Communitygithub.com

grahama1970/acceptance-contract

將客戶簡報、壓縮包、目錄或單一需求文件轉換為帶有類型標記的驗收合約套件,包含提取的需求、驗收檢查、開放性問題、不可變目標草稿以及由 create-report 支援的決策報告。當使用者提到 acceptance contract、brief to requirements、freeze the goal、create immutable goal、amend immutable goal、build a Battle requirements bundle 或 extract requirements from this bundle 時使用。

acceptance-contract 是什麼?

此技能用於在實作前,將簡報、工單、電子郵件、README、壓縮包或證據資料集轉換為可執行的驗收標準。它透過 `ensure` 指令作為機械性閘道:驗證現有的 `acceptance_bundle.json`,若缺少則自動提取,並在來源套件變更時封閉失敗。其 JSON 收據包含進度計量器,顯示完成百分比、檢查項目、待辦事項及下一步行動。此技能支援多種目標模式(建立草案、修改提案或不產生目標文字),並預設拒絕儲存庫根目錄,以防止實作檔案被誤用為驗收來源。可用於 Battle 平台,將產生的驗收合約作為競技場的 `acceptance_floor`,確保在模糊測試或超越合約攻擊之前先通過合約底線。

相容平台~Claude Code~Codex CLI~Cursor✓Antigravity
npx skills add https://github.com/grahama1970/agent-skills/tree/main/skills/acceptance-contract

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

acceptance-contract 是做什麼的?

在實作之前使用此技能,當簡報、工單、電子郵件、README、壓縮包或證據資料集需要轉換為可執行的驗收標準時。

用於實作工作的第一個指令:

skills/acceptance-contract/run.sh ensure <zip|directory|file> \
  --out /tmp/acceptance-contract \
  --project-name oai-trial \
  --goal-mode create

ensure 是機械性守門員:它驗證現有的 acceptance_bundle.json,若缺少則自動提取,並在提供的來源套件自凍結合約撰寫後發生變更時封閉失敗。其 JSON 收據包含一個 acceptance_contract.progress.v1 計量器,具有 percent、checks、outstanding 和 next_steps。在 ensure 返回 status=PASS 且進度計量器顯示剩餘工作之前,請勿根據簡報進行實作。

將客戶簡報、壓縮包或故意準備的規格目錄作為輸入傳入。預設情況下,CLI 會拒絕儲存庫根目錄,以防止實作檔案在不知不覺中成為驗收來源。僅在使用者明確要求全域合約時才使用 --allow-repo。

對於高風險的客戶簡報,在實作之前對簡報/壓縮包加上 acceptance_bundle.json 進行第二輪 $ask 圓桌審查。若可用,將 WebGPT 納入一位審查者。直接詢問:「這些合約需求是否正確?我們有沒有遺漏任何內容?」要求審查者檢查凍結合約中是否遺漏任何客戶義務,特別是表示類別、類型化值、邊界條件和取消資格的失敗模式。審查是建議性證據;決定性的閘道仍然擁有 PASS/FAIL 的控制權。oai-trial 的審查發現,型別化標量的涵蓋範圍還必須要求規範等價性:格式化的策略字串、僅數字的數值標量、十進制形式、科學記號和 SQLite 數值不能是分開的驗收宇宙。

它的功能

skills/acceptance-contract/run.sh extract <zip|directory|file> \
  --out /tmp/acceptance-contract \
  --project-name oai-trial \
  --goal-mode create

輸出:

  • acceptance_bundle.json — 經 pydantic 驗證的事實來源
  • acceptance_report.json — create_report.report.v1 JSON
  • acceptance_report.md — 透過 $create-report 呈現
  • IMMUTABLE_GOAL.draft.md — 目標文字草稿或修改提案

指令:

  • extract 始終從提供的來源寫入新的草案套件/報告。
  • ensure 驗證或建立凍結合約,並拒絕過時的來源雜湊值。
  • validate 僅驗證現有的 acceptance_bundle.json,並列印進度計量器。
  • status 讀取現有的 acceptance_bundle.json,並僅列印機器可讀的進度計量器。

目標政策

預設行為是草案,不變更。

  • --goal-mode create 寫入新的不可變目標草案。
  • --goal-mode amend 寫入修改提案,而非靜默編輯。
  • --goal-mode none 提取需求而不產生目標文字。

真正的不可變目標應僅在人類核准後才建立或修改。這條規則之所以存在,是因為 oai-trial 在實作定義的測試取代了客戶簡報時失敗了。

邊界

此技能從提供的本機檔案中提取清晰、可追溯的需求。當來源套件不明確時,它不會聲稱提取的合約是完整的。不明確之處將變成 open_questions[] 和「需要變更」報告。預設情況下,它拒絕儲存庫根目錄,因為 oai-trial 在程式碼形狀的檢查取代了交付的簡報時失敗了。

對於 Battle,將產生的 acceptance_bundle.json 作為競技場的 acceptance_floor 傳入,並將每個 acceptance_cases[].id 對應到 Battle 戰役設定檔中 required_case_ids 的一個或多個生成器案例 ID。這些對應的案例是合約底線,必須先通過,然後才能將模糊測試或超越合約的攻擊計入。不要讓 Battle 自行發明需求。

