markstream-migration

Audit and migrate existing Markdown rendering to Markstream. Use when Codex needs to replace another renderer, classify direct vs custom vs plugin-heavy usage, preserve behavior during adoption, migrate custom renderers into scoped Markstream overrides, or decide when `nodes` streaming is worth adopting.

Quality

92%

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

Quality

Content

85%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.

An information-dense, actionable migration playbook with specific Markstream prop/mode names, a well-sequenced workflow ending in validation, and a properly split-out one-level reference checklist. Its main weakness is mild redundancy between the Workflow and Default Decisions sections and a verbose streaming subsection.

Suggestions

Collapse the restated ordering rules in 'Default Decisions' (e.g. 'Renderer swap first, streaming optimization second', 'Smooth streaming is an intermediate option...') since they duplicate steps 3 and 6 of the Workflow.

Tighten step 6's 'Streaming vs recovering history' block into a compact prop table (mode / smooth-streaming / fade per scenario) instead of two prose sentences.

Add an explicit validate-then-fix retry loop in step 7 ('If tests/build fail, fix and re-run') to make the feedback loop explicit rather than implied.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence (no concept padding), but 'Default Decisions' restates Workflow ordering ('Renderer swap first, streaming optimization second', 'Smooth streaming is an intermediate option...') and step 6's streaming-vs-history detail is verbose, so it is not fully lean like the score-3 anchor.	2 / 3
Actionability	Concrete, copy-ready guidance dominates: 'prefer renderer-local `streamingComponents` ... and `htmlComponents`', 'use `setCustomComponents`', 'prefer `customHtmlTags`', 'choose `mode="chat"` ... `mode="docs"` ... `mode="minimal"`', 'pair it with `:fade="false"`'. Though instruction-only with no code block, the specific API/prop names meet the actionable bar per the code-vs-instruction scoring note.	3 / 3
Workflow Clarity	A clear 7-step numbered sequence with an explicit validation checkpoint ('Run the smallest relevant tests or build') and a gap-review checkpoint ('Review gaps honestly ... Call out ... behavior that still needs manual review'), matching the score-3 anchor; it is not capped at 2 because a validation step is present.	3 / 3
Progressive Disclosure	SKILL.md is an overview that points to one real, well-signaled one-level-deep reference ('Read [references/adoption-checklist.md] before changing code', verified to exist) plus a 'Useful Doc Targets' list, matching the score-3 clear-overview anchor rather than the inline-monolithic score-2 anchor.	3 / 3
	Total	11 / 12 Passed

Description

100%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.

A strong, third-person description that names several concrete migration actions and provides an explicit 'Use when...' trigger covering classification, behavior preservation, custom-renderer migration, and streaming-mode decisions. It is specific, complete, and clearly distinct to Markstream adoption.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Audit and migrate existing Markdown rendering', 'classify direct vs custom vs plugin-heavy usage', 'migrate custom renderers into scoped Markstream overrides', 'decide when `nodes` streaming is worth adopting' — matching the score-3 anchor for several specific concrete actions, not the score-2 single-domain anchor.	3 / 3
Completeness	It states what ('Audit and migrate existing Markdown rendering to Markstream') and an explicit 'Use when Codex needs to replace another renderer, classify ... preserve behavior ... or decide when `nodes` streaming is worth adopting' trigger clause, satisfying the score-3 anchor for both what AND when; not capped at 2 since the trigger is explicit.	3 / 3
Trigger Term Quality	Natural domain terms a migrating user would actually say are well covered: 'Markdown rendering', 'Markstream', 'renderer', 'custom renderers', 'plugin-heavy', 'nodes streaming'. It is not generic jargon (score 1) nor missing common variations (score 2).	3 / 3
Distinctiveness Conflict Risk	The Markstream-specific niche ('Markstream', 'scoped Markstream overrides', '`nodes` streaming') with distinct migration triggers makes it unlikely to fire for unrelated skills, matching the score-3 clear-niche anchor rather than the overlapping score-2 anchor.	3 / 3
	Total	12 / 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: Simon-He95/markstream-vue
Path: .agents/skills/markstream-migration/SKILL.md
Commit: f25ebd5

Reviewed: 11 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.