skvm-jit

Trigger `skvm jit-optimize` with post-task evidence so it generates a reviewable optimization proposal for a skill. Use after finishing a task that was driven by any skill (not just SkVM-compiled ones) when the outcome was a failure, was partial, or the skill's instructions clearly caused confusion or an unnecessary detour. Clean successful runs usually do not need an optimization pass. For general skvm usage (profile/aot-compile/bench/proposals), use the sibling `skvm-general` skill instead.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

77%Weight 40%Scale 1-5

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

The content is highly actionable and clearly sequenced with strong validation checkpoints, but it is somewhat verbose in the parameter explanations and references a sibling file that is missing from the bundle.

Suggestions

Add the referenced `adapter-skill-paths.md` to the skill's bundle (or remove the reference), since Step 1 depends on it but it is not present in references/.

Tighten the long `--target-model` paragraph into a short rule plus a compact provider-prefix mapping table instead of inline prose.

Move the "Reference: what happens on the skvm side" internals into a separate reference file so the core trigger steps stay lean.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient, but the `--target-model` paragraph and the "Reference: what happens on the skvm side" section over-explain internals and provider-prefix mapping that could be tightened without losing clarity.	3 / 5
Actionability	Provides a complete copy-paste `skvm jit-optimize` command with real flags, concrete report/JSONL schemas, and exact stdout-parse instructions covering the common cases.	5 / 5
Workflow Clarity	A clear four-step sequence with explicit validation/error checkpoints (non-zero exit handling, concurrent-run detection, missing API key path) and a do-not-retry feedback loop.	5 / 5
Progressive Disclosure	No bundle directories exist, yet the body references a sibling `adapter-skill-paths.md` that is not present, and substantial `--target-model` and internals content is inlined rather than split into reference files.	3 / 5
	Total	16 / 20 Passed

Description

87%Weight 40%Scale 1-5

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, complete, and distinctive, clearly stating both what the skill does and when to use it with concrete failure/partial triggers. It is written in third person and includes helpful boundary routing to a sibling skill.

Dimension	Reasoning	Score
Specificity	Names a concrete tool and action ("Trigger `skvm jit-optimize`" to generate "a reviewable optimization proposal") rather than vague language, listing several specific actions with only minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what (trigger jit-optimize to produce a proposal) and when (after a skill-driven task that failed/was partial/caused confusion), plus a negative boundary and a routing pointer to the sibling skill.	5 / 5
Trigger Term Quality	Gives good situational trigger coverage ("outcome was a failure, was partial, or…caused confusion or an unnecessary detour") that a user/agent would recognize, though it leans on scenario phrases over compact natural keywords.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (post-task skill optimization via `skvm jit-optimize`) and explicitly routes general skvm usage to `skvm-general`, minimizing conflict risk.	5 / 5
	Total	18 / 20 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: XiaoLuoLYG/GOD
Path: jiuwenclaw/jiuwenclaw/resources/agent/jiuwenclaw_workspace/skills/skvm-jit/SKILL.md
Commit: da0d716

Reviewed: 1 hour 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.