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

grahama1970/agent-ecosystem

Canonical map and shared contracts for the agent-governance ecosystem: the pi.receipt_envelope.v1 boundary envelope, the component graph, and the rules for which component owns which schema. Use when wiring a skill or extension into the shared receipt world, when asking how shame, triage-error, tau, ask, project-watchdog, ops-herdr, ponytail, and Memory fit together, or when validating an envelope.

grahama1970/agentic-evals

Agentic evaluation of skills using multi-trial fixtures, deterministic command assertions, trajectory checks, safety constraints, and evidence-backed readiness scoring. Use when users ask for agentic evals, multi-trial skill evaluation, skill trajectory validation, or readiness scoring for a skill workflow.

grahama1970/agent-inbox

File-based inter-agent messaging with headless dispatch. Check inbox, send bugs/requests to other projects, automatically spawn headless agents to fix bugs, and track progress via task-monitor.

grahama1970/agents-registry

Generate and query the centralized agent identity registry. Scans .pi/agents/*/AGENTS.md, parses frontmatter, outputs agents-registry.json and optionally syncs to /memory for semantic search.

grahama1970/agent-status

Artifact-driven status surfaces for long-running project-agent work. Maintains status.json, events.jsonl, proof manifests, and a stale-aware STATUS.html so humans can tell where the agent is, what passed, what is still unproven, and what decision or action is next — without dashboard theater.

grahama1970/align

Round-based context alignment before execution. Use when the human, project agent, WebGPT, scillm, ask, dogpile, memory, or project-knowledge may each hold different facts about a task; especially before ambiguous design, infographic, product workflow, high-stakes implementation, plan-iterate, project-infographic, or multi-review work.

grahama1970/analytics

Flexible data science analytics for any dataset. Auto-discovers schema, recommends charts, exports to create-figure. Works with JSONL, JSON, CSV from any source.

grahama1970/analyze-chatterbox-emotions

Evaluate generated Chatterbox voice files as voice-quality artifacts: affect match, arousal/valence proxies, pause placement, intelligibility inputs, clipping, loudness, and discontinuity flags. Use when reviewing Chatterbox emotional tags, pauses, Turbo/base affect delivery, Persona Dream utterance renders, or whether generated speech matches an intended product-facing affect.

grahama1970/analyze-elf

Reverse-engineer features from ELF binaries. Extracts CLI commands, state machines, protocols, Zod schemas, and data models. Automatically generates a /create-walkthrough prosecution brief with Mermaid diagrams. Uses /treesitter for AST analysis of bundled JS/TS source.

grahama1970/animation-vocabulary

Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and wants the right word to prompt an AI or designer with. For naming an effect, not designing or building one.

grahama1970/anonymize-data

Anonymize supported CSV, JSON, UTF-8 text, and SQLite files using an explicit policy through the oai-trial project. Use for anonymize data, pseudonymize exports, redact policy literals, or discover and explicitly approve fuzzy name aliases. The skill is a thin CLI/Docker interface, not another engine.

grahama1970/anvil

Heavy-duty "No-Vibes" debugging and hardening orchestrator. Use this for complex, stubborn bugs where `review-code` has failed, or for "Red Teaming" (hardening) a codebase. Runs multiple agents in parallel (Thunderdome) using git worktree isolation.

grahama1970/apple-design

Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces.

grahama1970/argue

Multi-persona structured debate orchestrator. Personas research via /dogpile, consult colleagues via /ask, and argue toward nuanced synthesis on complex questions.

grahama1970/arxiv

Search arXiv for papers and extract knowledge into memory. Use `search` to find papers, `learn` to extract knowledge.

grahama1970/ask

Use when the user asks to query project memory, ask an oracle, use supported browser-backed reviewers, run Tau roundtable/single-handler workflows, ask Pi-native subagents from within Pi, run persona/deep-review workflows, generate image prompts, check OS/project health through composed skills, or run an ask DAG. This skill is the executable /ask runtime; do not replace it with an informal subagent, plain web search, or hand-written review; inside Pi, explicit Pi-native subagent targets are routed through the pi-subagents tool as an Ask target type.

grahama1970/assess

Step back and critically reassess project state. Use when asked to "assess", "step back", "fresh eyes", "check alignment", "sanity check", "health check", "prune documentation", or "evaluate what's working". Offers documentation pruning and doc-code alignment analysis. Offer to run after major changes (don't auto-run).

grahama1970/assistant

Shared GPT + classifier inference gateway for persona monitor tasks. Routes validation and classification through a 4-tier cascade: heuristic → classifier → local GPT → scillm.

grahama1970/assistant-lab

Self-improvement workbench for /assistant. All the tools needed to diagnose, train, evaluate, and promote models in a continuous loop. The "warm pond" where /assistant evolves its own inference stack.

grahama1970/batch-quality

Pre-flight validation and quality gates for batch LLM operations. ACTUALLY tests samples through LLM before burning tokens. Uses SPARTA contracts for DuckDB validation queries. Integrates with task-monitor for enforced quality gates.

相關技能