codex-productivity-auditor

Sterne9

Forks0

Aktualisiert3. Juni 2026 um 05:36

Audit a project and recent Codex session behavior to recommend Codex productivity setup across AGENTS.md, skills, hooks, MCP/plugins, subagents, local environment actions, automations, memories, and workflow docs. Use when the user asks how to make repeated steering second nature or asks what Codex setup is missing.

Installation

Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.

Quelle

ingpoc

ingpoc/SKILLS

GitHub-Repository öffnen Creator-Repositorys ansehen

Download

Verwandte BerufeSOC

Basierend auf der SOC-Berufsklassifikation

SoftwareentwicklerInformatik- und Mathematikberufe·SOC 15-1252

Datei-Explorer

8 Dateien

SKILL.md

readonly

name	codex-productivity-auditor
description	Audit a project and recent Codex session behavior to recommend Codex productivity setup across AGENTS.md, skills, hooks, MCP/plugins, subagents, local environment actions, automations, memories, and workflow docs. Use when the user asks how to make repeated steering second nature or asks what Codex setup is missing.

Codex Productivity Auditor

Recommend the smallest durable Codex setup changes that make repeated user steering automatic without adding friction.

Workflow

Inspect project setup: AGENTS.md, .codex/config.toml, .codex/agents/, skills, hooks, workflow docs, scripts, and tests.

Run deterministic session analysis:

scripts/transcript_signal_scan.py --project <project-or-path>

Load only the references needed for the recommendation:
- session signals: references/session-analysis-rubric.md
- owner placement: references/owner-surface-rubric.md
- hooks, automations, MCP/plugins, or always-loaded rules: references/friction-risk-rubric.md
- subagent/model choices: references/model-routing-rubric.md
- signal vocabulary: references/signal-taxonomy.md
Check official OpenAI Codex docs when product behavior may drift.
Recommend at most five setup changes, plus what not to configure yet.

Fixed Decisions

Raw Codex JSONL under ~/.codex/sessions and ~/.codex/archived_sessions is the canonical session-analysis source.
Do not use qmd or Obsidian for scoring or recommendations; use them only for explicit human-readable lookup or semantic discovery requests.
For repeated local run/test/log command friction, prefer Codex local environment actions over hooks or automations.
Do not hand-write local-environment action schema. Create the first action through Codex app settings, inspect the generated project .codex artifact, then edit only with that schema in hand.

Recommendation Shape

Top Recommendations
1. <setup change>
   Evidence: <signal counts and pointers>
   Owner: <surface>
   Change: <exact action>
   Confidence: high|medium|low
   Validation: <command/proof>

Not Recommended Yet
- <feature>: <why>

Loopholes Checked
- <loophole>: <fix or downgrade>

Keep the answer compact. Do not paste long transcript excerpts; cite counts, JSONL file paths, line numbers, and command evidence.

Mehr aus diesem Repository

gleiches Repository

accenture-slides

ingpoc/SKILLS

Create premium Accenture-branded PowerPoint presentations following Tufte data visualization principles and Dieter Rams design philosophy. Use when creating slides, presentations, or decks for Accenture corporate settings that require (1) Accenture brand identity (purple A100FF chevron logo clean layouts) (2) Minimal data-focused design (Tufte less but better) (3) Executive-ready aesthetics for boardroom presentations client pitches or internal reports

2026-06-039

add-to-global-trigger

ingpoc/SKILLS

Route proposed additions to the global Codex control plane by deciding whether a request belongs in `~/.codex/AGENTS.md`, a global workflow or reference doc under `~/.codex/docs`, `~/.codex/bin/workflow.py`, or an enforceable non-prose surface. Use when asked to "add this to global AGENTS", "promote this workflow to global", "add a new global trigger", or decide whether something should be a trigger, workflow, reference, hook, lint rule, or runtime guard.

2026-06-039

agent-feedback-artifact

ingpoc/SKILLS

Add, remove, serve, test, and operate a server-backed in-page agent feedback capability for HTML artifacts, static pages, or local app builds. Use when the user wants Browser-style annotation inside the artifact/app itself, marker-local chat, comment-triggered agent work, queued marker processing, deterministic install/remove scripts, preflight/closeout checks, browser acceptance evidence, or progressive-disclosure access to marker context.

2026-06-039

agentharness-audit

ingpoc/SKILLS

Audits any agent harness codebase against 13 meta-principles of quality, scores each 0 to 10 with code citations, generates a self-contained HTML report for operators, and writes an agent-readable AGENTS.md improvement directive with file-level architecture recommendations to reach 9.5 or better. Use when the user wants to audit or rate an agent harness, evaluate harness quality, score an agent framework, get a roadmap for improving a harness, run agentharness-audit, audit this harness, rate Hermes, audit Codex, or audit a Claude Code harness. Not for individual skill audits or general code review.

2026-06-039

atlas-computer-use

ingpoc/SKILLS

Use when controlling ChatGPT Atlas through Codex Computer Use, especially browser tasks where context efficiency matters: fewer screenshots, fewer UI snapshots, fewer clicks, and cleaner browser state.

2026-06-039

audit

ingpoc/SKILLS

Audit project against golden principles, produce scorecard. Use for /audit, "check project quality". NOT for system setup health (/harness-audit) or eval scoring (/eval-score).

2026-06-039

name	codex-productivity-auditor
description	Audit a project and recent Codex session behavior to recommend Codex productivity setup across AGENTS.md, skills, hooks, MCP/plugins, subagents, local environment actions, automations, memories, and workflow docs. Use when the user asks how to make repeated steering second nature or asks what Codex setup is missing.

Codex Productivity Auditor

Recommend the smallest durable Codex setup changes that make repeated user steering automatic without adding friction.

Workflow

Inspect project setup: AGENTS.md, .codex/config.toml, .codex/agents/, skills, hooks, workflow docs, scripts, and tests.

Run deterministic session analysis:

scripts/transcript_signal_scan.py --project <project-or-path>

Load only the references needed for the recommendation:
- session signals: references/session-analysis-rubric.md
- owner placement: references/owner-surface-rubric.md
- hooks, automations, MCP/plugins, or always-loaded rules: references/friction-risk-rubric.md
- subagent/model choices: references/model-routing-rubric.md
- signal vocabulary: references/signal-taxonomy.md
Check official OpenAI Codex docs when product behavior may drift.
Recommend at most five setup changes, plus what not to configure yet.

Fixed Decisions

Raw Codex JSONL under ~/.codex/sessions and ~/.codex/archived_sessions is the canonical session-analysis source.
Do not use qmd or Obsidian for scoring or recommendations; use them only for explicit human-readable lookup or semantic discovery requests.
For repeated local run/test/log command friction, prefer Codex local environment actions over hooks or automations.
Do not hand-write local-environment action schema. Create the first action through Codex app settings, inspect the generated project .codex artifact, then edit only with that schema in hand.

Recommendation Shape

Top Recommendations
1. <setup change>
   Evidence: <signal counts and pointers>
   Owner: <surface>
   Change: <exact action>
   Confidence: high|medium|low
   Validation: <command/proof>

Not Recommended Yet
- <feature>: <why>

Loopholes Checked
- <loophole>: <fix or downgrade>

Keep the answer compact. Do not paste long transcript excerpts; cite counts, JSONL file paths, line numbers, and command evidence.