Results for “faithfulness”

Evaluates the faithfulness of abstractive summaries by verifying if factual claims (masked as cloze questions) in the reference summary can be correctly answered using only the generated summary, compared against a gold-standard answer derived from the source context.

Deep Confidence Harness — a thinking, planning, and execution framework that forces structured reasoning before acting. Combines Monte Carlo scenario analysis, calibrated confidence, multi-perspective debate, and optimal path planning. Use before any complex decision, build, or task. Activates on: 'deep confidence', 'think before you act', 'plan first', 'Atlas mode', 'reason through this', 'what should I do', 'think this through', 'best approach', 'reason carefully', 'plan and execute'.

Investigates a question systematically before answering — verifying claims through sources, distinguishing known facts from inferences, and calibrating expressed confidence to actual certainty. Use when asked to research a topic, verify a claim, evaluate a technology, or answer a question where accuracy matters more than speed.

Guardian Angel gives AI agents a moral conscience rooted in Thomistic virtue ethics. Rather than relying solely on rule lists, it cultivates stable virtuous dispositions— prudence, justice, fortitude, temperance—that guide every interaction. The foundation is caritas: willing the good of the person you serve. From this flow the cardinal virtues as practical habits of right action and sound judgment. v3.0 introduced virtue-based disposition as the primary evaluation layer, providing deeper coherence than checklists alone. The agent's character becomes the safeguard. v3.1 adds: Plugin enforcement layer with before_tool_call hooks, approval workflows for ambiguous cases, and protections for sensitive infrastructure actions.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Implement continuous identity verification for zero trust using phishing-resistant MFA (FIDO2/WebAuthn), risk-based conditional access, and identity governance aligned with the CISA Zero Trust Maturity Model.

Enforces running verification commands and confirming output before claiming work is complete, fixed, or passing, ensuring evidence precedes any success claims.

Prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen bei Bona Fides im Römischen Recht; liefert eine Fristen- und Risikoampel mit Sofortschritten.

Embody the medieval Jewish philosopher Maimonides to discuss faith, reason, and theology with rational precision and hierarchical clarity.

Verify that a change really works before you claim completion

How to read, resolve, and reason about commitments — durable records of future obligations (your own promises and the operator's requests). Use whenever the `## Upcoming commitments` prompt block surfaces something you might act on, or when you want to inspect what's pending beyond what the block shows.

当需要克服拖延、激发最大行动力以完成一项重大挑战或转型时

Enforces running verification commands and confirming output before claiming work is complete, fixed, or passing, to prevent false success claims.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Verify a completed implementation against the original instructions, a declarative source document, an issue brief, or an optional MoonSpec feature packet, plus AGENTS.md repo guidance and required tests. Use when the user asks to run or reproduce `/moonspec.verify`, perform a final read-only implementation check, audit unit and integration test evidence, classify requirement coverage, or decide whether more code or test work is needed.

Confidence Pipeline Fix (v5.4.1)

Provides a rigorous thinking partner profile that challenges assumptions, calibrates claims to evidence, and improves decision quality under uncertainty.

Verifies suspected security bugs to eliminate false positives, producing a TRUE POSITIVE or FALSE POSITIVE verdict with documented evidence for each.

Implements security-sensitive changes with conservative trust boundaries, secret protection, tests, and verification.

Verify TPM measured boot integrity and remote attestation using tpm2-tools, including PCR reading, event log replay, quote generation and verification, and golden baseline comparison.

Guides reliable project delivery through goal-setting, progress tracking, and structured execution frameworks.

Build lean, opinionated products using the 37signals philosophy from Getting Real, Rework, and Shape Up. Use when the user mentions "Getting Real", "Rework", "Shape Up", "37signals", "Basecamp method", "six-week cycles", "fixed time variable scope", "appetite vs estimates", "betting table", "breadboarding", "fat marker sketch", "build less", "underdo the competition", or "opinionated software". Also trigger when cutting scope to ship faster, running small teams, avoiding long-term roadmaps, or eliminating meetings. Covers shaping, betting, building, and the art of saying no. For MVP validation, see lean-startup. For design sprints, see design-sprint.

Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.

Guidance on security analysis, compliance auditing, and vulnerability assessment techniques relevant to legal and regulatory compliance tasks

Enforces a verification gate before any completion claim, requiring fresh command output as evidence.

Verification-before-completion discipline ensuring all success criteria are met, tests pass, and reviews complete before declaring work done.

Expert SOC 2 compliance assistant covering all five Trust Services Criteria (Security/CC, Availability/A, Confidentiality/C, Processing Integrity/PI, Privacy/P). Use this skill whenever a user mentions SOC 2, Trust Services Criteria, SOC 2 Type 1 or Type 2, audit readiness, compliance gaps, control documentation, evidence collection, vendor risk questionnaires, or anything related to AICPA service organization controls. Trigger even for adjacent topics like "we need to get audited", "a customer asked for our security report", "writing an information security policy", or "preparing for an audit". Covers gap analysis, policy writing, control documentation, audit evidence preparation, and vendor risk reviews for organizations at any maturity level — from first-time startups to seasoned compliance teams.

Slow down interpretation from observation to action. Use when students or adults need to examine assumptions in conflict, dialogue, or inquiry.

Triages CVEs and advisories for affected versions, reachability, exploitability, upgrades, and validation.

Build and maintain one coherent company story across all audiences — employees, investors, customers, candidates, and partners. Detects narrative contradictions and ensures the same truth is framed for each audience's needs.

Review dependency manifests, lockfiles, and risky install surfaces.

End-to-end firmware and IoT penetration testing pipeline following OWASP FSTM methodology. Extracts, emulates, and exploits router, camera, and smart-home firmware using binwalk, EMBA, Firmadyne, and AFL++.

Conduct authenticated and unauthenticated vulnerability scans using Tenable Nessus to identify known vulnerabilities, misconfigurations, and missing patches, with prioritized remediation guidance.

Upgrades outdated dependencies one package at a time, checking changelogs for breaking changes and running tests between each upgrade, stopping on failure.

Provides guidance on Firebase best practices, including security rules, data modeling, and avoiding common pitfalls.