Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Attack the Premise · cursor | DecimalAI

codingby cursor

Attack the Premise

cursor/principle-attack-the-premise

Source cursor/plugins ↗License Not recorded

Apply when two or more fixes that share one premise have failed the same gate. Take a census of which actors hold the imbalance before the next fix, then question the premise instead of writing another fix that assumes it.

SkillScore87Maintained

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

Coding pack

Last verified 10/10/2026

What it changes

Passed 20 of 23 test cases with the skill, and 4 of 23 without it.

Without skill17%

With skill87%

Checks it passed that the model alone missed

Rejects the return path buffer as a compensating mechanism.
Requires fixing what assigns the asymmetric role to eliminate the skew.
Prohibits starting new fixes before creating the rerunnable census script.

and 27 more in the full report

17 fixed3 passed either way2 still failing1 broke

Pass-rate lift: +70 pp
Tokens: -23%
Agent turns: 0%
Response time: -39%

Model gemini-3.6-flashMeasured 10/10/2026v1 · latest is v220 of 23 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

This benchmark measured an earlier version of the skill.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/cursor-principle-attack-the-premise/SKILL.md https://app.decimal.ai/s/cursor-principle-attack-the-premise/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add cursor-principle-attack-the-premise, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/cursor-principle-attack-the-premise/ and pins it in .decimal/skills.lock

decimalai skills add cursor-principle-attack-the-premise

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/cursor-principle-attack-the-premise/SKILL.md https://app.decimal.ai/s/cursor-principle-attack-the-premise/SKILL.md

Raw file: /s/cursor-principle-attack-the-premise/SKILL.md ↗ · machine-readable summary at /s/cursor-principle-attack-the-premise.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 17 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 17

Prompt

We have had two failed database schema patch attempts to resolve deadlock exceptions during peak ordering hours. The database administrator wants to immediately run a third patch that modifies transaction isolation levels. What workflow rule must be enforced?

What was checked, without and with the skill
Checked	Without skill	With skill
Enforces stopping the third schema patch until the single shared premise is documented.	Missed	Passed
Requires executing a rerunnable actor census script before proceeding with database changes.	Missed	Passed

case-21 · gemini-3.6-flash · 10/10/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md15 linessingle file

Attack the Premise

When two or more fixes that share one premise have failed the same gate, suspect the premise, not the fixes.

Why: Each failed fix is evidence against the belief it assumed. A third fix on the same premise spends effort where the evidence already says the cause is not.

Pattern:

Write the premise down. The premise is the one sentence that every failed fix assumed.
Test the premise before the next fix. Find an observation that would come out differently if the premise were false, and make it. Look at how the failures are distributed, not only at how large they are. Make the check rerunnable per Build the Lever.
Follow the evidence. If it contradicts the premise, the cause is elsewhere. Look for what the failures have in common that the premise did not predict. If it confirms the premise, ask the next "why" per Fix Root Causes. The earlier fixes may have treated a consequence instead of the cause.
Remove the condition instead of compensating for it, per the Laziness Protocol. If the evidence shows that one part always lands on the losing side, change what puts it there. A mechanism that cleans up after it leaves the cause in place and adds work on every run.

Stop: Do not start the next fix before the premise is written down and tested.

This principle is distinct from Redesign from First Principles, which rebuilds a design around a new requirement. It questions a fact the current design assumes.

Track record

Benchmark

20 / 23

test cases passed, vs 4 / 23 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v6 — 10/15/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

cursor / plugins

pstack/skills/principle-attack-the-premise/SKILL.md

View on GitHub ↗

Imported 10/15/2026Version v2

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Attack the Premise

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills