Tooluck logoTooluck
SKILL.md

thinking-via-negativa

Agent skill fromtjboudreaux/cc-thinking-skills

Use when the reflex is to add a feature, layer, or process. Prefer removing harmful or nonessential elements first, with an irreversibility guard before deletion.

How to install thinking-via-negativa

install thinking-via-negativa
# install the cc-thinking-skills pack with the skills CLI
npx skills add tjboudreaux/cc-thinking-skills

# or add only this skill to Claude Code: copy the folder

skills/thinking-via-negativa/

# into

~/.claude/skills/thinking-via-negativa/ (all projects)

.claude/skills/thinking-via-negativa/ (one project)

skills/thinking-via-negativa/SKILL.md

MITFull file
1# Via Negativa
2
3Improve by subtraction before addition. Prefer removing harm, waste, and nonessential complexity; add only when a demonstrated need remains after removal candidates are exhausted.
4
5## When to Use
6
7- About to add a feature, abstraction, dependency, process, or control to fix a problem.
8- Simplifying a system or workflow where complexity is the tax.
9- Prioritizing by deciding what not to keep, build, or maintain.
10- Performance or reliability work where eliminating a bad path beats bolting on mitigation.
11
12## When NOT to Use
13
14- Load-bearing controls: auth, validation, tests, rate limits, retries, safety checks — presume necessary until proven dead.
15- A demonstrated requirement that cannot be met by removal or simplification.
16- Aesthetic minimalism without evidence of non-use or net harm.
17- Irreversible deletion without a rollback path when impact is unknown.
18
19## Procedure
20
211. **Pause the add reflex.** State the goal and the proposed addition in one line.
222. **Ask the subtraction question first.** List what could be removed or stopped to achieve the same goal with less surface area.
233. **Catalog candidates with evidence.** Prefer unused, redundant, high-cost/low-value, or harmful elements. Require usage, call-graph, metrics, or experiment evidence — not taste.
244. **Apply the irreversibility guard.** Classify reversible vs hard-to-restore; identify dependents; refuse deleting unproven mystery guards. Plan staged removal or flag when risk is non-trivial.
25…

Excerpt shown under the repository's MIT license.

More skills in cc-thinking-skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates