Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

evaluator

Étoiles2

Forks0

Mis à jour19 juin 2026 à 00:52

Use after implement-feature to score the current implementation against the active feature's spec.md Criterios de Aceitacao, emitting a pass/fail list. Read-only — makes no code changes.

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

CaioWF

CaioWF/keel

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Analystes en assurance qualité des logiciels et testeursProfessions informatiques et mathématiques·SOC 15-1253

SKILL.md

readonly

name	evaluator
description	Use after implement-feature to score the current implementation against the active feature's spec.md Criterios de Aceitacao, emitting a pass/fail list. Read-only — makes no code changes.

evaluator

When: right after implement-feature finishes a task (or a batch of tasks), before deciding whether to loop back for fixes or move on. Re-run any time the implementation changes.

Template: none — this skill is purely evaluative, it does not fill or produce a template-based artifact.

Output: a pass/fail list reported inline to the user (one line per Critérios de Aceitação scenario) — no new file is mandated, no existing file is edited.

Steps:

Resolve the active feature from .specify/state (fallback: newest dir under specs/).
Read specs/<active-feature>/spec.md, focusing on Critérios de Aceitação (the Given/When/Then scenarios).
For each scenario, inspect the current implementation and its tests to determine whether the behavior is actually satisfied — read code, run existing tests/build if needed, do not assume from tasks.md checkboxes alone.
Emit one line per scenario: PASS or FAIL plus a short reason. Also flag any scenario that has no corresponding test at all.
Make no code, test, or doc edits — this skill is read-only. If you spot a fix, describe it instead of applying it.
Summarize: overall status is "met" only if every scenario is PASS; otherwise "not met" with the failing list.

Next: fix-runner if any scenario fails or gates are red; otherwise hand control back to implement-and-evaluate to continue with the next task or proceed to code-review.

Plus depuis ce dépôt

même dépôt

okf-enrich

CaioWF/keel

Ingest a raw source into the project's OKF knowledge bundle — distill it into concept pages, refresh the index, and log the change. keel's compounding "LLM wiki" loop.

2026-07-112

finishing-a-development-branch

CaioWF/keel

Use when implementation is complete, gates pass, and you need to decide how to integrate the work — presents structured options (merge, PR, keep, discard) and handles the chosen workflow, including worktree cleanup. Closes the SDD cycle after review-and-simplify.

2026-07-102

subagent-driven-development

CaioWF/keel

Use when executing implementation plans with independent tasks in the current session

2026-07-102

implement-and-evaluate

CaioWF/keel

Orchestrates the implement-feature, evaluator, fix-runner loop for the active feature until all Criterios de Aceitacao are met and quality gates are green.

2026-07-102

tasks-writer

CaioWF/keel

Use after the plan is approved to break the active feature's plan into a concrete task checklist, written into specs/<feature>/tasks.md from the tasks template.

2026-07-102

observability-and-instrumentation

CaioWF/keel

Use while implementing a feature that has retries, queues, background jobs, external calls, or any critical path an on-call engineer will need to reason about in production. Invoke when adding a new endpoint, dependency, or async flow, and before considering such a feature done — instrumentation is developed alongside the code, like tests, not bolted on after.

2026-07-082

name	evaluator
description	Use after implement-feature to score the current implementation against the active feature's spec.md Criterios de Aceitacao, emitting a pass/fail list. Read-only — makes no code changes.

evaluator

When: right after implement-feature finishes a task (or a batch of tasks), before deciding whether to loop back for fixes or move on. Re-run any time the implementation changes.

Template: none — this skill is purely evaluative, it does not fill or produce a template-based artifact.

Output: a pass/fail list reported inline to the user (one line per Critérios de Aceitação scenario) — no new file is mandated, no existing file is edited.

Steps:

Resolve the active feature from .specify/state (fallback: newest dir under specs/).
Read specs/<active-feature>/spec.md, focusing on Critérios de Aceitação (the Given/When/Then scenarios).
For each scenario, inspect the current implementation and its tests to determine whether the behavior is actually satisfied — read code, run existing tests/build if needed, do not assume from tasks.md checkboxes alone.
Emit one line per scenario: PASS or FAIL plus a short reason. Also flag any scenario that has no corresponding test at all.
Make no code, test, or doc edits — this skill is read-only. If you spot a fix, describe it instead of applying it.
Summarize: overall status is "met" only if every scenario is PASS; otherwise "not met" with the failing list.

Next: fix-runner if any scenario fails or gates are red; otherwise hand control back to implement-and-evaluate to continue with the next task or proceed to code-review.