deslop
Remove AI-generated code slop and clean up code style on the current branch's diff.
Skill by gh0stwin
Chalk Labs
Need help deploying deslop?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/gh0stwin-deslop
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/deslop
What's inside
- Skill name
deslop- Description
- Remove AI-generated code slop and clean up code style on the current branch's diff. Use before commit or when a diff reads as machine-generated. Skip when the diff is a pure rename or a mechanical format-only change.
- License
- MIT
- Instructions
- 31 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Remove AI code slop Check the diff against the base branch and remove AI-generated slop introduced on this branch. ## Focus Areas - Extra comments that are unnecessary or inconsistent with local style - Defensive checks or try/catch blocks that are abnormal for trusted code paths - Casts to `any` used only to bypass type issues - Deeply nested code that should be simplified with early returns - Dead compatibility paths, unused parameters, and speculative guards - Edits unrelated to the change the branch claims to make - Other patterns inconsistent with the file and surrounding codebase ## Steps 1. Get the diff: `git diff <base>...HEAD` plus `git status --porcelain` for uncommitted work. Name the base explicitly; do not assume `main`. 2. Read each hunk in the context of its file, not in isolation. Slop is a mismatch between the hunk and the surrounding code. 3. Delete or rewrite only what the hunk itself introduced. Leave pre-existing style alone. 4. Re-run the narrowest check that proves behavior is unchanged (the branch's own test, build, or lint command). 5. Report in one to three sentences: what you removed and what you verified. ## Guardrails - Keep behavior unchanged unless fixing a clear bug. - Prefer minimal, focused edits over broad rewrites. - Do not restyle untouched code, reorder imports the formatter owns, or rename symbols the diff did not introduce. - If a removal needs a shape decision, stop and hand off to the **architect** skill rather than guessing. - Keep the final summary concise.
From gh0stwin/pi-pstack, MIT.
More from gh0stwin/pi-pstack
- 0.526score
reproduce-and-fix-issues
gh0stwin
Reproduce triaged bugs through a configured app-verification adapter, verify existing fixes, and open a bounded draft pull request only after before-and-after…
SkillBFreshness: BClaude Code +9 - 0.526score
triage-issue-reports
gh0stwin
Triage one report through its intake binding with a single verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation.
SkillBFreshness: BClaude Code +9 - 0.520score
create-skill
gh0stwin
Author, revise, or validate a pi skill (a SKILL.md folder) against the Agent Skills standard.
SkillBFreshness: BClaude Code +9 - 0.501score
interrogate
gh0stwin
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
SkillBFreshness: BClaude Code +9 - 0.501score
how
gh0stwin
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which…
SkillBFreshness: BClaude Code +9 - 0.499score
make-bot-ui
gh0stwin
Use when building a custom UI (page, dashboard, buttons) that should wake a pi agent from a local server, when the user must provide a wake token, or when…
SkillBFreshness: BClaude Code +9 - 0.499score
setup-benny
gh0stwin
Configure Benny and prepare its triage and reproduce runs on pi.
SkillBFreshness: BClaude Code +9 - 0.496score
blast-radius
gh0stwin
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of…
SkillBFreshness: BClaude Code +9 - 0.496score
no-comments
gh0stwin
Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
SkillBFreshness: BClaude Code +9 - 0.496score
automate-me
gh0stwin
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how…
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 11, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/gh0stwin/pi-pstack
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from gh0stwin
- 0.526score
reproduce-and-fix-issues
gh0stwin
Reproduce triaged bugs through a configured app-verification adapter, verify existing fixes, and open a bounded draft pull request only after before-and-after…
SkillBFreshness: BClaude Code +9 - 0.526score
triage-issue-reports
gh0stwin
Triage one report through its intake binding with a single verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation.
SkillBFreshness: BClaude Code +9 - 0.520score
create-skill
gh0stwin
Author, revise, or validate a pi skill (a SKILL.md folder) against the Agent Skills standard.
SkillBFreshness: BClaude Code +9 - 0.501score
interrogate
gh0stwin
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
SkillBFreshness: BClaude Code +9 - 0.501score
how
gh0stwin
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which…
SkillBFreshness: BClaude Code +9 - 0.499score
make-bot-ui
gh0stwin
Use when building a custom UI (page, dashboard, buttons) that should wake a pi agent from a local server, when the user must provide a wake token, or when…
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get deslop running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
deslop skill. Agent Mart. https://agentmart.dev/skills/gh0stwin-deslop (last updated 2026-10-24)