Contractual Skills: A GovernSpec Design Framework for Enterprise AI Agents

• URL: http://arxiv.org/abs/2605.22634v2
• Date: Sun, 24 May 2026 12:02:09 GMT
• Title: Contractual Skills: A GovernSpec Design Framework for Enterprise AI Agents
• Abstract summary: This paper proposes contractual skills, a GovernSpec-inspired design framework for organizing SKILL.md files as readable task contracts.<n>The framework clarifies the boundary between contractual skills, GovernSpec YAML contracts, Model Context Protocol (MCP) surfaces, tool adapters, runtime guardrails, tracing, and evaluation systems.
• Score: 8.419155861590548
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Skills have become a practical packaging mechanism for agent instructions, workflows, scripts, and reference materials. In enterprise settings, however, a skill often needs to express more than task guidance: goals, input boundaries, permissions, human approval points, evidence requirements, output contracts, quality criteria, verification steps, and handoff rules. This paper proposes contractual skills, a GovernSpec-inspired design framework for organizing SKILL.md files as readable task contracts while preserving lightweight skill discovery and progressive loading. The framework clarifies the boundary between contractual skills, GovernSpec YAML contracts, Model Context Protocol (MCP) surfaces, tool adapters, runtime guardrails, tracing, and evaluation systems. We evaluate the framework with three offline empirical studies. The first text-generation experiment covers three enterprise skills, fifteen synthetic tasks, four instruction conditions, and eight generation models, producing 960 outputs and 1680 cross-judge score records. The second study is a public-skill A/B expansion: eight public skills are compared with contractual rewrites across forty-eight synthetic tasks, six generation models, two repeats, 1152 outputs, and two complete judge files. In this setting, contractual skills raise mean quality from 4.692 to 4.914 and reduce critical-error rate from 0.083 to 0.013. The third study is an offline tool-calling challenge with eight models and 192 simulated tool-call records. The results suggest that contractual skills are best understood as a governance layer that makes task intent, boundaries, and acceptance criteria explicit, not as a standalone safety mechanism.

