Compact Docs Writer

Shrinks version-controlled agent-read docs for token economy without dropping any rule, shown as a diff.

Tested · Works

Test report

Verdict
Tested · Works
Score
9.2/10
Tested
Jul 16, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Aug 10, 2026 · ff37745

Upstream indeed changed on our test day (commit 'improve self-test', 2026-07-16 14:32), but the diff shows it's a version bump 1.4 → 1.5 plus one added self-review item: 'addition audit' — each added sentence must now also pass a no-op test. This is a tightening of an existing procedure, not a problem fix or a new risk, so the pass verdict remains. Re-ran the protocol from scratch on the new version: install command works verbatim, frontmatter parsed (name, description, allowed-tools, license), the skill pulls no external files at all, Stage 0 clean — no scripts, network, or hidden instructions. Live A/B on an expanded code review rules doc (319 words, measured via wc -w): baseline compressed to 70 words but silently dropped the justification for three rules (why reviewer from owning team, why 24 hours to respond, why 400-line limit), while running with the skill's body yielded 117 words and preserved all eight rules and their 'why'. Same pattern as last time: baseline is shorter, the skill is the only one that doesn't lose intent.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 8/10
  • Docs & honesty 5/5

What Compact Docs Writer does

Rewrites or drafts a doc (e.g. CONTRIBUTING.md, CLAUDE.md, a skill file) to carry every rule and constraint in the fewest possible words, since these docs are re-read by agents on every session. Applies a no-op test to justify each deletion, collapses recurring concepts into single 'leading words', and presents the result as a fenced diff with a word/token delta measured with `wc -w` rather than estimated, applying only after explicit approval. Explicitly skips throwaway docs like one-off plans.

How to install Compact Docs Writer

git clone https://github.com/FrancescoBorzi/agent-toolkit.git
mkdir -p ~/.claude/skills
cp -r agent-toolkit/skills/compact-docs-writer ~/.claude/skills/compact-docs-writer

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Compact Docs Writer

  • /compact-docs-writer Shrinks version-controlled agent-read docs for token economy without dropping any rule, shown as a diff.

It also activates on plain-language prompts like these:

  • shrink this CONTRIBUTING.md without losing any of the actual rules
  • make my CLAUDE.md shorter but keep the reasoning behind each rule
  • show me a diff of the token savings after trimming this doc

Frequently asked questions

Is the Compact Docs Writer skill free?
Yes. The skill itself is free from FrancescoBorzi/agent-toolkit. SkillProof publishes the install command and an independent test verdict at no cost.
Does Compact Docs Writer work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. Upstream indeed changed on our test day (commit 'improve self-test', 2026-07-16 14:32), but the diff shows it's a version bump 1.4 → 1.5 plus one added self-review item: 'addition audit' — each added sentence must now also pass a no-op test. This is a tightening of an existing procedure, not a problem fix or a new risk, so the pass verdict remains. Re-ran the protocol from scratch on the new version: install command works verbatim, frontmatter parsed (name, description, allowed-tools, license), the skill pulls no external files at all, Stage 0 clean — no scripts, network, or hidden instructions. Live A/B on an expanded code review rules doc (319 words, measured via wc -w): baseline compressed to 70 words but silently dropped the justification for three rules (why reviewer from owning team, why 24 hours to respond, why 400-line limit), while running with the skill's body yielded 117 words and preserved all eight rules and their 'why'. Same pattern as last time: baseline is shorter, the skill is the only one that doesn't lose intent.
What is the Compact Docs Writer SkillProof Score?
9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Compact Docs Writer?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Compact Docs Writer with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.