Agent skill
evaluation-plan
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/development/evaluation-plan
SKILL.md
name: evaluation-plan description: Pflege Evaluationsmetriken und Schwellenwerte; verwenden bei Aenderungen an Metriken, Messmethoden oder Akzeptanzkriterien fuer Evaluation.
Skill: evaluation-plan
Zweck
Halte die Evaluation nachvollziehbar und messbar fuer die Case Study.
Wann anwenden
- Wenn neue Metriken oder Schwellenwerte definiert werden.
- Wenn Messmethoden angepasst werden muessen.
Vorgehen (Schritt-fuer-Schritt)
- Lies
docs/04_evaluation/EVALUATION_PLAN.md. - Aktualisiere Metriken, Messmethoden und Akzeptanzschwellen.
- Verknuepfe Metriken mit relevanten NFRs, falls vorhanden.
Lernperspektive
- Warum so? Evaluation macht Fortschritt und Qualitaet messbar.
- Alternativen: ad-hoc Demo-Feedback ohne klare Kriterien.
- Warum nicht hier? Ohne Kriterien ist Lernfortschritt schwer belegbar.
Repo-Referenzen
docs/04_evaluation/EVALUATION_PLAN.mddocs/01_requirements/NFR.en.md
Qualitaetscheck
- Metriken sind messbar definiert.
- Schwellenwerte sind konsistent mit NFRs.
- Keine untestbaren Aussagen.
Phasenbezug
| Phase | Aufgabe | Status |
|---|---|---|
| Phase 4 | Evaluationsplan definieren | erledigt |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?