Jeden Skill in Manus ausführen
mit einem Klick

Jeden Skill in Manus mit einem Klick ausführen

eval-result

Sterne1

Forks1

Aktualisiert7. Mai 2026 um 17:02

Use inside the TDD skill evaluation harness to package coder-agent output into a uniform result bundle for evaluator scoring.

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.

In Manus ausführen

Quelle

intent-driven-dev

intent-driven-dev/tdd-skill-evaluation-harness

GitHub-Repository öffnen Creator-Repositorys ansehen

Download

In Manus ausführen

Verwandte BerufeSOC

Basierend auf der SOC-Berufsklassifikation

Softwarequalitätssicherungsanalysten und -testerInformatik- und Mathematikberufe·SOC 15-1253

Datei-Explorer

2 Dateien

SKILL.md

readonly

name	eval-result
description	Use inside the TDD skill evaluation harness to package coder-agent output into a uniform result bundle for evaluator scoring.

Eval Result

Purpose

Return factual, ordered evidence from a coder worktree so skill-eval can score the run without relying on unsupported self-report.

Bundle Contract

Return a concise result bundle:

agent_role: junior | mid | senior
model_id: string
workspace: string
task_status: pass | partial | fail
commands:
  - phase: RED | GREEN | REFACTOR | VERIFY
    command: string
    result: pass | fail
    summary: string
changed_files:
  - path: string
    purpose: test | production | config | docs
evidence_notes:
  - string
known_gaps:
  - string

Rules

Report facts from artifacts and command output only.
Preserve command order.
Do not claim TDD compliance unless RED/GREEN/REFACTOR evidence supports it.
Record gaps explicitly instead of smoothing them over.

Mehr aus diesem Repository

gleiches Repository

env-setup

intent-driven-dev/tdd-skill-evaluation-harness

Use to set up a prompt-operated TDD benchmark environment before evaluation. Trigger when the user wants to choose a stack, ensure test, branch coverage, line coverage, and mutation-testing tools are available, create the workspace conventions, or write the benchmark problem statement into a prompt file for later coder-agent evaluation.

2026-05-071

skill-eval

intent-driven-dev/tdd-skill-evaluation-harness

Use to orchestrate and evaluate a multi-agent TDD skill benchmark. Trigger when the user says start eval, wants junior/mid/senior coder agents on separate model tiers, parallel git worktrees, adversarial evaluation of result bundles, deterministic coverage/mutation scoring, or a consolidated parity report.

2026-05-071

tdd

intent-driven-dev/tdd-skill-evaluation-harness

Use for language-agnostic coder-agent behavior under strict test-driven development. Trigger when implementing a task with test-first workflow, RED/GREEN/REFACTOR cycles, minimal production changes, and verifiable ordering evidence for later evaluation.

2026-05-071

name	eval-result
description	Use inside the TDD skill evaluation harness to package coder-agent output into a uniform result bundle for evaluator scoring.

Eval Result

Purpose

Return factual, ordered evidence from a coder worktree so skill-eval can score the run without relying on unsupported self-report.

Bundle Contract

Return a concise result bundle:

agent_role: junior | mid | senior
model_id: string
workspace: string
task_status: pass | partial | fail
commands:
  - phase: RED | GREEN | REFACTOR | VERIFY
    command: string
    result: pass | fail
    summary: string
changed_files:
  - path: string
    purpose: test | production | config | docs
evidence_notes:
  - string
known_gaps:
  - string

Rules

Report facts from artifacts and command output only.
Preserve command order.
Do not claim TDD compliance unless RED/GREEN/REFACTOR evidence supports it.
Record gaps explicitly instead of smoothing them over.