Community编程与开发github.com

grahama1970/agent-status

人工制品驱动的状态展示面板,用于长时间运行的项目代理工作。维护 status.json、events.jsonl、证明清单和感知过期的 STATUS.html,使人能够了解代理的进展情况、哪些测试通过了、哪些尚未验证、下一步需要做什么决定或操作——无需仪表盘剧场。

agent-status 是什么?

该技能为长时间运行的代理工作提供了一种去仪表盘化的状态追踪方案。它基于严格的人工制品优先原则,通过 'status.json'(作为真相源)、'events.jsonl'(记录状态转换日志)、'proof_manifest.json'(列出所有证据文件)和 'STATUS.html'(自动生成、感知过期的渲染页面)四个核心文件来呈现状态。其核心设计哲学是:状态人工制品生成后,HTML 页面才对其进行渲染,从而避免虚构进度、百分比或隐藏真实情况。该技能明确规定了八种允许的状态(如 `not_started`、`running`、`blocked`、`done`),并强制执行十条反仪表盘剧场规则,例如:“不得使用百分比”、“每个通过事件必须附上证据文件”、“每个空闲状态必须说明原因”、“每个等待人类的状态必须包含决策菜单”。它适用于 'plan-iterate'、'orchestrate'、'review-design'、'review-code'、'debugger' 等多步骤代理工作场景,并与 Claude Code、Cursor、Codex 等基于命令行/文件的代理平台兼容,最终通过可读的 HTML 页面和聚合的状态 JSON 文件向人类使用者提供明确、可审计的进度视图。该技能的主要目标是让人类能够快速回答八个关键问题:代理正试图完成什么?当前到了哪一步?刚通过了什么?什么尚未验证?下一步行动是什么?代理是否正在运行、被阻塞、空闲或等待人类?当前声明的证据是什么?代理下一步不应做什么?

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

Installed? Explore more 编程与开发 skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

agent-status 是做什么的?

当项目代理正在进行多步骤工作,且人类需要了解实际情况时,请使用此技能。

该技能并非仪表盘生成器。它生成一个由机器可读人工制品支持的真相展示层:

.plan-iterate/<campaign-id>/status/
  status.json
  events.jsonl
  proof_manifest.json
  STATUS.html

HTML 只渲染当前状态人工制品。它不得虚构进度、百分比或完成声明。

核心原则

状态人工制品优先 → HTML 渲染人工制品 → 人类可检查证据

绝不要这样做:

美化页面优先 → 模糊的绿色文字 → 人类猜测进度

首次视图必须回答的问题

生成的页面必须回答:

  1. 代理正试图完成什么?
  2. 我们当前确切的进度如何?
  3. 刚通过了什么?
  4. 什么尚未验证?
  5. 下一步行动是什么?
  6. 代理是正在运行、被阻塞、空闲,还是等待人类?
  7. 当前声明有什么证据支持?
  8. 代理下一步不应做什么?

状态模型

允许的状态:

  • not_started
  • running
  • needs_attention
  • blocked
  • failed
  • passed_scoped_gate
  • done
  • idle

重要区别:

passed_scoped_gate != done

仅当最终目标有明确的最终证据人工制品时,才使用 done。

常用命令

初始化一个项目阶段:

./run.sh init \
  --campaign refactor-harness-e2e \
  --goal "完成范围明确的 Refactor Harness E2E 验证"

标记一个关卡为运行中:

./run.sh update \
  --campaign refactor-harness-e2e \
  --state running \
  --current-step "运行强化的并发 LLM + OpenCode 总结关卡"

记录一个通过的限定范围关卡:

./run.sh gate-passed \
  --campaign refactor-harness-e2e \
  --label "A01-A18 强化的并发 LLM + OpenCode 总结" \
  --verdict PASS_SPEC \
  --proof ".plan-iterate/refactor-harness-e2e/proof/refactor-concurrent-mixed.json" \
  --next-action "启动审查者数据包 + 审查者扇入阶段" \
  --not-proven "Transport Room B1 UI" \
  --not-proven "build_review_packet 审查者扇入" \
  --not-proven "完整的 OpenCode 消息传递"

请求人类做出决定:

./run.sh needs-human \
  --campaign refactor-harness-e2e \
  --question "代理应该运行下一个项目阶段?" \
  --option "A=继续 Harness: 审查者数据包 + 审查者扇入" \
  --option "B=Transport UI: 启动 Transport Room B1" \
  --option "C=仅稳定:检查点并停止"

再次渲染状态页面:

./run.sh render --campaign refactor-harness-e2e

反仪表盘剧场规则

  1. 无百分比。
  2. 除非最终目标证据存在,否则不得使用绿色“完成”标签。
  3. 每个 PASS 必须指明其证据人工制品。
  4. 每个状态必须显示什么尚未验证。
  5. 每个空闲状态必须说明代理为何空闲。
  6. 每个等待人类的状态必须包含决策菜单。
  7. 每个被阻塞的状态必须指明缺失的人工制品、服务、关卡或决定。
  8. 仅当页面读取 status.json 时,才允许自动刷新。
  9. 如果 status.json 已过期,页面必须指明已过期。
  10. 审查者判定是收据,而非完成证明。

何时使用

用于以下场景:

  • /plan-iterate
  • /orchestrate
  • /review-design
  • /review-code
  • /debugger
  • /ask deep-review
  • /code-runner
  • /subagent-runner
  • 任何持续时间超过一个集中命令的多步骤项目代理工作

人工制品预期

status.json 是真相源。

events.jsonl 仅追加,记录状态转换。

proof_manifest.json 列出状态声明中提及的证据人工制品。

STATUS.html 是生成、感知过期且可在浏览器中安全打开的页面。

完成标准

对于长时间运行的代理工作,最终答案应总结当前状态人工制品,并在可能的情况下链接或引用 STATUS.html 的路径。

除非满足以下条件,否则不得声称完成:

  • 状态为 done;
  • last_completed.proof_path 指向最终的证据人工制品;
  • not_proven 为空或明确声明“范围外”;
  • 阻塞项为空。

Individual skills in this repo

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

grahama1970/acceptance-contract

Turn a client brief, zip bundle, directory, or single requirements file into a typed acceptance-contract bundle with extracted requirements, acceptance checks, open questions, an immutable-goal draft, and a create-report-backed decision report. Use when users say acceptance contract, brief to requirements, freeze the goal, create immutable goal, amend immutable goal, build a Battle requirements bundle, or extract requirements from this bundle.

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/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.

相关技能