1619 个 · 按相关度排序
Designs or reviews provenance-bound DAG attempt traces, coverage gaps, cancellation, and unknown-effect reconciliation. NOT for claiming execution completeness, deployment monitoring, or root-cause proof.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
Verify every visual-evidence artifact (screenshot/GIF/recording) attached to a PR carries a provenance manifest binding it to real daemon-backed truth — daemon port, run id, transcript head hash, agent node id, commit, and an honest real/fixture/mock source label — and that operator-control-panel PRs cover the required set of proof states. Use when gating a PR's proof artifacts before merge, auditing whether a "LIVE" visual claim is backed by a real daemon run versus a reused or fixture-backed mock, or defining the required state-coverage set for a control-panel change. NOT for the capture technique itself — headless Playwright, `screencapture -x -l`, non-interruptive capture (use port-daddy-agent-skill's visual-evidence doctrine), designing the receipt body schema an artifact attaches to (use agent-work-receipt-designer), or the broader dogfood/Potemkin product-quality bar (use multi-agent-authoring-product-bar).
中文简介正在准备中。当前显示原文说明。
Analyze a Coval accent testing report from runs across different speaker accents. Use when a user provides a Coval report URL, report export, run IDs, screenshots, or metric summary and wants evidence-backed next steps such as prompt changes, STT/confirmation adjustments, accent-robust routing, or expanded accent coverage.
中文简介正在准备中。当前显示原文说明。
Audit an existing Coval evaluation setup for coverage, misleading scores, missing evidence, judge validation and execution risk. Read-only; use when inheriting an eval or deciding whether its results support a release decision.
中文简介正在准备中。当前显示原文说明。
Analyze a Coval audio-quality testing report from runs across different voice, speaking-style, volume, interruption, and background-noise scenarios. Use when a user provides a Coval report URL, report export, run IDs, screenshots, or metric summary and wants evidence-backed next steps such as prompt changes, tool handling fixes, STT/TTS adjustments, trace setup, or expanded audio-scenario coverage.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
Build a compact Coval test set from product requirements, observed conversation failures or a coverage gap. Design realistic scenarios with separate expected behaviors, provenance and controlled voice/persona variation.
中文简介正在准备中。当前显示原文说明。
Run the pytest test suite with coverage. Accepts optional filter flags. Use after making changes to verify nothing broke.
中文简介正在准备中。当前显示原文说明。
Profound LLM citation tracker (extension). Time-series brand citation rates across ChatGPT, Perplexity, and other LLMs. Pairs with seo-seranking for triangulated AI visibility coverage.
中文简介正在准备中。当前显示原文说明。
Use when implementing features or fixing bugs with strict Test-Driven Development (TDD). Activate for coding tasks that require new functionality, refactoring, or comprehensive test coverage, especially when the user mentions TDD or Test Driven Development.
中文简介正在准备中。当前显示原文说明。
Drive Keel agent test-first or evidence-first execution for a selected OpenSpec task. Use when a task needs software tests, hardware testbench, assertions, lint, new behavior proof, regression coverage, or red/green evidence before implementation.
中文简介正在准备中。当前显示原文说明。
Use when adding or repairing Spark regression tests for asynchronous ownership, cancellation, persistence, restart recovery, or cross-surface projections. Not a coverage campaign, performance benchmark, source-text policy check, or full delivery review.
中文简介正在准备中。当前显示原文说明。
Proves a Godot 4.x build is actually green and holds its project conventions. Trigger when a GUT or GDScript result needs believing (a suite green while a script failed to parse, a one-file run that ran the whole suite, drifted CI guard counts, a coverage claim, a gate figure, a failing check someone wants softened); to review scenes, signals, awaits, threads, determinism, saves, imports or .uid files, or the upgrade rule (not the migration); to prove a simulation or balance rule; for import settings and the pixel-art render precondition; or say godotsmith (check, guard, gate, review, intake). API reference is the Godot docs'; art reads pixelsmith's; audio direction soundsmith's.
中文简介正在准备中。当前显示原文说明。
Use when adding or repairing Spark regression tests for asynchronous ownership, cancellation, persistence, restart recovery, or cross-surface projections. Not a coverage campaign, performance benchmark, source-text policy check, or full delivery review.
中文简介正在准备中。当前显示原文说明。
[51] EXECUTE. Commitment to maximum quality work with 150% coverage. Use when you need the highest quality output for critical tasks, complex problems, important decisions, or when standard work isn't enough. Triggers on "maximum quality", "150% mode", "full quality", "critical task", or when you explicitly want AI to work at its best.
中文简介正在准备中。当前显示原文说明。
[60] VALIDATE. Ensure new (staged and unstaged) changes are covered by tests at >70% and the full test suite is green. Use when asked to validate coverage for recent changes, add tests for modified code, or verify nothing else broke.
中文简介正在准备中。当前显示原文说明。
Perl testing patterns using Test2::V0, Test::More, prove runner, mocking, coverage with Devel::Cover, and TDD methodology.
中文简介正在准备中。当前显示原文说明。
Python testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.
中文简介正在准备中。当前显示原文说明。
Kotlin testing patterns with Kotest, MockK, coroutine testing, property-based testing, and Kover coverage. Follows TDD methodology with idiomatic Kotlin practices.
中文简介正在准备中。当前显示原文说明。
Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.
中文简介正在准备中。当前显示原文说明。
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
中文简介正在准备中。当前显示原文说明。
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
中文简介正在准备中。当前显示原文说明。
Django testing strategies with pytest-django, TDD methodology, factory_boy, mocking, coverage, and testing Django REST Framework APIs.
中文简介正在准备中。当前显示原文说明。