Install
$ agentstack add skill-v1-io-v1tamins-v1-deslop ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Remove AI Code Slop
Check the diff against main and remove branch-introduced code that adds no behavior, proof, or maintainability value.
Use v1-simplify for broader reuse/quality/efficiency cleanup. Use this skill when the target is recognizable agent-generated residue: defensive wrappers, narration comments, casts, logging, or abstraction created without a concrete need.
Usage
Typical invocations:
- Claude Code:
/v1-deslop - Codex: invoke
v1-deslopfrom the skills menu or use$v1-deslop
Removal Gate
Remove a line, block, helper, or wrapper only when at least one condition is true:
- It duplicates existing project behavior or adjacent patterns.
- It handles a state already ruled out by validation, typing, or caller contract.
- It narrates obvious code instead of documenting a hidden constraint.
- It hides a type/design problem with
any, broad casting, or catch-all fallback. - It adds logging, retries, configuration, or abstraction without a caller, failure mode, or test.
Keep it when it protects a real trust boundary, documents a non-obvious invariant, preserves public API compatibility, or is needed by existing behavior.
What It Removes
- Extra comments that a human wouldn't add or are inconsistent with the rest of the file
- Extra defensive checks or try/catch blocks that are abnormal for that area of the codebase (especially if called by trusted/validated codepaths)
- Casts to
anyto get around type issues - Over-engineered patterns that don't match the file's existing style
- Unnecessary type annotations on obvious types
- Verbose error handling where simpler patterns exist
- Redundant null checks in already-validated paths
- Excessive logging beyond what's normal for the codebase
What It Preserves
- Actual bug fixes and intended functionality
- Comments that provide genuine value
- Defensive code at trust boundaries (user input, external APIs)
- Type annotations that improve clarity
Process
- Get the diff between current branch and main.
- Review each changed file for the Removal Gate conditions.
- Remove only gated slop while preserving intended behavior.
- Run the smallest relevant formatter, typecheck, lint, or test command available.
- Report a 1-3 sentence summary of what changed and which check ran.
Output
A brief summary like: > "Removed 3 unnecessary try/catch blocks in query.py, deleted 5 redundant comments in handler.ts, and removed 2 any casts that were hiding type issues."
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: v1-io
- Source: v1-io/v1tamins
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.