simple-check
Skill1 starsChanged 43 days agoMITView on GitHub
Pre-ship review of the change just made, ending with a ship verdict. Use after finishing a feature or fix, or when the user asks to check, verify, or sanity-check changes. Reports only.
In this repository15 other files it gives its agents.
- simple-cantoneseSkill
- simple-chineseSkill
- simple-cloudflareSkill
- simple-code-reviewSkill
- simple-commitSkill
- simple-debugSkill
- simple-full-refactorSkill
- simple-launchSkill
- simple-orchestratorSkill
- simple-readmeSkill
- simple-refactorSkill
- simple-releaseSkill
- simple-restructureSkill
- simple-supabaseSkill
- simple-text-cleanupSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
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 25
Read the surrounding code and usages, not just the diff.
- Distinctive: line 26
Search for docs that mention what changed, even if they are not in the diff.
- Distinctive: line 27
Run the project's build, type check, lint, or tests when available.
≈ “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.
Files
Simple Check
Evaluate the change that was just made, not the whole codebase. Scope is the current diff (git diff and git diff --staged), or the files changed in this session if there is no diff.
Criteria
- The change is logically correct and does what was intended
- Existing functionality is intact, with no regressions, broken flows, or side effects
- Related code is updated too, such as call sites, types, and tests
- Docs match the change: README, CLAUDE.md or AGENTS.md, docs folders, and other info files. Check features, setup steps, commands, env vars, config, and file trees that the change affects
- Naming, structure, and patterns follow the repo's conventions
- Nothing is left behind, such as debug logs, commented-out code, TODOs, or secrets
Rules
- Read the surrounding code and usages, not just the diff.
- Search for docs that mention what changed, even if they are not in the diff.
- Run the project's build, type check, lint, or tests when available. If you cannot, say what was not run.
- Report only real issues you can point to. Do not pad with nitpicks.
- Report only. Do not change code unless the user asks.
Output
- Issues found, each with
file:lineand what to fix - Verdict: ready to ship, or not, and the blockers
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.