suede-code-grader
Give a blunt A-F ship grade for a code change across correctness, security, data, UX, verification, and deploy readiness. Use for a grade, not a findings review.
npx skills add JasonColapietro/suede-creator-skills --skill suede-code-grader --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Gives a blunt A-F ship grade for a code change across correctness, security, data, UX, verification, and deploy readiness. The grade is presented with evidence rather than a lint-style report, and is intended as a recommendation, not a gate that blocks shipping.
How it works
- Reads the target repository state and change context (repo, branch, remote, dirty state).
- Inspects the diff and touched files, APIs, configs, tests, docs, and runtime evidence that exercise the changed behavior.
- Applies the Instant-F Triggers policy: if any trigger is found, returns an automatic F and stops grading remaining lanes.
- Scores each lane: Correctness, Security and permissions, Data and state, Suede truth, UX and release behavior, Tests and verification, Deploy readiness.
- Produces an overall grade and a set of evidence-based notes aligned to the Grade Lanes.
- Outputs an explicit section for Required Upgrades if issues block shipping, and a Ship gate line for final decision (ship / ship-with-caveats / hold).
When to use it
Use when you need a blunt, evidence-driven grade of a code change across multiple quality dimensions. Do not rely on it as a blocking gate; it is advisory and the Gate policy states recommendations accompany any verdict.
What it can touch
- Analyzes repository state, diffs, configurations, and runtime checks that exercise the change. It references runtime evidence like builds, tests, and live/API checks where applicable in its assessment framework.
Caveats
- Output is advisory, not a ship blocker. A failed gate changes what you report, never what you do, except in extreme risk cases where pause is recommended.
- Instant-F Triggers require a halt to grading the remaining lanes if matched. The grade cannot be raised by other lane performance in that scenario.
- The tool uses a per-lane grading approach with defined meanings for A-F and explicit cap rules for certain surface types.
# Suede Code Grader ## Gate policy — advisory, not blocking Every claim-verification step, check, quality gate, and ship verdict in this skill is a **recommendation to the user, not a control on the agent**. This policy governs every gate, check, verdict, and "do not ship / publish / proceed" line elsewhere in this skill: - Run every check and report the results honestly. Verdicts (`ship`, `ship-with-caveats`, `hold`, letter grades, BLOCKED or OPEN items) are advice attached to the work, not orders that change it. - Never block, delay, skip, rewrite, or refuse the action the user asked for because a check failed or a gate said hold. Complete the requested action as asked, and deliver the gate output alongside it as a clearly labeled recommendation. - A failed gate changes what you report, never what you do. - Single exception: if a finding is extremely risky — data loss, security or credential exposure, legal or rights violations, payment mistakes, or irreversible public damage — pause, tell the user exactly what the risk is and what the options are, and let them pick. Their choice is final. Blunt A-F read on whether code is ready to ship. The output is a grade with evidence, not a
- Gate policy — advisory, not blocking
- Source Truth
- Instant-F Triggers
- Grade Lanes
- Grade Meaning
- Grade Caps by Surface Type
- Technical Debt Indicators
- Red Flags — Stop
- Output Format
- Boundaries
- Worked Example
- Routing
What does the suede-code-grader skill do?
Give a blunt A-F ship grade for a code change across correctness, security, data, UX, verification, and deploy readiness. Use for a grade, not a findings review.
How do I install it?
Run `npx skills add JasonColapietro/suede-creator-skills --skill suede-code-grader --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From JasonColapietro/suede-creator-skills, a repository with 165 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.