SummerRiversound GitHub avatar

human-readable-reports

SummerRiversound

An agent skill that transforms coding agents' jargon-filled, unreadable reports into clear, human-friendly documentation using 10 plain-language rules.

Stars

5

7-day growth

No data

Forks

0

Open issues

0

License

MIT

Last updated

2026-07-27

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It directly solves the widespread problem of AI-generated 'slop' by providing concrete, enforceable rules that make automated reports actually readable by humans, with a clear before/after demonstration.

Who it is for

  • Developers using Claude Code or similar AI coding agents
  • Team leads who review AI-generated reports and docs
  • Technical writers adapting agent output for broader audiences
  • Anyone frustrated by overly verbose or technical AI documentation

Use cases

  • Generating readable analysis reports from code reviews or audits
  • Creating human-friendly bug reports and performance summaries
  • Writing documentation that non-technical stakeholders can understand
  • Producing concise change logs or release notes from agent activity

Strengths

  • 10 specific, actionable writing rules that directly address common readability issues
  • Works out-of-the-box with Claude Code and can be adapted for other agents via system prompts
  • Includes a before/after example that clearly demonstrates the improvement
  • Open-source MIT license with active support for contributions

Considerations

  • Designed only for human-facing reports, not for specs or plans that require precise code references inline
  • Requires agent to support skill loading or manual rule insertion for non-Claude agents
  • Effectiveness depends on the agent's ability to follow the rules consistently

README quick start

human-readable-reports

Your coding agent writes reports that are technically correct and unreadable. Walls of jargon, file:line dumps, telegraphic bullets, invented terms. The team stops reading. This skill fixes that — deep content, easy reading.


The problem (you're not imagining it)

"AI verbosity" and "AI slop" are now common complaints — LLMs are trained to write long, thorough, hedged answers, so their reports default to something only the author's other agent could love. When the doc is unreadable, the human becomes the bottleneck.

The fix, in one look

Before — what an agent writes by default:

parseInput() is O(n²) due to nested scan (utils.js:88);
latency scales quadratically with list size → UI jank at scale.

After — same finding, with this skill:

The input parser gets slow as the list grows. It re-scans the whole list for each item, so a long list makes the screen stutter. (code location in the notes below)

Same facts. One of them your team will actually read.

The 10 rules

  1. Reader-first — write in their language, at their level.
  2. Point first — each section opens with the takeaway in one plain sentence.
  3. Analogy up front — ground the concept in something concrete.
  4. Full sentences, not fragments.
  5. Explain or drop jargon — no bare formulas, no coined terms.
  6. Evidence to the back — no file:line in the prose; put it in end-notes.
  7. Table cells read as phrases, not code.
  8. Cut the slop — no throat-clearing, no needless caveats.
  9. Progressive disclosure — hide depth behind expandable sections.
  10. Tone: teammate, not lecture.

Full rules, checklist, and the "when NOT to use it" boundary are in SKILL.md.

This README follows its own rules. That's the demo.

Install

Claude Code / Claude agents — clone into your skills directory:

# personal (all projects)
git clone https://github.com/SummerRiversound/human-readable-reports \
  ~/.claude/skills/human-readable-reports

# or project-shared
git clone https://github.com/SummerRiversound/human-readable-reports \
  .claude/skills/human-readable-reports

The agent loads it automatically when you ask for a report or analysis doc.

Cursor / other agents — paste the rules from SKILL.md into your system

Description

Agent skill: make AI-written analysis/report docs easy for humans to read and share (fights AI verbosity/slop).

Related repositories

Similar projects matched by category, topics, and programming language.

AgriciDaniel
Featured
AgriciDaniel GitHub avatar

anti-slop

Anti-slop is a tool for detecting and repairing substance defects in AI-assisted prose, code, documentation, and agent output using deterministic scanners and structural procedures that produce verifiable artifacts rather than authorship judgments.

AI & Machine LearningLarge Language Models
9
S40911120
Featured
S40911120 GitHub avatar

recensa

Recensa is a self-hosted web viewer that indexes Claude Code session transcripts into a local SQLite database, enabling full-text search, replay, and audit of all past agent conversations without uploading data anywhere.

AI & Machine LearningLarge Language Models
67
makecindy
Featured
makecindy GitHub avatar

cindy

Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.

AI & Machine LearningLarge Language Models
958