Skip to main content
affpapa.org
RU EN
skill CX Codex

grade-system — Claude Code skill: grading and installation

This skill grades an MEL/SRHR system across components, quality dimensions, and adapted OECD-DAC criteria. Use it for a structured review of risks and evidence.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add gasserane/personal-skills --skill grade-system -a claude-code
Open on GitHub

What grade-system does

grade-system assigns letter grades to nine system components and ten quality dimensions. It reviews Ann, Vi, Li, Researcher, specialists, the wiki, the test harness, the qa_block schema, and the three-repository architecture. The result also covers three concrete risks, questions an external evaluator would ask, and changes that could move the grade.

The skill draws on improvement logs, the agent registry, wiki pages, and test runs such as python tests/run_tests.py, including fixture coverage. Its report must state that the evaluator is operating inside the system and may favour patterns similar to its own reasoning. That internal calibration does not replace review by a community or an external MEL practitioner. The project files and Python test commands must be accessible for the assessment to use them.

What it helps with

  • grade an MEL/SRHR system by component
  • check reliability across an agent architecture
  • map system quality to adapted OECD-DAC criteria
  • surface three concrete operational risks
  • identify changes that could raise the grade

Example prompts for the agent

  • Run /grade-system and assess the current MEL/SRHR system using its logs and tests.
  • Use /grade to review the components, quality dimensions, and adapted OECD-DAC criteria.
  • Grade the system honestly and list what an external evaluator would still need to examine.

How to install grade-system

1Skills CLI (Vercel)

npx skills add gasserane/personal-skills --skill grade-system -a claude-code

2Manually: put the files in place

~/.claude/skills/grade-system/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/grade-system/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about grade-system

How do I install grade-system in Claude Code?

Run npx skills add gasserane/personal-skills --skill grade-system -a claude-code, then check ~/.claude/skills/grade-system/SKILL.md.

What does grade-system do?

It gives letter grades across system components and quality dimensions, identifies concrete risks, recommends grade-movement steps, and records the bias limits of internal grading.

How is grade-system different from system-audit?

grade-system rates the overall quality posture. system-audit looks for specific issues that need fixing.

Similar skills

SKILL.md skills catalog →
find-skills vercel-labs Discovers and installs agent skills from skills.sh directly inside your coding assistant. Handy when you need domain-specific workflows for a project. CX Codex +1 4,000,000installs frontend-design official anthropics This skill guides intentional visual design for new interfaces and redesigns. Use it when a generic generated UI is not enough. 1,025,790installs grill-me Matt Pocock grill-me interviews you about a plan or design to expose gaps and sharpen decisions. Use it before implementation starts. 1,424,476installs grill-with-docs Matt Pocock This skill interviews you about a plan or design and creates ADRs and a glossary along the way. Use it when decisions need sharper definition. 1,219,756installs improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. 1,163,035installs design-taste-frontend Leonxlnx This skill directs the design of public pages and work screens, then checks the result in a browser through screenshots. Use it when an interface feels generic or unfinished. CX Codex +1 678,700installs

From the same set13

li Catalogs, retrieves and reorganizes documents in a personal knowledge library and MEL Wiki. It does not answer domain questions. CX Codex +1 652installs toc-builder Builds a Theory of Change with preconditions, testable assumptions and an evidence plan. Useful for programme design and funder submissions. CX Codex +1 645installs instrument-designer Builds the data-collection tool itself: questionnaires, interview and focus-group guides, observation checklists. Useful once indicators exist but nothing measures them. CX Codex +1 645installs wrap-up This skill closes a working session: it gathers git state, errors and open tasks, delivers a status report, then commits and pushes pending work. CX Codex +1 639installs learning-product Turns a Researcher Evidence Brief into one of four outputs: a two-page MA brief, a workshop pack, a regional brief or a donor memo. Citations stay limited to the brief. CX Codex +1 626installs accreditation-desk-review Runs the desk-review stage of an IPPF Member Association accreditation: judge the self-assessment and evidence against each standard and check, record reviewer conclusions, and draft interview questions. CX Codex +1 557installs implementation-pack Builds a post-award project pack: applies the signed grant-agreement figures to a proposal baseline and produces files a project manager can run with. CX Codex +1 551installs mel-discipline Makes the agent walk five stages when writing an analytical deliverable, from scoping to an honest report on what it checked. Useful when a deadline pushes you to cite a source you never opened. CX Codex +1 355installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor