Skip to content
Skills Library
Management & product · Analysis

negative-space

/negative-space

Diffs a text against a domain checklist for trading claims, plans or code changes and lists the checklist items it never mentions. Use this whenever the user reads a result or plan and wants to see what it does not say. Pairs with blind-spot-sweep, dark-matter, erase-the-center and pov-core.

Licence
MIT
Last repository change
26.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
2
Scripts
1
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 26.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What to check before installing
  • 1 scripts in this package. Review them before installing, as Claude may execute them.

Scripts: negative_space.py

What it does and when to use it

Diffs a text against a domain checklist for trading claims, plans or code changes and lists the checklist items it never mentions. Use this whenever the user reads a result or plan and wants to see what it does not say. Pairs with blind-spot-sweep, dark-matter, erase-the-center and pov-core.

Original author description

Diffs a text against a domain checklist for trading claims, plans or code changes and lists the checklist items it never mentions. Use this whenever the user reads a result or plan and wants to see what it does not say. Pairs with blind-spot-sweep, dark-matter, erase-the-center and pov-core.

How it works

  1. The tool (ships with this skill)
  2. Uses and limits
Original SKILL.md headings · 33 lines, 212 words
SKILL.md preview
---
name: negative-space
description: Diffs a text against a domain checklist for trading claims, plans or code changes and lists the checklist items it never mentions. Use this whenever the user reads a result or plan and wants to see what it does not say. Pairs with blind-spot-sweep, dark-matter, erase-the-center and pov-core.
---

# negative-space

An **around** lens: it reads the shape a text leaves empty. Three built-in checklists give the outline of a complete text:
- **trading**: costs, sample size, out-of-sample, drawdown, data source, benchmark, sizing, regime, multiple testing, paper vs live;
- **plan**: owner, deadline, success measure, rollback, budget, dependencies, verification, done-definition;
- **code**: tests, error handling, rollback, performance, secrets, docs, compatibility, edge cases.

The domain is picked by trigger words, or set with domain=. Each item is either COVERED, with the cue that matched, or ABSENT.

## The tool (ships with this skill)

`negative_space.py`: pure stdlib on top of pov-core. Selftest 6/6.

```
python negative_space.py <file|text> [--opt domain=trading|plan|code] [--json]
python negative_space.py --selftest
from negative_space import apply; apply(note, domain="plan")
```

Example (pov-core probe text):

```
[negative-space] (text) trading checklist: 8 of 10 items unsaid (sample size, out-of-sample, drawdown, benchmark, sizing, regime/period, multiple testing, paper vs live)
  - ABSENT   out-of-sample - the text never says
```

## Uses and limits

- A cue word counts as coverage even when it is used in passing ("data" covers data source). COVERED means the item is mentioned, not that it is handled well.
- The checklists are fixed. Extend CHECK in the tool for a new domain rather than forking the skill.
- Paper-only for trading claims.
Files in this package (2)
  • SKILL.md 2 KB
  • negative_space.py 6 KB

Versions

The database has no other skills named negative-space.

Database snapshot: 13.11.2026 · package version ab0c6d990cc2 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100erase-the-center
    Finds the most central keyword of a text or plan - the one with the widest sentence span (in the most sentences), ties broken by co-occurrence degree (most distinct partner words), then first seen; discourse words like obviously/clearly/basically/really/just are never the center…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.