Related papers

• VASO: Formally Verifiable Self-Evolving Skills for Physical AI Agents [57.240036084348354]
  We introduce VASO, a framework for verification-guided self-evolution of robot skill contracts.<n>VASO verifies logically inconsistent skill contracts, then verifies plans induced by the skill against global and local temporal specifications.<n>On Clearpath Jackal and PX4 quadcopter tasks, VASO reaches 97.2% formal-specification compliance using fewer than 100 optimization samples.
  arXiv  Detail & Related papers  (2026-06-03T20:02:35Z)
• When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems [7.628682710807044]
  LLM agents increasingly rely on community-contributed skills that expand an agent's operational capability set.<n>We study a core safety problem in agentic AI systems: whether individually safe skills can compose into unsafe installed skill sets.<n>We present SkillReact, a compositional security measurement framework with three components.
  arXiv  Detail & Related papers  (2026-05-30T00:38:07Z)
• SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents [15.669318649782285]
  We introduce SkillGenBench, a benchmark for evaluating skill generation pipelines under a unified protocol.<n>A generator receives raw corpora and produces standardized skill artifacts, which are then executed under fixed harnesses.<n> Experiments across a range of skill-generation methods and backbones show substantial performance variation.
  arXiv  Detail & Related papers  (2026-05-18T17:28:36Z)
• SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs [70.1970574147839]
  We propose SKILLGRAPH, a framework that represents reusable skills as nodes in a directed graph.<n>SKILLGRAPH retrieves not just individual skills, but an ordered skill subgraph that can guide multi-step decision making.<n> Experiments show that SKILLGRAPH achieves state-of-the-art performance against memory-augmented RL methods.
  arXiv  Detail & Related papers  (2026-05-12T12:21:49Z)
• FORTIS: Benchmarking Over-Privilege in Agent Skills [68.34663362794069]
  We present a benchmark that evaluates over-privilege in agent skills across two stages.<n>We find that over-privileged behavior is the norm rather than the exception.<n>The results indicate that the skill layer, far from containing agent behavior, is itself a primary source of privilege escalation in current systems.
  arXiv  Detail & Related papers  (2026-05-09T20:57:18Z)
• The Productivity-Reliability Paradox: Specification-Driven Governance for AI-Augmented Software Development [0.0]
  Controlled studies report 20-56% productivity gains on well-scoped tasks, while the most rigorous RCT documents a 19% slowdown for experienced developers.<n> telemetry across 10,000+ developers shows 98% more pull requests but 91% longer review times with flat delivery metrics.<n>This paper argues these findings constitute the Productivity-Reliability Paradox (PRP): a systematic phenomenon emerging from non-deterministic code generators and insufficient specification discipline.
  arXiv  Detail & Related papers  (2026-05-01T23:37:50Z)
• From Context to Skills: Can Language Models Learn from Context Skillfully? [56.5857437218136]
  Ctx2Skill is a self-evolving framework that autonomously discovers, refines, and selects context-specific skills.<n>It can be plugged into any language model to obtain better context learning capability.
  arXiv  Detail & Related papers  (2026-04-30T09:53:15Z)
• From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills [5.327990835740087]
  Scheduling- Structural-Logical (SSL) representation disentangles skill-level scheduling signals, scene-level execution structure, and logic-level action/resource-use evidence.<n>We instantiate SSL with an LLM-based normalizer and evaluate SSL-derived representations in two tasks, Skill Discovery and Risk Assessment.
  arXiv  Detail & Related papers  (2026-04-27T04:25:15Z)
• KWBench: Measuring Unprompted Problem Recognition in Knowledge Work [0.0]
  KWBench is a benchmark for unprompted problem recognition in large language models.<n>It can identify a professional scenario before attempting to solve it.<n>It contains 223 tasks sourced from practitioners across acquisitions, contract negotiations, clinical pharmacy, organizational politics, fraud analysis, and incentive design.
  arXiv  Detail & Related papers  (2026-04-17T07:04:54Z)
• Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents [66.97968363332465]
  We introduce Claw-Eval, an end-to-end evaluation suite addressing all three gaps in agent benchmarks.<n>Claw-Eval comprises 300 human-verified tasks spanning 9 categories across three groups.<n>Every agent action is recorded through three independent evidence channels.
  arXiv  Detail & Related papers  (2026-04-07T17:43:18Z)
• SoK: Agentic Skills -- Beyond Tool Use in LLM Agents [6.356997609995175]
  Agentic systems increasingly rely on reusable procedural capabilities, textita.k.a., agentic skills, to execute long-horizon reliably.<n>This paper maps the skill layer across the full lifecycle (discovery, practice, distillation, storage, composition, evaluation, and update)<n>We analyze the security and governance implications of skill-based agents, covering supply-chain risks, prompt injection via skill payloads, and trust-tiered execution.
  arXiv  Detail & Related papers  (2026-02-24T13:11:38Z)
• Before the Vicious Cycle Starts: Preventing Burnout Across SOC Roles Through Flow-Aligned Design [3.9436596316632073]
  Flow theory suggests that when job demands misalign with practitioner capabilities, work becomes overwhelming or tedious rather than engaging.<n>We analyzed 106 SOC job postings from November to December 2024 across 35 organizations in 11 countries.<n>Three patterns emerged, suggesting organizations prioritize collaboration over technical capabilities.
  arXiv  Detail & Related papers  (2026-02-16T10:00:06Z)
• SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks [61.89812116484928]
  Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time.<n>We present SkillsBench, a benchmark of 86 tasks across 11 domains paired with curated Skills and deterministic verifiers.<n>We show curated Skills raise average pass rate by 16.2 percentage points(pp), but effects vary widely by domain.<n>Self-generated Skills provide no benefit on average, showing that models cannot reliably author the procedural knowledge they benefit from consuming.
  arXiv  Detail & Related papers  (2026-02-13T07:06:06Z)
• SOPBench: Evaluating Language Agents at Following Standard Operating Procedures and Constraints [59.645885492637845]
  SOPBench is an evaluation pipeline that transforms each service-specific SOP code program into a directed graph of executable functions.<n>Our approach transforms each service-specific SOP code program into a directed graph of executable functions and requires agents to call these functions based on natural language SOP descriptions.<n>We evaluate 18 leading models, and results show the task is challenging even for top-tier models.
  arXiv  Detail & Related papers  (2025-03-11T17:53:02Z)
• CLOVER: A Test Case Generation Benchmark with Coverage, Long-Context, and Verification [71.34070740261072]
  This paper presents a benchmark, CLOVER, to evaluate models' capabilities in generating and completing test cases.<n>The benchmark is containerized for code execution across tasks, and we will release the code, data, and construction methodologies.
  arXiv  Detail & Related papers  (2025-02-12T21:42:56Z)
• Unearthing Skill-Level Insights for Understanding Trade-Offs of Foundation Models [61.467781476005435]
  skill-wise performance is obscured when inspecting aggregate accuracy, under-utilizing the rich signal modern benchmarks contain. We propose an automatic approach to recover the underlying skills relevant for any evaluation instance, by way of inspecting model-generated rationales. Our skill-slices and framework open a new avenue in model evaluation, leveraging skill-specific analyses to unlock a more granular and actionable understanding of model capabilities.
  arXiv  Detail & Related papers  (2024-10-17T17:51:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.