菜单
Load when entering an unfamiliar codebase, or before proposing an architecture-level change. Do not load for tiny edits, known local fixes, post-implementation summaries, or tasks already scoped by a current state-map.md.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Load before implementing anything that runs continuously or per-item at scale — animation and render loops, timers, pollers, per-request middleware, large-collection iteration. Do not load for one-shot scripts, setup code, or paths that run a bounded handful of times.
Load before hand-writing or hand-editing files a toolchain normally generates or owns — Xcode project files, lockfiles, generated schemas or migrations, IDE workspace files. Do not load for ordinary source code.
Load on strike 3, a tangled run, or a contradiction that cannot be localized. Do not load for first failures, ordinary test red/green loops, or known environment outages.
Load for cross-session orchestration — dispatching work to an Albion/GLM worker over tmux, polling a worker completion manifest, or reviewing worker output. Do not load for in-session subagent delegation; use delegation instead.
Load when the stop gate blocks twice on the same task. Do not load for ordinary unfinished work, first gate blocks, or reports where no completion claim is being made.
Load when writing a subagent brief for non-trivial dispatched work. Do not load for direct edits, trivial lookups, user-facing summaries, or delegation already covered by an existing brief.
| name | maturity-assessment |
| description | Load when entering an unfamiliar codebase, or before proposing an architecture-level change. Do not load for tiny edits, known local fixes, post-implementation summaries, or tasks already scoped by a current state-map.md. |
Extend charter §3 (escalation) with a codebase maturity read. Record the result in state-map.md before architecture-level judgment or broad edits.
| Dimension | Inspect | Signal |
|---|---|---|
| Tests / CI presence | tests/, CI configs, package scripts, fixture quality | validation surface and release discipline |
| Docs | README, architecture notes, runbooks, inline contracts | explicit intent vs inherited practice |
| Structure coherence | module boundaries, naming, layering, dead folders | local change cost |
| Dependency freshness | lockfile age, deprecated packages, security policy | upgrade pressure |
| Churn / age signals | recent commits, stale hotspots, ownership gaps | risk concentration |
| Hot paths | auth, persistence, migrations, queues, billing, deploy scripts | blast radius |
| Tier | Calibration | Do more of | Forbidden |
|---|---|---|---|
| Prototype | Low ceremony; behavior may outpace structure | small direct edits, cheap smoke checks, user-visible progress | process ceremony, framework rewrites, premature abstractions |
| Growth | Patterns exist but are uneven | align nearby code, add narrow tests around touched behavior | repo-wide normalization, hidden compatibility layers |
| Mature | Conventions are part of the product | match local contracts, preserve public shape, verify through existing gates | drive-by refactors, style churn, test weakening |
| Legacy | Behavior is valuable and under-specified | characterization tests before change, tiny reversible patches, explicit rollback notes | speculative cleanup, dependency jumps, unverified simplification |
Write at most 15 lines in state-map.md.
## Maturity assessment
Tier:
Evidence:
- Tests / CI:
- Docs:
- Structure:
- Dependencies:
- Churn / age:
- Hot paths:
Behavioral calibration:
Forbidden at this tier:
Confidence:
If evidence conflicts, choose the lower-trust tier and name the contradiction.