Individual skill
create-formal-verification-skill
Find the guarantee in a repo where a bug would hurt users most and tests are weakest, verify it with a fitting formal tool, and leave a proven project-local verify skill that reruns the check. Triggers: /create-formal-verification-skill, "prove this invariant", or a request to model-check a race.
plugins/requie/endostack/skills/create-formal-verification-skill/SKILL.md
Source commit d780783eba4ecc7c8b9429f95c9362df95f07c61
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 4, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 1,533
- Repository last updated
- Nov 7, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai-coding Repository topic
- awesome Repository topic
- awesome-list Repository topic
- codex Repository topic
- codex-plugins Repository topic
- openai Repository topic
- codex-skill Repository topic
- codex-skills Repository topic
- marketplace Repository topic
- codex-marketplace Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 7,187 bytes
Read excerpt
# create-formal-verification-skill
An example-based test exercises only the cases someone wrote down. A formal check exhausts a stated scope, which may be all interleavings of a model, all inputs below a size bound, or the entire input space. Apply one where that gap matters, then leave a skill that later agents rerun each time they edit the covered code.
Assume the user cannot read TLA+ or any proof language. Report everything using the names and concepts of the code itself, so they can judge the outcome and decide what to do without learning the tool.
Good targets: concurrency, retries, state machines, parsers, permission checks, and unsafe memory access, anywhere tests feel thin. If the area already has a generated verify skill, use the `maintain-formal-verification-skill` skill ([../maintain-formal-verification-skill/SKILL.md](../maintain-formal-verification-skill/SKILL.md)) instead.
## 1. Choose what to verify
Read the code first, and put questions to the user only where the code leaves a gap. When the user pointed at a particular area or defect, begin with it.
The best candidate is a guarantee the code makes, whose failure hurts users, and whose failing case tests rarely reach. Pick the highest-value candidate in the codebase, not the easiest to formalize. Security guarantees often rank highest: "a revoked token is never accepted after revocation commits", "a payout is never sent twice for one invoice", "a path from user input never resolves outside the upload root".