dreeke-trust-test
Skill1 starsChanged 11 days agoNo licenceView on GitHub
Apply Robin Dreeke's 6-dimension trust framework from 'Sizing People Up' (ex-FBI Behavioral Analysis Program, 2020) to predict another person's behavior. The 6 dimensions — vesting, longevity, reliability, actions, language, stability — each with 10 positive and 10 negative signals. Use whenever the user asks to read, оценить, просчитать, профайлить, размотать a specific person — colleague, candidate, contractor, co-founder, investor, friend, romantic interest — or asks whether to trust them, whether to hire/partner/invest, whether a relationship is worth continuing. Trigger phrases — RU 'оцени человека', 'стоит ли доверять', 'что за человек', 'размотай его', 'профайл', 'просчитай', 'надёжный ли он', 'стоит ли связываться'; EN 'should I trust', 'read this person', 'gut check', 'sizing him up', 'should I hire/partner/invest'. Also fires when the user describes a person's behavior and asks what it means or what to expect next — 'странно повёл себя', 'почему он так сделал', 'подведёт ли'.
In this repository85 other files it gives its agents.
- skills/repo-task-proof-loop/AGENTS.mdAGENTS.md
- skills/repo-task-proof-loop/CLAUDE.mdCLAUDE.md
- agent-desktop-cliSkill
- agents-best-practicesSkill
- agent-transcriptSkill
- ai-stage-gateSkill
- api-connector-builderSkill
- apifySkill
- audit-instruction-systemSkill
- auto-improveSkill
- balancedSkill
- brainstormingSkill
- browser-skillSkill
- china-fashion-shoppingSkill
- chrome-cdpSkill
- cicd-speedupSkill
- coaching-session-summarizerSkill
- codebase-designSkill
- cognitive-toolkitSkill
- data-scraper-agentSkill
- data-throughput-acceleratorSkill
- deep-researchSkill
- deslopSkill
- diagnosing-bugsSkill
- dispatching-parallel-agentsSkill
- documentation-lookupSkill
- domain-modelingSkill
- eval-harnessSkill
- evals-from-sessionsSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- firecrawlSkill
- first-customer-finderSkill
- github-author-contextSkill
- github-deep-reviewSkill
- gmailSkill
- google-calendarSkill
- grillingSkill
- grill-with-docsSkill
- handoffSkill
- improve-codebase-architectureSkill
- karpathy-guidelinesSkill
- kill-ai-slopSkill
- lossless-doc-compressSkill
- loyalty-privileges-lookupSkill
- make-pr-easy-to-reviewSkill
- markdown-converterSkill
- ml-system-design-reviewSkill
- no-ai-slopSkill
- nutrient-document-processingSkill
- os-what-could-go-wrongSkill
- platform-source-researchSkill
- playwrightSkill
- ponytail-auditSkill
- ponytail-reviewSkill
- posthogSkill
- prompt-caching-playbookSkill
- prototypeSkill
- receiving-code-reviewSkill
- regex-vs-llm-structured-textSkill
- The first 60 shown.
The file
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.

