Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

Commencer

evidence

Étoiles0

Forks0

Mis à jour10 mars 2026 à 12:09

Generate a standardized evidence comment for a PR

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.

Exécuter dans Manus

Source

wtthornton

wtthornton/TheStudio

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

SKILL.md

readonly

name	evidence
description	Generate a standardized evidence comment for a PR
user-invocable	true
argument-hint	[PR number or description of changes]
allowed-tools	Read, Glob, Grep, Bash

Generate an evidence comment for: $ARGUMENTS

Read thestudioarc/15-system-runtime-flow.md for the evidence comment format.

Produce a standardized evidence comment with:

TaskPacket ID + correlation_id (if available)
Intent Summary — Goal statement from the Intent Specification
Acceptance Criteria — Checklist format with checkboxes
What Changed — High-level summary of modifications
Verification Results — ruff, pytest, security scan results
Test Commands — Exact commands to reproduce verification
Expert Coverage — Which expert classes were consulted
Loopback Counts — Number of verification/QA retries (if any)
Defect Categories — Any defects found and their classification

This is the audit trail. Every PR tells the story of how it got here.

Plus depuis ce dépôt

même dépôt

tapps-memory

wtthornton/TheStudio

Manage shared project memory for cross-session knowledge persistence. 33 actions: save, search, federation, profiles, Hive, and more.

2026-03-240

tapps-memory

wtthornton/TheStudio

Manage shared project memory for cross-session knowledge persistence. 33 actions: save, search, federation, profiles, Hive, and more.

2026-03-240

ralph-loop

wtthornton/TheStudio

Execute one Ralph development loop iteration. Reads fix_plan.md, implements the first unchecked task, verifies, and commits.

2026-03-220

session-plan

wtthornton/TheStudio

Review open epics and create a Helm session plan with Meridian review

2026-03-130

epic

wtthornton/TheStudio

Create a new epic using Saga's 8-part structure

2026-03-100

intent

wtthornton/TheStudio

Build a structured Intent Specification for a task

2026-03-100

name	evidence
description	Generate a standardized evidence comment for a PR
user-invocable	true
argument-hint	[PR number or description of changes]
allowed-tools	Read, Glob, Grep, Bash

Generate an evidence comment for: $ARGUMENTS

Read thestudioarc/15-system-runtime-flow.md for the evidence comment format.

Produce a standardized evidence comment with:

TaskPacket ID + correlation_id (if available)
Intent Summary — Goal statement from the Intent Specification
Acceptance Criteria — Checklist format with checkboxes
What Changed — High-level summary of modifications
Verification Results — ruff, pytest, security scan results
Test Commands — Exact commands to reproduce verification
Expert Coverage — Which expert classes were consulted
Loopback Counts — Number of verification/QA retries (if any)
Defect Categories — Any defects found and their classification

This is the audit trail. Every PR tells the story of how it got here.