enforce-scannable-density
Skill1 starsChanged 4 months agoMITView on GitHub
Edit a portfolio case study for high signal, compact hierarchy, and fast scanning without losing evidence. Use when a draft is fluffy, repetitive, slow to navigate, paragraph-heavy, full of generic process language, or needs concise headings, key-value blocks, comparison matrices, captions, and technical spec blocks.
In this repository11 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Write the reader’s five highest-value questions.
- Distinctive: line 14
Remove throat-clearing, repeated context, passive constructions, generic process claims, and unsupported praise.
- Distinctive: line 24
Run a 30-second scan test and list any answer still difficult to locate.
- Distinctive: line 26
Never manufacture density by shrinking type, stacking unrelated facts, turning prose into decorative tables, or deleting uncertainty.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Enforce Scannable Density
Make complexity easier to find, not merely shorter. Apply the reduction, organization, and time-to-understand passes in references/density-pass.md.
Workflow
- Write the reader’s five highest-value questions.
- Measure whether the answer to each is visible in the title, summary, headings, captions, or first sentence of a section.
- Remove throat-clearing, repeated context, passive constructions, generic process claims, and unsupported praise.
- Group related evidence and give each section one job.
- Move the outcome, constraint, and pivotal decision earlier.
- Choose the lightest fitting form:
- prose for causal explanation;
- bullets for non-sequential factors;
- key-value blocks for compact facts;
- tables only for records with shared comparable fields;
- monospace blocks only for commands, logs, or technical specifications.
- Preserve quantitative data, caveats, ownership, attribution, and evidence labels.
- Run a 30-second scan test and list any answer still difficult to locate.
Never manufacture density by shrinking type, stacking unrelated facts, turning prose into decorative tables, or deleting uncertainty.
Output
Return the revised structure and copy, a cut/move/convert ledger, the five-question scan result, and any evidence weakened by the edit.
Example
Input:
We were very excited to embark on a comprehensive process that involved looking at
many different approaches before ultimately deciding on a new approvals experience.Expected outcome:
Decision — Replace blanket approvals with risk-based gates.
Evidence needed — alternatives considered, approval threshold, and measured effect.Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

