pahlevikunpahlevikun/levistack/skills/engineering/noslop/SKILL.md

noslop

Skill0 starsChanged 19 days agoMITView on GitHub

Domain router for the no-slop filter on backend handlers, APIs, frontend UI, database access, infra/config, tests, and code comments. Stops tutorial layering, generic errors, OpenAPI filler, a11y/perf theater, N+1 queries, and AI comment noise. Pairs with code-review (noslop dimension) and polyglot-copywriter for review/MR prose. Use when generating or auditing code that must fit this repo—not a paste. Subskill noslop-code is comments-only. Default mode: during; after mode for audits.

1 other project uses a version of this.

Adopted by

Most recently taken up by

owayo/nosloptheir own version, first seen Oct 25, 2026

Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
owayo/noslop★ 13same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository57 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/comments.mdcCursor rule
- .cursor/rules/commit-messages.mdcCursor rule
- .cursor/rules/git-workflow.mdcCursor rule
- .cursor/rules/manage-stack.mdcCursor rule
- .cursor/rules/no-worktrees.mdcCursor rule
- manage-stackSkill
- convert-as-skillSkill
- create-agentSkill
- create-agents-mdSkill
- create-commandSkill
- create-hookSkill
- create-ruleSkill
- create-skillSkill
- retrospectiveSkill
- super-architectureSkill
- super-cachingSkill
- super-elixirSkill
- super-nodejsSkill
- super-protobufSkill
- super-tech-blueprintSkill
- atomic-semantic-commitSkill
- code-reviewSkill
- create-bruno-collectionSkill
- create-documentationSkill
- create-ticketsSkill
- ready-specSkill
- write-adrSkill
- write-changelogSkill
- write-mr-descriptionSkill
- write-planSkill
- write-postmortemSkill
- write-runbookSkill
- output-saversSkill
- safe-refactorSkill
- tddSkill
- verifySkill
- get-movingSkill
- later-listSkill
- standupSkill
- challenge-meSkill
- codebase-learnerSkill
- researchSkill
- second-opinionSkill
- traceSkill
- color-kitSkill
- design-system-kitSkill
- diagramSkill
- infographicSkill
- product-polish-workflowSkill
- prototype-wireframeSkill
- ui-ux-kitSkill
- evidenceSkill
- find-skillsSkill
- handoffSkill
- rumblingSkill
- use-levistackSkill

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
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

Distinctive:
Ask the user (in their chat language) when noslop applies: during the work or after.
line 31
Distinctive:
Do this first; load only what the task needs.
line 37
Distinctive:
Every layer, type, and error shape must pass the purpose test (R-31).
line 73
Distinctive:
Before adding a file, layer, or dependency: what does this serve?
line 77
Distinctive:
Done: when: rules pass; edge paths are real.
line 81
Very specific:
Run delivery-gate.md every pass on executable surfaces.
line 115

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Noslop

No Slop: tight, intentional code and messages for AI-assisted work

Apply when generating or editing executable code, API/CLI copy, OpenAPI, config, migrations, or comments. Code must fit this repo's boundaries and vocabulary, not a tutorial paste.

Ask the user (in their chat language) when noslop applies: during the work or after. Auto mode: during.

Rule: noslop.md. Gate order: workflow-gates.md.

Step 0: detect the domain

Do this first; load only what the task needs. Index: references/domains/README.md.

If the diff or task touches…	Domain	Load
Handlers, services, workers, jobs, domain logic	backend	backend.md + core pack below
HTTP routes, status codes, envelopes, OpenAPI, webhooks	api	api.md + core pack
SQL, ORM, migrations, indexes, transactions	database	database.md + core pack
Components, CSS, layout, client state, a11y	frontend	frontend.md + core pack
Env, feature flags, IaC snippets, deploy config in diff	infra-config	infra-config.md + core pack
Test files, fixtures, mocks, assertions	tests	tests.md + core pack
README/CHANGELOG-only or pure docs with no code surface	docs	docs-exclusions.md — prose skills instead
Code comments only (no logic edits)	comments	Core delivery gate + `noslop-code`

Core pack (all executable domains): slop-patterns.md + mandatory-rules.md + delivery-gate.md. User-facing CLI/API copy: add principles-and-cli-copy.md.

Package layout

noslop/
├── SKILL.md                      # router (this file)
├── references/
│   ├── core/                     # R-01–R-38, gates, patterns, workflow
│   └── domains/                  # per-layer checklists
├── templates/                    # architecture read, audit, AGENTS pointer
└── skills/
    └── noslop-code/        # comment hygiene; never touches executable code

What this is (and is not)

Filter, not a framework mandate.

Does not require DDD, microservices, or Clean Architecture unless the repo already uses them.
Does not ban interfaces, middleware, or retries — rejects patterns without purpose.
Does not replace polyglot-copywriter for human-facing prose (MR bodies, essays).

Every layer, type, and error shape must pass the purpose test (R-31). Details: mandatory-rules.md.

Core principle

Before adding a file, layer, or dependency: what does this serve? If the answer is "every tutorial does this" or "it's best practice", rework.

Swap-company test: if the product name changed, would this module still belong in this codebase?

Done when: rules pass; edge paths are real; R-35 verify evidence exists in the current turn (a command run this turn, not memory).

Craftsmanship standard

Id	Standard
C-1	Intentionality — "AI default" is a red flag
C-2	Functional completeness — real work or honest errors, no fake success
C-3	Content-driven structure — modules exist for this product's flow
C-4	Resilience — empty, validation, timeout, rate limit, upstream failure
C-5	Evidence over claims — metrics and compliance real or omitted

Principles (KISS/YAGNI/deletion test): principles-and-cli-copy.md.

Two usage modes

When do you want to use noslop?
DURING — apply mandatory-rules.md while coding; finish with delivery-gate.md.
AFTER — write audit using templates/audit-after-mode.md; user picks finding numbers to fix.

Templates

Task	Load
Architecture read (before backend code)	templates/architecture-read.md
After-mode audit file	templates/audit-after-mode.md
First-run AGENTS.md pointer	templates/agents-md-pointer.md

Before coding (backend-heavy work)

Fill templates/architecture-read.md — required at delivery for handler/API/database changes.

Delivery gate

Run delivery-gate.md every pass on executable surfaces. Comments only: delivery gate + noslop-code checklist.

When invoked by code-review

Scope: MR review comment bodies and user-facing API/error copy flagged in the diff — not executable code inside suggestion fences.
Mode: after — audit draft comment text before posting GitLab draft notes.
Inline vs summary: reject generic rollup blocks; each finding stays on its inline draft. See code-review.
Dimensions: cite rule IDs (R-XX) in findings; Dim column stays noslop. Full MR signals: review-dimensions.md §8.
Pair with polyglot-copywriter (code-review use case) for STE-simple phrasing after slop removal.

When invoked by write-mr-description

Scope: MR description markdown — not commit subjects or code paths.
Mode: after render from TEMPLATE.md; strip AI filler and unjustified breaking claims before opening the draft MR.

Old skill name

Old	Use
`noslop`	This skill (`noslop`)
`noslop-code`	`noslop-code`

Related skills

noslop-code: the task edits comments only.
code-review: review a diff with the noslop dimension.
write-mr-description: the filtered change is ready for an MR.
safe-refactor: the slop needs a structural fix, not a delete.
polyglot-copywriter: rewrite prose in comments or docs.

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.

Check your setup, free