Antithesis Research
This one walks you through researching a codebase for Antithesis testing: mapping architecture, finding failure-prone areas, and cataloging testable properties as structured markdown artifacts. It prompts you upfront about external references, scans for existing SDK assertions, and runs either ensemble or single-agent workflows depending on scope. The output lands in a scratchbook with system analysis, property catalogs, deployment topology, and evaluation synthesis. Useful when you're starting an Antithesis integration from scratch or expanding property coverage after triage. The reference files are prescriptive about how to discover properties and what counts as a good safety, liveness, or reachability claim.
- skills.sh installs
- 680
- GitHub stars
- 310
- last updated
- Aug 21, 2026
Install
$ npx -y skills add antithesishq/antithesis-skills --skill antithesis-research --agent claude-codeInstalls into .claude/skills of the current project.
Files
Antithesis Research
Skill version: 2026-11-12 6ba10e2
Purpose and Goal
Research a target system and produce scratchbook artifacts that unblock the rest of the workflow. Success means:
antithesis/scratchbook/sut-analysis.mdcaptures architecture, state, concurrency, and failure-prone areasantithesis/scratchbook/property-catalog.mdlists concrete, testable properties with prioritiesantithesis/scratchbook/deployment-topology.mddescribes the minimal useful container topologyantithesis/scratchbook/properties/{slug}.mdcaptures per-property evidence trails and contextantithesis/scratchbook/property-relationships.mdmaps suspected clusters and connections between propertiesantithesis/scratchbook/evaluation/synthesis.mdrecords categorized evaluation findings and actions taken
Prerequisites and Scoping
At the start of every research run, ask the user about external references:
Before I start, are there docs, design notes, related repos, issue trackers, or anything else outside this directory tree that I should also consult? "Just this directory" is fine.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/antithesishq/antithesis-skills
- Categories
- Data Science & ML, Productivity & Planning
- First seen
- Jun 3, 2026
More from antithesishq/antithesis-skills
All 6Recommended
More Data Science & ML
medical-researchgexijin/vibeRetrieves scientific papers from PubMed and creates plain-language research summaries. Use when users ask about medical research, scientific studies, clinical t671skills.sh installs
tooluniverse-literature-deep-researchmims-harvard/tooluniverseDeep literature review — PubMed, EuropePMC, bioRxiv preprints, citation networks, evidence synthesis. Disambiguates queries, runs collision-aware searches, grad669skills.sh installs
tool-foundation-sprint-founding-hypothesisproduct-on-purpose/pm-skillsDay 2 end capstone move of a Foundation Sprint. Compresses the sprint's full strategic frame into a single canonical sentence (the Founding Hypothesis) plus an 667skills.sh installs
instagram-account-researchpostplusai/postplus-skillsResearch Instagram accounts for creator discovery, competitor profiling, and account health snapshots using hosted profile and post collection.665skills.sh installs
industry-researchrkreddyp/investrecipesComprehensive industry research skill providing methodologies, frameworks, and best practices for analyzing industry trends, key companies, market dynamics, and647skills.sh installs
pytorch-lightningdavila7/claude-code-templatesHigh-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from lap645skills.sh installs