跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
AI 与知识库

analyse-agentic-system

Use when asked to analyse, review, or refresh an external agent runtime, orchestration system, agent operating layer, agent memory/knowledge/context-engineering system, or narrower model-dependent operational mechanism from inspectable sources.

zby · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add zby/commonplace --skill analyse-agentic-system

技能说明


name: analyse-agentic-system description: "Use when asked to analyse, review, or refresh an external agent runtime, orchestration system, agent operating layer, agent memory/knowledge/context-engineering system, or narrower model-dependent operational mechanism from inspectable sources." type: kb/types/instruction.md user-invocable: true argument-hint: " plus source input (repository, checkout, snapshot/bundle, or documents) and optional public review path" allowed-tools: Read, Write, Grep, Glob, Bash, Task context: fork model: opus

Analyse an Agentic System

Analyse one external agentic system at one frozen evidence boundary. Identify what the system wires, where its responsibilities end, and what its memory/context and epistemic routes support. Run a runtime baseline and both mandatory lenses, then write one exact result and publish a compact generated review. Delegate memory/context analysis to a fresh specialist and integrate its typed report into that result.

Invocation authorizes the run directory under kb/reports/state/agentic-system-analysis/, one generated review under kb/agentic-systems/reviews/, its identical exact-result copy under kb/reports/retained/agentic-system-analysis/<run-id>/result.md, and the local memory specialist input and report inside that run directory. It does not authorize changes to source worktrees, auxiliary indexes or surveys, transfer scans, landscape synthesis, other retained reports, or Git staging and commits.

Failure rule

Keep a correctable pre-publication failure in running state, fix the candidate or result, and repeat the failed check. Set run-status: failed with one concise reason only when abandoning the run or when a publication error leaves public state uncertain. Do not resume a failed run or maintain a phase ledger, packet, correction log, retry log, or validation receipt. Use a new run ID. Temporary candidates are non-canonical and may be overwritten or removed by the run owner.

Steps

1. Open the run and resolve output paths

  1. Allocate AAS-<YYYY-MM-DD>-<system-slug>-<nn>. Create kb/reports/state/agentic-system-analysis/<run-id>/run-state.md from the run-state template with run-status: running. The exact result path is always <run-id>/result.md. Run commonplace-validate <run-state-path> immediately. Choose the source-native system name once here and copy it exactly into the result.

  2. Derive the public review path as kb/agentic-systems/reviews/<system-slug>.md unless the caller supplied one. A caller-supplied path must also be directly under reviews/. Before reading sources or drafting, run:

    commonplace-agentic-analysis-publication inspect-destination --generated-destination <review-path> --source-identity <source-identity>
    

    This reads incumbent metadata internally and returns only eligibility and expected_incumbent_sha256 (a digest or absent). Save that value in this run's ## Run prose for both publication commands. Never inspect incumbent prose, descriptions, prior results or audits to resolve the destination; guessed line counts such as head or sed -n '1,22p' are not metadata extraction. Hand-authored or different-source collisions need a qualified slug. Other inspection failures are publication blockers to report at once; analysis may continue, but do not promise publication or bypass the guard. Resolve the blocker and repeat inspection before publication. A verified, unchanged earlier publication can be replaced while uncommitted; arbitrary local edits cannot. No Git commit is required merely to rerun the review.

  3. Record separately any caller-authorized auxiliary paths and any separately commissioned transfer scan. Automatic review publication does not authorize those operations.

  4. Confirm the target is in scope: an agent runtime, orchestration framework, agent operating layer, memory/knowledge/context-engineering system, or a narrower mechanism whose operation depends on model calls it issues or serves. An MCP server, tool, or returning computation may qualify without owning the enclosing runtime. If the target is outside this boundary, write and validate an out-of-scope result, complete the run without a public review, and stop.

  5. Classify the target as an enclosing runtime, embedded inner runtime, runtime client, returning computation, workflow, extension or tool mechanism, builder or improvement plane, host integration, memory/knowledge/context-engineering system, or another defined class. State functional inclusions, exclusions, external dependencies, and one boundary kind: whole-system, subsystem-only, or complete artifact, partial loop. Do not assign responsibilities owned by an excluded host to the selected target.

If no coherent boundary or reachable source can be established, write a typed blocked result with every required section and explicit unreached dispositions. Complete the run without publishing a review.

If a coordinator reads prior-review prose or substantive prior audit findings before freezing the exact result and candidate, disclosure does not restore a source-only pass. Stop that analysis, mark the run failed for prior-analysis exposure, and require a fresh coordinator context with a new run ID and clean source-only inputs. Do not publish the exposed draft or try to repair its independence claim. A later, separately commissioned audit after both artifacts were frozen records its timing; it does not retroactively contaminate their construction. Keep subsequent analytical changes outside that exposed context.

2. Freeze and inspect sources once

  1. Before inspection, record a compact source allowlist: the exact repositories, captures, documents, and time boundary that may supply evidence. A supplied reposi
阅读完整来源 ↗