specification-driven-coding-evaluation-scorecard
Use to score generated prompts, blueprints, code, products and multi-agent systems.
Skill by 2ord98
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/2ord98-specification-driven-coding-evaluation-scorecard
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/specification-driven-coding-evaluation-scorecard
What's inside
- Skill name
specification-driven-coding-evaluation-scorecard- Description
- Use to score generated prompts, blueprints, code, products and multi-agent systems.
- License
- MIT
- Instructions
- 19 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: "specification-driven-coding-evaluation-scorecard" does not match folder "evaluation-scorecard"
Files (1)
- SKILL.md
SKILL.md (first lines)
# specification-driven-coding-evaluation-scorecard ## Instructions Use `docs/18-evaluation-scorecards.md` and the relevant file in `scorecards/`. ## Required output - Overall score 0-100 - Area scores - Top 5 gaps - Risks still open - Patch minima consigliata ## Failure condition Never mark an output as ready without stating the remaining gaps.
From 2ord98/spec-coding-manifesto, MIT.
More from 2ord98/spec-coding-manifesto
- 0.513score
specification-driven-coding
2ord98
Use when a user wants to build, modify, evaluate or improve software with an AI agent or app builder.
SkillCFreshness: C★ 3Claude Code +9 - 0.509score
specification-driven-coding-mobile-app
2ord98
Use when building iOS, Android, Expo, Flutter, SwiftUI, Jetpack Compose, or mobile-first apps.
SkillCFreshness: C★ 3Claude Code +9 - 0.509score
specification-driven-coding-multi-agent-control-system
2ord98
Use when designing multi-agent orchestration, control towers, agentic operations, or tool-calling systems.
SkillCFreshness: C★ 3Claude Code +9 - 0.509score
specification-driven-coding-project-router
2ord98
Use when selecting the correct project profile and blueprint before writing a specification.
SkillCFreshness: C★ 3Claude Code +9 - 0.509score
specification-driven-coding-rag-system
2ord98
Use when designing RAG, knowledge assistants, document chat, or retrieval systems.
SkillCFreshness: C★ 3Claude Code +9 - 0.509score
specification-driven-coding-anti-sameness
2ord98
Use when output risks looking like a generic app-builder app, landing, dashboard, or SaaS.
SkillCFreshness: C★ 3Claude Code +9 - 0.509score
specification-driven-coding-builder-ingestion
2ord98
Use when an AI builder receives this repository as guidance for turning incomplete requests into specific products.
SkillCFreshness: C★ 3Claude Code +9 - 0.509score
specification-driven-coding-vertical-blueprint
2ord98
Use when turning a specification into an implementation-ready blueprint for app builders or coding agents.
SkillCFreshness: C★ 3Claude Code +9 - 0.509score
specification-driven-coding-blueprint-compiler
2ord98
Use when converting a raw brief or spec into a Vertical Blueprint Contract for an AI app builder or coding agent.
SkillCFreshness: C★ 3Claude Code +9 - 0.509score
specification-driven-coding-web-app
2ord98
Use when building websites, SaaS apps, dashboards, admin panels, WordPress themes, or full-stack web products.
SkillCFreshness: C★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 23, 2026 (5 months ago)
- Last release
- May 28, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/2ord98/spec-coding-manifesto
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from 2ord98
- 0.513score
specification-driven-coding
2ord98
Use when a user wants to build, modify, evaluate or improve software with an AI agent or app builder.
SkillCFreshness: C★ 3Claude Code +9 - 0.509score
specification-driven-coding-mobile-app
2ord98
Use when building iOS, Android, Expo, Flutter, SwiftUI, Jetpack Compose, or mobile-first apps.
SkillCFreshness: C★ 3Claude Code +9 - 0.509score
specification-driven-coding-multi-agent-control-system
2ord98
Use when designing multi-agent orchestration, control towers, agentic operations, or tool-calling systems.
SkillCFreshness: C★ 3Claude Code +9 - 0.509score
specification-driven-coding-project-router
2ord98
Use when selecting the correct project profile and blueprint before writing a specification.
SkillCFreshness: C★ 3Claude Code +9 - 0.509score
specification-driven-coding-rag-system
2ord98
Use when designing RAG, knowledge assistants, document chat, or retrieval systems.
SkillCFreshness: C★ 3Claude Code +9 - 0.509score
specification-driven-coding-anti-sameness
2ord98
Use when output risks looking like a generic app-builder app, landing, dashboard, or SaaS.
SkillCFreshness: C★ 3Claude Code +9
Cite this page
specification-driven-coding-evaluation-scorecard skill. Agent Mart. https://agentmart.dev/skills/2ord98-specification-driven-coding-evaluation-scorecard (last updated 2026-10-24)