shellbrain-usage-review

Étoiles12

Forks1

Mis à jour19 mai 2026 à 08:32

Use when a reviewer agent needs one fast cross-repo picture of how agents are using Shellbrain, where the product is working, where it is failing, and which expected capabilities are being skipped.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Source

cucupac

cucupac/shellbrain

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Métiers associésSOC

Basé sur la classification professionnelle SOC

Spécialistes en gestion de projetsProfessions des affaires et des opérations financières·SOC 13-1082

Explorateur de fichiers

4 fichiers

SKILL.md

readonly

name	shellbrain-usage-review
description	Use when a reviewer agent needs one fast cross-repo picture of how agents are using Shellbrain, where the product is working, where it is failing, and which expected capabilities are being skipped.

Shellbrain Usage Review

Run the canonical cross-repo analytics report and synthesize it for review.

Primary Command

shellbrain admin analytics --days 2

What To Extract

where Shellbrain is working well
where it is failing
what is failing and why
where working agents are skipping expected recall
where internal recall or knowledge-builder runs are failing
the top priorities that should drive product follow-up

Operating Rules

treat the JSON report as the source of truth
do not reconstruct the report with ad hoc SQL unless the command is broken
summarize the strongest wins, the most important failures, and the highest-priority capability gaps first
use repo_rollups only as secondary supporting context

Plus depuis ce dépôt

même dépôt

shellbrain

cucupac/shellbrain

Use when an agent should remember to ask Shellbrain for targeted recall at task start, subproblem changes, repeated failures, hypothesis changes, or closeout.

2026-07-1412

shellbrain

cucupac/shellbrain

Use when an agent should remember to ask Shellbrain for targeted recall at task start, subproblem changes, repeated failures, hypothesis changes, or closeout.

2026-07-1412

clean-architecture

cucupac/shellbrain

Define and enforce the owner's language-agnostic clean-core architecture for new software projects and refactors. Use when deciding responsibility placement, dependency direction, structural stage, safe refactor moves, semantic types, pure policies, entrypoints, startup wiring, adapters, and dependency boundaries.

2026-05-1912

clean-code

cucupac/shellbrain

Clean existing code by enforcing semantic integrity, reader clarity, and local efficiency without changing architecture. Use when auditing or improving code that has fake optionality, silent fallbacks, stale compatibility, permissive parsing, unclear names, dead wrappers, redundant work, or over-abstraction. Prefer required typed state, explicit errors, fail-fast validation, deletion of obsolete branches, clear names, simple functions, and focused tests.

2026-05-1912

shellbrain-usage-review

cucupac/shellbrain

Use when a reviewer agent needs one fast cross-repo picture of how agents are using Shellbrain, where the product is working, where it is failing, and which expected capabilities are being skipped.

2026-05-1912