Ready to supercharge your AI agents?

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

Hard Cut · udecode | DecimalAI

codingby udecode

Hard Cut

udecode/hard-cut

Source udecode/dotai ↗License Not recorded

Remove a feature completely with no backward compatibility; delete surfaces, callers, tests, docs, fallbacks, stubs, and dead exports.

SkillScore74Maintained

Automatic

Coding pack

Last verified 8/15/2026

What it changes

Passed 17 of 23 test cases with the skill, and 10 of 23 without it.

Without skill43%

With skill74%

Checks it passed that the model alone missed

The file pkg/webhooks/v1.go is deleted.
The file LegacyImportModal.tsx is deleted.
The response contains no 410 status code responses.

and 14 more in the full report

9 fixed8 passed either way4 still failing2 broke

Pass-rate lift: +30 pp
Tokens: -25%
Agent turns: 0%
Response time: -41%

Model gemini-3.6-flashMeasured 8/15/2026v117 of 23 cases passed with skill

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

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/udecode-hard-cut/SKILL.md https://app.decimal.ai/s/udecode-hard-cut/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add udecode-hard-cut, 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/udecode-hard-cut/ and pins it in .decimal/skills.lock

decimalai skills add udecode-hard-cut

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

curl -fsSL --create-dirs -o .claude/skills/udecode-hard-cut/SKILL.md https://app.decimal.ai/s/udecode-hard-cut/SKILL.md

Raw file: /s/udecode-hard-cut/SKILL.md ↗ · machine-readable summary at /s/udecode-hard-cut.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

While deleting `calculateTaxV1` in `src/billing/tax.ts`, there are JSDoc comments explaining why `calculateTaxV1` was originally used for EU transactions and a `// TODO: remove calculateTaxV1 once V2 is stable`. What should be done with these comments?

What was checked, without and with the skill
Checked	Without skill	With skill
The comments describing calculateTaxV1 are deleted.	Missed	Passed
The TODO comment regarding calculateTaxV1 is deleted.	Passed	Passed

case-06 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md51 linessingle file

Hard Cut

Use this when a feature should die, not linger.

Rules

Delete the surface. Do not deprecate it.
Do not leave throw new Error("Not implemented"), placeholder notices, "feature removed" banners, or TODOs about bringing it back unless the user explicitly asks.
Do not keep compatibility aliases, deprecated shims, fallback parsing, migration bridges, or dead exports.
Delete tests for deleted behavior. Keep tests only for the behavior that still exists.
Delete comments that describe deleted code or mourn the old feature.
If removal exposes adjacent dead code, keep cutting until the graph is clean.

Sweep

Find the real surface area:
- exports
- commands and flags
- routes
- UI entrypoints
- feature flags
- docs and examples
Trace references with rg.
Delete the implementation and the glue:
- call sites
- types
- state
- tests
- docs
- comments
Grep again for the removed name and obvious aliases.
Run the narrowest honest verification for the surviving product.

Smells

deprecated notices

Track record

Benchmark

17 / 23

test cases passed, vs 10 / 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 v4 — 8/3/2026

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

udecode / dotai

skills/hard-cut/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

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

Hard Cut

Rules

Sweep

Smells

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills