clean scan.

  • 70Gemini CLIAI tool · Apache-2.0 · #4 overall
  • 65Claude CodeAI tool · Proprietary (Anthropic Commercial Terms) · #11 overall
  • 65ClineAI tool · Apache-2.0 · #12 overall
  • 31AiderAI tool · Apache-2.0 · #45 overall

Related jobs

Sources for tool facts

google-gemini/gemini-cli · anthropics/claude-code · cline/cline · Aider-AI/aider. Data fetched 2 Nov 2026. Scores and labels are automated, relative and not a hands-on test.

Get the board every Monday

One email a week: the new top 10, the biggest score changes and every safety label that changed.

Free. Double opt-in: you confirm by email first, unsubscribe in one click.