safety-net-builder
Skill1 starsChanged 35 days agoNo licenceView on GitHub
Write characterization tests that pin down the CURRENT behavior of untested legacy code before anyone changes it, establishing a regression baseline. Make sure to use this whenever someone is about to modify production/legacy code that has little or no test coverage — and ALSO when they express the worry rather than the request: "I need to change this untested function but I'm scared I'll break something", "how do I safely change code that has no tests", "what should I do first before touching this untested code", "I don't want to break production". Direct triggers: "there are no tests for this", "I need a safety net before I change X", "characterize this behavior", "pin down what this does before I touch it", "lock in current behavior", or right after change-scoper identifies an impact zone to cover. The right first move when changing unguarded code is a safety net, so trigger even when the user only voices the fear and hasn't asked for tests by name. It captures what the code ACTUALLY does today (not what it should do), flags behavior that looks buggy but pins it anyway, and does not fix anything itself — it runs before surgical-fixer or feature-grafter touch unguarded code.
In this repository35 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- board-reconcileSkill
- change-scoperSkill
- codebase-cartographerSkill
- commit-conventionsSkill
- debuggerSkill
- dynamo-bootstrapSkill
- dynamo-bootstrapSkill
- dynamo-designSkill
- dynamo-designSkill
- dynamo-probeSkill
- dynamo-probeSkill
- dynamo-rebuildSkill
- dynamo-rebuildSkill
- dynamo-repairSkill
- dynamo-repairSkill
- dynamo-reworkSkill
- dynamo-submissionSkill
- dynamo-submissionSkill
- dynamo-verifySkill
- dynamo-verifySkill
- feature-grafterSkill
- feature-integratorSkill
- grillingSkill
- intake-triageSkill
- phase-executorSkill
- pr-descriptionSkill
- product-architectSkill
- product-guideSkill
- product-state-initSkill
- quality-gateSkill
- refactor-stewardSkill
- regression-guardSkill
- root-cause-investigatorSkill
- surgical-fixerSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “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.
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.