「guardrail」の検索結果

Design spec with 98 rules for building CLI tools that AI agents can safely use. Covers structured JSON output, error handling, input contracts, safety guardrails, exit codes, and agent self-description.

日本語の概要は準備中です。原文の説明を表示しています。

Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance.

日本語の概要は準備中です。原文の説明を表示しています。

Core context and guardrails for Openrind Desktop native app

日本語の概要は準備中です。原文の説明を表示しています。

Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode". (gstack)

日本語の概要は準備中です。原文の説明を表示しています。

AEM as a Cloud Service Java/OSGi best practices, guardrails, and legacy-to-cloud pattern transformations. Use for Cloud Service–correct bundles, deprecated APIs, schedulers, ResourceChangeListener, replication, Replicator, JCR observation (javax.jcr.observation.EventListener), OSGi Event Admin (org.osgi.service.event.EventHandler), DAM AssetManager, BPA-style fixes, HTL (Sightly) Cloud SDK lint warnings (data-sly-test redundant constant value comparison), or any time you need the detailed pattern reference modules under this skill.

日本語の概要は準備中です。原文の説明を表示しています。

Author the project's non-negotiable engineering rules — the constitution that every feature spec, plan, and implementation must satisfy. Load when the user asks to write a constitution, define project rules, set engineering invariants, write project standards, define non-negotiables, capture agent guardrails as policy, or when spec-driven-development orchestrator routes here. Also triggers on "project constitution", "engineering invariants", "non-negotiable rules", "project policy", "set our standards", "/constitution". Output: docs/constitution.md. The third strategic artifact alongside AGENTS.md (agent behavior) and product-soul (strategy).

日本語の概要は準備中です。原文の説明を表示しています。

Capture actionable learnings that emerge during conversation — when the agent or user discovers that a skill, a set of skills, or a process needs to be updated based on what's happening in the current chat. Sub-skill of the learn-from orchestrator. Load when the user says "we should update the skill for this", "this should be a skill rule", "add this as a gotcha", "the skill should know about this", "update the process for this", "remember this for next time", "this is important for the skill". Also triggers when the agent notices a skill's guidance was wrong or incomplete, a process step failed or was unnecessary, a new pattern emerged, a guardrail was missing, a workaround became a pattern, or a debugging session reveals a gap.

日本語の概要は準備中です。原文の説明を表示しています。

Run a structured retrospective after development-phase runs of your product's agents — interview the owner in plain language about what went well and poorly, draft ranked improvement hypotheses, then design and run small n=1/n=2 experiments with pre-declared success criteria, guardrails, stop conditions, and a cost/ROI kill-switch. Load when the user says how did that run go, retro this run, the agent output was bad, what should we improve, draft hypotheses, run a small experiment, or after repeated dev runs of an agentic system produce uneven quality. Priority: output quality over performance over cost, each with diminishing-returns stops. NOT a product A/B test (experimentation), NOT coding-agent harness repair (harness-evolution), NOT production-scale learning (runtime-learning-loop).

日本語の概要は準備中です。原文の説明を表示しています。

Write a rigorous, decision-grade experiment spec — falsifiable hypothesis, primary metric, guardrails, randomisation unit, exposure definition, method (A/B, holdout, switchback, quasi-experiment, MAB), MDE/duration plan, peek policy, validity threats, and pre-committed decision rule. Platform-agnostic. Load when the user has a candidate experiment and needs to spec it before launch, or says "spec this experiment", "write the test plan", "design this A/B test", "what's the hypothesis", "how big a sample do we need", "how long should we run this", "define the metrics for this test", or when the experimentation orchestrator routes here.

日本語の概要は準備中です。原文の説明を表示しています。

Design spec with 98 rules for building CLI tools that AI agents can safely use. Covers structured JSON output, error handling, input contracts, safety guardrails, exit codes, and agent self-description.

日本語の概要は準備中です。原文の説明を表示しています。

Autonomous DevSecOps & FinOps Guardrails.

