Results for “pass-at-k”

Detect Kerberoasting attacks by monitoring for anomalous Kerberos TGS requests targeting service accounts with SPNs for offline password cracking.

Provides a formal evaluation framework for Claude Code sessions, implementing eval-driven development (EDD) principles to define pass/fail criteria, measure reliability with pass@k metrics, and create regression test suites.

Iterate on a pull request until actionable CI checks pass and high/medium review feedback is addressed, stopping at human approval, draft, or merge gates.

Quality Gates

Rule (adak-rule)

Runs and writes tests, verifies behavior, and orchestrates two-pass TDD across scoped modes, blocking on quality gates and never editing production code.

Executes small ad-hoc tasks with GSD guarantees, spawning planner and executor agents, tracking tasks in .planning/quick/, and updating STATE.md. Supports composable flags for discussion, research, plan-checking, and verification.

Implements code features phase by phase from a JSON or Markdown plan, with configurable unit-test and quality-gate choices, token-budgeted execution, and resumable state.

Walk a business/UAT approver through a plain-language demo of a verified feature and capture business acceptance signoff.

Implements a feature phase by phase from a phased JSON or Markdown plan, with configurable unit-test and quality-gate choices per phase, token-budgeted execution, resumable state, and TDD handoff.

Runs full Trailmark structural analysis by building a graph and computing pre-analysis passes for hotspots, taint, blast radius, privilege boundaries, and attack surface.

Patch code to bypass checksums, global state, and validation checks that block fuzzer progress, using conditional compilation for C/C++ and Rust.

Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.

Runs and writes tests for a project, supporting unit, integration, and end-to-end scopes, plus two-pass TDD orchestration with quality-gate checks and regression sweeps.

Audits code quality against a shared contract, producing structured findings and blocking pipeline phases on critical issues without modifying code.

Assesses organizational readiness for post-quantum cryptography migration per NIST FIPS 203/204/205 standards, performs cryptographic inventory scanning, evaluates hybrid TLS configurations, and validates CRYSTALS-Kyber and CRYSTALS-Dilithium readiness.

Universal transformation λ(ο,K).τ with recursive self-improvement. USE WHEN routing reasoning, validating knowledge graphs, preparing CICM/ANZCA examinations, or when self-improvement of reasoning/architecture/context is required. Routes queries through R0-R3 complexity pipelines, validates topology (η≥target) and governance (KROG), emits per style (Φ), and compounds learnings into knowledge K. Triggers on complexity assessment, multi-step reasoning, examination mode, or /λ invocation.

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles.

Rule (ahak-rule)

Use the pk-doctor skill to run the aggregator health check and resolve

Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.

Rule (agak-rule)

Walks a person through code changes one step at a time in conversation, starting at the entry point and following the flow that changes, showing a small chunk per step and explaining it in plain language. Defaults to the current branch's changes, and walks the code from the perspective of any context provided instead — a file, directory, symbol, pull request, plan, or ticket. Use when someone wants to be walked through, taught, paced through, or shown around code or a branch step by step, or to learn how a change works before reviewing or extending it. Stops after every step and waits, so the learner sets the pace. Paces through code that already exists and builds nothing — to build new work while being paced through it, use pairing. Does not produce a written overview to read alone — use code-overview. Does not review code quality — use code-review. Does not diagnose bugs — use investigate.

Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles.

Executes authorized attack simulations against Active Directory environments to identify misconfigurations, weak credentials, dangerous privilege paths, and exploitable trust relationships that could lead to domain compromise.

Processes a PR's review comments (Copilot or human), classifies them, applies the fixes that belong, replies to each thread, and pushes. Use whenever the user says "address the review", "fix what Copilot said", "handle the comments", mentions Copilot already reviewed a PR, or passes a PR number/URL with pending reviews — or in Spanish "revisá los comentarios", "arreglá lo que dijo Copilot", "atendé el review".