Results for “attribute-agreement”

UAT Sign-off

Create and maintain lightweight Architecture Decision Records as agent-readable decision memory — what was decided, why, and which alternatives were rejected. Use when "record this decision", "set up ADRs", "the agent keeps suggesting Y again". Docs vs code drift → plan-docs-sync. Session state → handoff.

Compare, cross-review, and merge competing plans from multiple agents into one executable direction with a clear handoff.

Designs an approval-gated feature specification from approved requirements, covering architecture decisions, component boundaries, quality constraints, and definition of done.

TRAK: Attributing Model Behavior at Scale

Maintains persistent project context for Business Central AL extensions across sessions, developers, and AI agents. Combines two complementary mechanisms: Architecture Decision Records (ADRs) that capture why technical decisions were made, and Session Handoff documents that capture where the project is right now. Generates, updates, and queries both document types. Use this skill whenever starting a new coding session on an existing project, ending a session and need to document progress, onboarding a new developer or AI agent to an existing codebase, explaining why a technical decision was made, wondering why something is designed a certain way, resuming work after a break, or handing off work between team members. Also trigger when the user says 'document this decision', 'why is this designed like this', 'where did we leave off', 'catch me up', 'what was decided', 'create an ADR', 'end of session', 'handoff', or 'context for next session'.

Use with analysis-agent or task-agent for task-local transaction, isolation, and conflict decisions. Do not use without a transaction decision or as task owner.

Design and verify auditable human oversight, approval gates, escalation paths, and safe state transitions for AI agent workflows. Use when deciding which agent actions require review, adding approve/reject or dual-control flows, preventing unauthorized autonomous effects, creating decision records, reducing rubber-stamping, or recovering safely from rejected, expired, or failed actions.

Use this when the team needs to define permissions, roles, membership rules, resource ownership, or action-level authorization separate from authentication choice. Trigger on requests about access models, RBAC, ABAC, tenancy, or protected operations.

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

Use when designing or auditing AI product human-in-the-loop — write approval, proposal accept/reject, action confirm, spend caps, run detail, memory capture, or any AI action with irreversible blast radius. Trigger on confirmation UX, undo, cost-before-act, show-the-plan, citations, or keeping the owner in control.

Provides guidelines and best practices for aggregates and aggregate roots, referencing detailed documentation.

Action (apaz-action)

NIH grant research skill for clinical researchers. Grill-me intake (research idea + career stage + preliminary data + environment + submission posture + known institute targets) locks down the funding strategy before any search runs. Runs a 5-facet Consensus positioning analysis (with draft Significance/Innovation language), maps the research to the right NIH institutes and study sections via RePORTER, finds NOSIs and funded overlap, and produces an editable Word document (.docx) with budget/scope-aware mechanism recommendations, submission timelines, and a mandatory program officer recommendation. Use when the user asks about research funding or makes any grant-related request (e.g., 'grants for [topic]', 'find grants for my research idea', 'what grants match my research', 'help me find NIH funding', 'grant opportunities for my research'). NIH-only scope — non-NIH funders (PCORI, DOD CDMRP, VA, foundations) are out of scope and flagged at intake.

从一份或多份现有配置抽取可审阅的 agent-config.yaml，并跨 Windows、Linux、macOS 与 WSL 声明式同步 Codex ~/.codex/config.toml 和 Claude Code ~/.claude/settings.json。用于导入、去重、解决冲突、剔除配置项、初始化、检测、校验、渲染、预览差异、应用、检查状态或诊断；不用于凭据、登录状态、项目级配置、~/.claude.json、skills、agents、hooks 或 MCP 配置。

Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.

Generates structured Given/When/Then acceptance criteria for a user story or feature slice. Use when translating product requirements into testable scenarios that cover the happy path, edge cases, error states, and non-functional expectations for engineering handoff and QA.

Rule (afak-rule)

Researches authoritative APIs and data sources for a project, producing per-API docs, a data catalog, and an integration blueprint for a React + Supabase + Vercel + AI stack.

Action (afaz-action)

Drafts intellectual property assignment agreements transferring patents, trademarks, copyrights, and trade secrets. Covers conveyancing language, registration recordation, consideration, representations and warranties, and post-closing obligations. Use when drafting IP assignments, asset purchase IP transfers, or technology transfer documents.

Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings. Use when defining red-team rules of engagement, assessing prompt injection or excessive agency, testing tool and identity boundaries, evaluating memory or cross-agent attacks, scoring a campaign, or verifying remediation in an approved environment.

Analyze an API, schema, migration, or compatibility decision with `analysis-agent`, or implement its bounded contract change with `task-agent`. Do not select it when no data or public-contract surface is affected.

Designs the contract for an API change inside one codebase — a component's props, a function surface, URL or query parameters, an event payload, or a module boundary — through a discovery pass, an options document with one recommendation, a question round, and an adversarial validation round, with every element of the contract justified from one stated goal. Use when you want to design, shape, decide, or nail down an interface, contract, signature, or API change for a capability you can already describe, sized for roughly one pull request. Produces a design document and changes no code. Does not specify what a feature should do — use plan-a-feature. Does not plan delivery or sequencing — use plan-implementation. Does not assess the architecture of existing code — use architectural-analysis. Does not write the code — use tdd. Does not restructure existing code — use refactor. Runs its rounds without pausing for review; to review each round as it lands, use pairing.

融合分类系统与规则抽象能力，构建基于规则的分类体系，支持规则驱动的分类需求和规则执行。

Scores real estate leads based on engagement, budget, timeline, and property preference matching

Benchmarks automatic post-editing (APE) models on WMT'18 SMT, SubEdits, and MLQE-PE datasets, reporting BLEU, ChrF, and TER scores computed with SacreBLEU and TERCOM.

Imported skill approval from langchain

Feature specification creation from codebase research. Produces requirements, acceptance criteria, architecture decisions, implementation plans, and risk analysis.

Give a decisive, project-grounded point of view in the subject's own shape: a graded verdict on an external-adoption question, a holistic take on a document, or a position on a user-supplied approach set. Use for a solo POV, a mid-session second opinion, a named-peer cross-check, any request to consult other models or reconcile their opinions, an `oracle` panel, or a correction-cost-gated proactive cross-check offer. Not for findings review (use ce-doc-review), neutral explainers, or generating options (use ce-ideate or ce-brainstorm).

Record a decision: finalized → ADR (optionally rule + guide or spec + plan); open proposal → RFC. Use for 'we decided', 'record this decision', 'make it a standard', 'draft an RFC', 'should we switch to Y'. Not for feature planning or documenting existing code.

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md. Identifying inconsistencies, duplications, ambiguities, and underspecified items.

Applies Google's E-E-A-T framework to structure analysis, guide decision-making, and improve search visibility outcomes.

`analysis-agent`/`task-agent`/`review-agent`: use when endpoints, payloads, errors, auth, pagination, idempotency, or compatibility need a contract; skip when APIs are unchanged.

Syncs key-value preferences and state across multiple agents using a shared TiDB Zero database, with optional auto-provisioning of a free ephemeral database.