verify-changes
Skill0 starsChanged 3 days agoMITView on GitHub
Run the checks that must pass before finishing or committing any code change in this repo (lint, type check, tests, production build) and review the diff for project-rule violations. Use before every commit or before reporting a task as done.
- Reads credentials
13 other projects use a version of this.
Adopted by
Most recently taken up by
- mab-go/xmind-mcptheir own version, first seen Nov 8, 2026
- FilenCloudDienste/filen-rstheir own version, first seen Oct 9, 2026
- vudovn/ag-kittheir own version, first seen Oct 8, 2026
- idaholab/moosetheir own version, first seen Oct 8, 2026
- foru17/neko-mastertheir own version, first seen Oct 8, 2026
- foru17/clash-mastertheir own version, first seen Oct 8, 2026
Used with
Projects with it also use intelligent-routing, design-spec 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.
SKB3002Skillintelligent-routing
Automatic agent selection and intelligent task routing. Analyzes user requests and automatically selects the best specialist agent(s) without requiring explicit user mentions.
Also in 3 projects that use this
jornalistainclusivoSkilldesign-spec
How to author a DESIGN.md file — the machine-readable design-token + human-rationale format that must exist before any UI is built. YAML front-matter token schema (colors, typography, spacing, rounded, components), type system, token references, and canonical section order.
Also in 3 projects that use this
xenitV1Skillbash-linux
Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.
Also in 3 projects that use this
xenitV1Skillred-team-tactics
Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting.
Also in 3 projects that use this
xfstudioSkillrust-pro
Master Rust 1.75+ with modern async patterns, advanced type system
Also in 3 projects that use this
- +7 more from xenitV1
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- vudovn/ag-kit★ 8.2ksame name
- vudovn/antigravity-kit★ 8.2ksame name
- foru17/clash-master★ 4.2ksame name
- foru17/neko-master★ 4.2ksame name
- idaholab/moose★ 2.4ksame name
- h0x91b/dev-3.0★ 333same name
- FilenCloudDienste/filen-rs★ 104same name
- mab-go/xmind-mcp★ 9same name
- zzfancitizen/agent-skills-self-learning-sample★ 3same name
- 26zl/universal-agent-skills★ 2same name
3 more not listed
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 repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- add-page-sectionSkill
- database-changeSkill
- portfolio-security-checkSkill
- add-page-sectionSkill
- database-changeSkill
- portfolio-security-checkSkill
- verify-changesSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Run all four checks and keep going after a failure, so you see every problem at once:
- Distinctive: line 31
If a check already failed before your change, say so in your report instead of fixing unrelated code.
- Distinctive: line 39
Run git diff and check:
“Common” is measured: kept by at least 6 in 10 of the 11 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.
Files
Verify changes
The main branch syncs to Lovable and deploys from there, so every commit must
leave the site in a working state.
1. Run the checks
Run all four checks and keep going after a failure, so you see every problem at once:
bun run lint
bunx tsc --noEmit
bun run test
bun run build- Fix the errors your change introduced. Do not silence a rule with
eslint-disableor@ts-ignoreunless you explain the reason in a comment. - Known lint baseline: much of the existing code (generated by Lovable) is
not Prettier-formatted, so
bun run lintalready reports manyprettier/prettiererrors onmain. Do not reformat the whole repo as part of an unrelated task. Instead, lint only the files you changed, for examplebunx eslint src/routes/things.tsx, and make those files clean. On Windows withcore.autocrlf=true, ignoreDelete ␍errors: they come from the checkout, not from the committed files. - If a check already failed before your change, say so in your report instead of fixing unrelated code.
src/routeTree.gen.tsis regenerated by the dev server or the build. If you added or removed a route, run the build so the file updates, and commit the regenerated file.
2. Review the diff
Run git diff and check:
- No edits to generated files (
routeTree.gen.tsexcepted when regenerated,src/integrations/supabase/types.ts,src/components/ui/*,drizzle/meta/*). - No content hard-coded into components; content belongs in the database.
- No secrets, service-role keys or new
.envvalues. - New public routes have a complete
head(): title, description, og tags. - Database changes come as a new migration file with RLS. Old migrations are unchanged.
- No leftover
console.logor debug code.
3. Report
State which checks passed, which failed and why, and anything you could not verify, for example a migration that only Lovable Cloud can apply.
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
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.