日本語の概要は準備中です。原文の説明を表示しています。

Identifies differential m6A methylation between conditions from MeRIP-seq paired IP/input data using exomePeak2 with `bam_ip` + `bam_input` (control arm) and `bam_treated_ip` + `bam_treated_input` (treatment arm) for integrated GC-bias-aware differential calling (Liu 2022 *NAR Genom Bioinform* 4:lqac046), QNB beta-binomial test (Liu 2017 *BMC Bioinformatics* 18:387), MeTDiff HMM-based differential bundled with MeTPeak, RADAR (Zhang 2019 *Genome Biol* 20:294) with its `filterBins -> diffIP -> reportResult` workflow, and the defensible paired-symmetric case of edgeR / DESeq2 on featureCounts-on-peaks matrices when batch / lot covariates need explicit fixed-effect handling (exomePeak2's top-level API does NOT accept arbitrary covariates). Covers paired vs unpaired vs interaction designs, batch confounding (antibody lot, RNA prep, sequencing run) and the per-lot meta-analysis strategy when exomePeak2 is the primary caller, the stoichiometry-vs-expression-vs-IP-efficiency confound that all MeRIP differential methods inherit, normalisation choice (size factor on IP, on input, on per-sample IP/input ratio), the McIntyre 2020 reproducibility caveat, effect-size filtering as a guardrail against under-powered N=2 designs, and orthogonal-validation routes for absolute stoichiometry (GLORI / SAC-seq / m6Anet `mod_ratio`). Use when comparing m6A levels across two or more conditions, choosing between exomePeak2 / QNB / RADAR / MeTDiff for a given design, handling batch confounding when exomePeak2's API is too rigid, normalising against input properly, distinguishing real hyper- / hypo-methylation from expression-level shifts, applying effect-size thresholds, interpreting volcano plots of differential peaks, or planning a follow-up orthogonal stoichiometry validation.

日本語の概要は準備中です。原文の説明を表示しています。

Analyze a Coval adversarial / red-team testing report and turn it into an agent-hardening plan. Use when a user provides a Coval report URL, report export, run IDs, screenshots, or a per-scenario scorecard from an adversarial sweep and wants evidence-backed next steps such as prompt/guardrail changes, refusal hardening, verification fixes, escalation routing, or expanded attack coverage.

日本語の概要は準備中です。原文の説明を表示しています。

Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance.

日本語の概要は準備中です。原文の説明を表示しています。

Design spec with 98 rules for building CLI tools that AI agents can safely use. Covers structured JSON output, error handling, input contracts, safety guardrails, exit codes, and agent self-description.

日本語の概要は準備中です。原文の説明を表示しています。

Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.

日本語の概要は準備中です。原文の説明を表示しています。

Knowledge and guardrails for the mise + fnox + infisical secrets toolchain, covering secret injection, secret providers, and env var hygiene.

日本語の概要は準備中です。原文の説明を表示しています。

Establishes git workflow guardrails including conventional commits, commit message hooks, branch naming conventions, PR templates, and code review processes. Provides hook configurations, workflow templates, and emergency bypass instructions. Use when users request "setup git hooks", "enforce commit conventions", "add PR templates", or "standardize git workflow".

日本語の概要は準備中です。原文の説明を表示しています。

Design, build, deploy, and operate production AI agent systems — single agents, multi-agent teams, and autonomous swarms. Complete methodology from agent architecture through orchestration, memory systems, safety guardrails, and operational excellence.

日本語の概要は準備中です。原文の説明を表示しています。

Produces a narrow-interval quality signal for a WinDAGs skill that a third party can verify without inspecting model weights or method internals. The mechanism is attribution-kNN over a tamper-evident outcome log (task→skills→accept/reject store), combined with a conformal-prediction calibration certificate that provides a formal coverage guarantee. Thompson/Beta sampling is explicitly rejected as a category error: it produces a selection signal for stationary i.i.d. rewards, not an attestation signal for context-dependent LLM output quality. The resulting bundle — outcome-log Merkle root + conformal threshold + optional TEE guardrail signature — constitutes a "narrow-interval trust" credential: verifiable, bounded, and internals-opaque.

日本語の概要は準備中です。原文の説明を表示しています。