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

80%

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 ./skills/vibe-research-workflow/SKILL.md

Quality

Content

70%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.

A well-structured orchestrator skill with a clear multi-step workflow, explicit validation checkpoints, and clean one-level-deep progressive disclosure. Its weak spots are mild verbosity from restating rules already in the references, and reliance on "see references" for the executable detail of each phase.

Suggestions

Trim the restated six-rule list and the "meta-skill that orchestrates" paragraph since both duplicate references/behavior-guidelines.md, to improve conciseness.

Inline at least one concrete technique per phase (e.g., the Plan Mode / Small Steps cues for coding) before the "see references" pointer, so the body is actionable without loading every reference.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes competence, but passages like "This skill is a meta-skill that orchestrates tool selection, flow design..." and the restated six rules add padding that could be tightened since the rules already live in references/behavior-guidelines.md.	2 / 3
Actionability	The output format tables, per-phase tool mappings, and integrity-gate checklist give concrete structure, but the core phase procedures are delegated as "see references/..." rather than carrying the executable detail inline, leaving the guidance partially incomplete.	2 / 3
Workflow Clarity	The six-step procedure is clearly sequenced and the Integrity gate provides explicit validation checkpoints with a feedback loop ("Any red-line violation stops the session... fix the violation or consult an advisor before continuing"), matching the level-3 anchor.	3 / 3
Progressive Disclosure	The body is a clean overview pointing to five real one-level-deep references (all verified to exist), each clearly signaled with "See: references/...", and content is appropriately split rather than inlined.	3 / 3
	Total	10 / 12 Passed

Description

90%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 description that pairs a clear statement of what the skill does with an explicit, natural-language trigger clause. The only soft spot is specificity, where the lead framing is slightly more conceptual than a concrete action list.

Suggestions

Lead with concrete actions (e.g., "Plans and enforces an AI-assisted research workflow across coding, figure, and writing phases") before the conceptual framing to lift specificity.

Dimension	Reasoning	Score
Specificity	It names concrete sub-flows ("Vibe Coding, Vibe Figure, and Vibe Writing") and a specific tool list (Cursor, Claude Code, Codex, Figma, Gemini), but the opening framing ("Guides AI-assisted research... with behavioural rules") is conceptual rather than a list of multiple concrete actions, so it sits just below the level-3 anchor.	2 / 3
Completeness	It clearly states both what the skill does and when to use it via an explicit "Use when..." clause with concrete triggers, matching the level-3 anchor exactly.	3 / 3
Trigger Term Quality	Phrases like "how to use AI for research", "Vibe Coding tips", "AI-assisted writing workflow", and "which AI tool for this" are natural things a user would actually say, giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The AI-research integrity-workflow niche and its distinct trigger phrasings make it unlikely to fire for the wrong skill, fitting the level-3 clear-niche anchor.	3 / 3
	Total	11 / 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: HKUSTDial/Supervisor-Skills
Path: skills/vibe-research-workflow/SKILL.md
Commit: aff5de9

Reviewed: 23 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.