agentleFS
stijnvanhullestijnvanhulle/agents/.agents/skills/deslop/SKILL.md

deslop

Skill2 starsChanged 56 days agoMITView on GitHub

Audits a diff or file for over-engineering and AI code and prose tells, then applies only the fixes the user confirms. Use before opening a PR, when asked to clean up, simplify, or review a diff, or when code looks generated.

130 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use simple-issue-description, control-cli and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • JwuthriSkill

    simple-issue-description

    Turn a rough bug report, feature request, support note, or pull request into a short, plain-language issue focused on the problem and desired behavior. Use when a contributor asks to simplify an issue, explain what a PR is for, create the corresponding issue for a PR, remove implementation detail from a report, or invokes /simple-issue-description.

    Also in 4 projects that use this

  • ElyzeSolutionsSkill

    control-cli

    Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services. Use for CLI UX checks, startup regressions, memory leaks, hangs, prompt flows, or terminal demos.

    Also in 6 projects that use this

  • JwuthriSkill

    openseo-review-web-content

    Write and review content for the OpenSEO website (web/) — blog posts, guides, feature pages, FAQs. Distills the philosophy for on-brand, useful, accurate content. Use whenever adding or editing user-facing prose in web/content or web/src.

    Also in 4 projects that use this

  • learnerLjSkill

    verify-this

    Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or INCONCLUSIVE.

    Also in 6 projects that use this

  • ElyzeSolutionsSkill

    control-ui

    Build or adapt a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI. Use for local UI verification, screenshots, accessibility snapshots, perf profiles, visual diffs, or reproducing UI bugs.

    Also in 7 projects that use this

  • ten9876Skill

    papercuts

    Read-only AetherSDR issue triage that surfaces the UX papercuts, bugs, and regressions you can fix AND prove today with the agent automation bridge. Use when the user says $papercuts or /papercuts, or asks to "find papercuts", "what can I fix and prove today", "triage bridge-provable issues", "what UX bugs can the bridge close", "sort issues by priority I can knock out", or otherwise wants a curated, lifecycle-aware (design→code→prove) shortlist of issues — NOT the label-and-respond /triage workflow. This is the discovery step that feeds /fb. Strictly read-only: it never labels, comments, closes, or edits issues.

    Also in 4 projects that use this

  • +5 more from Jwuthri

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 128 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the matching convention rules first, including the testing rule for any test you add.

    line 52
  2. Distinctive:

    Keep trust-boundary checks and real error handling.

    line 54
  3. Distinctive:

    Run format, lint, and the relevant tests.

    line 55
  4. Very specific:

    Leave the fixes in the working tree.

    line 58

“Common” is measured: kept by at least 6 in 10 of the 128 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Deslop

Find what a diff adds that the task did not need, and remove only what the user confirms.

1. Walk the reuse-first ladder

For each new dependency, file, wrapper, or export, stop at the first rung that fits:

  1. Does it need to exist? Skip guards for inputs that cannot occur and flags nobody asked for.
  2. Is it already in this codebase? Search before writing a helper or component.
  3. Does the standard library or language cover it?
  4. Does the platform or framework cover it?
  5. Does an installed dependency cover it?
  6. Does one inline line do it, instead of a new function or component?
  7. Otherwise, write only what the task needs.

Flag a dependency an earlier rung covers, a wrapper with one caller, an unrequested flag, generality for inputs nobody passes, a type alias that only renames another type, and a compatibility shim nobody asked for. Two real callers justify reuse.

For a new module or layer, run the deletion test: imagine it gone. If the complexity vanishes, it was a pass-through. If it reappears across several callers, it earns its place. One implementation behind an interface is a hypothetical seam, not a real one.

2. Check the code tells

  • Comments that restate the code or do not match the local comment density.
  • Abnormal defensive checks or try/catch on trusted paths. Trust-boundary validation stays.
  • any casts that dodge a type error.
  • Nesting that early returns would flatten, and any else or else if.
  • Naming, import, or export style that differs from nearby code.
  • Tests that restate the implementation or check what TypeScript already guarantees.
  • Changed comments and docs: the humanizer tells. Skip when no prose changed.
  • Docs that explain internals the reader does not act on, such as which package bundles a dependency. Delete the sentence rather than reword it.

3. Report, then ask

A request to review, assess, or explain a diff is audit-only: report and stop, unless the user also asked for fixes or already approved them. Otherwise write the findings list in chat (see Output), then, in the same reply, follow the ask skill with one question per finding, or per group that shares one fix, named after the finding (Unused enabled flag in Studio?). Every finding gets a question, so send a follow-up call when there are more than four.

4. Apply only what was confirmed

  • Read the matching convention rules first, including the testing rule for any test you add.
  • Make surgical edits that preserve behavior, unless the fix is a clear bug.
  • Keep trust-boundary checks and real error handling. Never weaken a type, rule, or test.
  • Run format, lint, and the relevant tests.
  • Re-audit the whole resulting diff against steps 1 and 2 and the convention rules, and fix what your edits introduced.
  • Leave the fixes in the working tree. Committing, pushing, or opening a PR, including a stacked PR on someone else's branch, is a separate decision to put through ask.

Output

A bulleted list, one bullet per finding: path:line, the rung or tell, the fix, and Apply or Skip as your recommendation. Never a prose summary. End with one bullet for what you checked and found fine. After applying, one bullet per change and one per skipped finding.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.