add-new-jit-ee-api

Add a new API to the JIT-VM (aka JIT-EE) interface in the codebase.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/add-new-jit-ee-api/SKILL.md

Quality

Content

80%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill body is highly actionable and token-efficient, with concrete paths and copy-paste diffs for each layer of the JIT-EE extension. Its main gaps are the lack of an executable validation/build feedback loop and a monolithic structure that could offload the large SuperPMI section to a reference file.

Suggestions

Add a verification step after generation/edits, e.g. build CoreCLR and confirm the new API compiles, with a fix-and-retry loop, to lift workflow_clarity to 3.

Move the detailed SuperPMI step-6 per-file instructions and diffs into a references file (e.g. superpmi.md) linked one level deep, keeping SKILL.md as an overview.

Tighten the repeated 'Implement the API if asked, leave ... otherwise' phrasing into a single stated convention to recover a few tokens.

Dimension	Reasoning	Score
Conciseness	The body is lean and task-focused with concrete file paths and diffs, assuming Claude's competence; the only explanatory note (SuperPMI's role) is justified internal-tooling context Claude would not already know.	3 / 3
Actionability	It provides specific repo paths, copy-paste-ready diff examples for every layer, and concrete commands (gen.sh/gen.bat), giving fully executable guidance.	3 / 3
Workflow Clarity	The 8 steps are explicitly ordered and a Definition-of-Done checklist is present, but for a 10-file batch change there is no executable build/test validation or fix-retry feedback loop, which caps the score at 2.	2 / 3
Progressive Disclosure	Content is well-sectioned into Goal/Inputs/Steps/DoD, but it is a monolithic ~230-line single file with large inline diffs and no one-level-deep references that the substantial SuperPMI detail could be split into.	2 / 3
	Total	10 / 12 Passed

Description

57%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and clearly scoped to a narrow niche, but it only conveys the 'what' with a single action and lacks an explicit 'when to use' trigger clause. Adding a 'Use when...' clause and a few natural-term variations would raise completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when adding or extending a JIT-VM/JIT-EE API in the CoreCLR JIT interface.'

Include natural trigger variations users might say, such as 'add a JIT-EE API', 'extend the JIT-VM interface', or 'add a CORINFO method'.

Optionally enumerate the supporting actions (update ThunkInput, regenerate, edit corinfo.h/CorInfoImpl/jitinterface.cpp, wire SuperPMI) to lift specificity to the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ('JIT-VM (aka JIT-EE) interface') and one concrete action ('Add a new API'), but does not list multiple specific actions, so it stops short of the top anchor.	2 / 3
Completeness	It states what the skill does but provides no 'Use when...' or equivalent trigger for when to invoke it, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Terms like 'JIT-VM', 'JIT-EE', and 'API' are what a specialist would say, but only one phrasing is offered with no common variations, leaning on technical jargon.	2 / 3
Distinctiveness Conflict Risk	The JIT-VM/JIT-EE interface extension niche is highly specific with distinct triggers, making conflict with other skills unlikely.	3 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: dotnet/runtime
Path: .github/skills/add-new-jit-ee-api/SKILL.md
Commit: ba10a6e

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.