القائمة
Add local-first observability for coding agents. Use when a repo needs logging conventions, request or correlation IDs, diagnostics, scripts/logs, scripts/diagnose, debugging docs, metrics/tracing guidance, or smoke-test diagnostics.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Diagnose failed or unreliable agent workflows by classifying bad assumptions, missing observations, tool misuse, wrapper failures, hidden repair loops, incomplete validation, handoff gaps, and repeated failure patterns. Use after a failed harness run, flaky agent output, or confusing validation loop.
Review agent-generated changes against project rules. Use when asked for a review, before opening a PR, after large Codex edits, or when checking diffs for correctness, security, architecture, tests, docs drift, dependencies, migrations, and release risk.
Generate or maintain a minimal high-signal AGENTS.md for coding agents. Use whenever a repo needs agent instructions, an existing AGENTS.md is too long or vague, or project docs/scripts need a concise routing map for Codex.
Define and mechanically enforce architecture boundaries for a repo. Use when a project needs allowed dependency rules, forbidden imports, layer documentation, dependency maps, circular dependency checks, or protection against agent-created architectural drift.
Scaffold a new TypeScript web, mobile, API, or full-stack project with Better-T-Stack, then harden it with the Pax Fullstack Harness. Use whenever the user wants a new TypeScript app scaffold, mentions Better-T-Stack, asks for a modern type-safe stack, or wants Codex to start a repo that is agent-ready from day one.
Use guided Chrome DevTools MCP setup and workflows for browser runtime debugging. Use when a web app needs console, network, DOM, accessibility, Lighthouse, performance, responsive, or live-browser investigation beyond normal tests.
| name | observability-harness |
| description | Add local-first observability for coding agents. Use when a repo needs logging conventions, request or correlation IDs, diagnostics, scripts/logs, scripts/diagnose, debugging docs, metrics/tracing guidance, or smoke-test diagnostics. |
Make runtime behavior inspectable through local logs, diagnostics, and documented debugging paths before adding heavy external platforms.
Use chrome-devtools-runtime-debugger for browser console, network, DOM, accessibility, Lighthouse, responsive, or performance investigation.
Use sprint-contract-observability for process observability: sprint contracts, evaluator rubrics, and task traces.
Define observability basics.
Add local diagnostics.
scripts/logs.scripts/diagnose when repeatable diagnostics exist.scripts/healthcheck when helpful.docs/observability/browser-debugging.md when Chrome DevTools MCP is relevant.Document behavior.
docs/observability/logging.mddocs/observability/debugging.mdKeep it boring.