vibe-research-workflow

Guides AI-assisted research across three sub-flows, Vibe Coding, Vibe Figure, and Vibe Writing, with behavioural rules that keep the user in charge of academic judgment while delegating mechanical work to AI. Recommends the right tool (Cursor, Claude Code, Codex, Figma, Gemini) for the current stage. Use when the user asks 'how to use AI for research', 'Vibe Coding tips', 'AI-assisted writing workflow', 'which AI tool for this', or starts an AI-assisted work session.

Quality

86%

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

73%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 body is well-structured with a clear sequenced procedure, a strong integrity-gate validation mechanism, and good progressive disclosure to real reference files. The weakest area is actionability: in-body content leans on structural templates and file pointers rather than concrete executable steps.

Suggestions

Inline a few concrete executable examples (e.g., a sample tool-recommendation call, a sample completed output-format table) so Claude can act without first opening every reference file.

Tighten the 'When NOT to use' routing prose into terse bullet criteria, trimming framing like 'two-to-five times productivity gain' that Claude does not need.

Format the references/... pointers as markdown links (e.g., [behavior-guidelines.md](references/behavior-guidelines.md)) to improve one-click navigation.

Dimension	Reasoning	Score
Conciseness	Mostly lean and well-structured, assuming Claude's competence, but contains some padded framing ('two-to-five times productivity gain', 'modern research workflow') and a verbose 'When NOT to use' routing section that could be tightened.	4 / 5
Actionability	Provides a clear numbered procedure, integrity-gate checklist, and output-format table templates, but the in-body guidance mostly directs Claude to reference files rather than giving concrete executable steps, leaving key execution details external.	3 / 5
Workflow Clarity	A clear six-step sequence with a dedicated integrity gate containing explicit validation checkpoints and a feedback loop ('Any red-line violation stops the session... fix or consult an advisor'), plus [user-attest]/[inspection] tagging that makes validation states explicit.	5 / 5
Progressive Disclosure	A concise overview body that clearly signals five real, one-level-deep reference files organized by section, with bulk detail appropriately externalized; minor gap is that references are plain paths rather than markdown links, slightly reducing navigability.	4 / 5
	Total	16 / 20 Passed

Description

91%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.

A strong, well-constructed description that clearly states capabilities and provides explicit, natural trigger phrases for when to use it. The main gap is that the described actions lean toward orchestration/governance rather than enumerating comprehensive concrete output actions.

Dimension	Reasoning	Score
Specificity	Names the domain (AI-assisted research) and three concrete sub-flows plus tool recommendation, but the actions are governing/orchestration actions rather than a comprehensive list of concrete output actions, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both 'what' (guides three sub-flows with behavioural rules and tool recommendation) and 'when' via an explicit 'Use when...' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural quoted trigger phrases users would actually say ('how to use AI for research', 'Vibe Coding tips', 'AI-assisted writing workflow', 'which AI tool for this') alongside concrete tool names, giving comprehensive coverage.	5 / 5
Distinctiveness Conflict Risk	A clear niche (Vibe Research, named sub-flows, integrity-gated) with distinct triggers; minor overlap risk with generic 'AI for research' or adjacent drafting skills, but largely distinguishable.	4 / 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: HKUSTDial/Supervisor-Skills
Path: skills/vibe-research-workflow/SKILL.md
Commit: 207bc6f

Reviewed: 9 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.