CtrlK
BlogDocsLog inGet started
Tessl Logo

deep-research

Runs a deep, survey-grade literature investigation on a research topic: freezes research questions, searches from multiple adversarial perspectives, verifies every citation, synthesizes evidence into a MECE taxonomy with in-sentence cross-comparison, and answers the research questions in an evidence-first report. Use when the user asks for a literature review, a survey of a field, research landscape mapping, or a deep dive into what is known about a topic.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

A well-structured methodological skill body: a clearly sequenced research workflow with explicit validation gates and feedback loops, lean prose that assumes competence, and clean one-level-deep progressive disclosure into real reference files. Minor tightening of the opening stance prose and slightly more inline detail would lift the actionability/conciseness dimensions.

Suggestions

Trim the narrative stance-setting in the Overview ('The role is a senior researcher...', 'This is not a search engine and not a bullet-point answer') to the essentials to improve conciseness.

Inline one or two concrete artifacts for actionability — e.g. a short example of the MECE taxonomy structure or a sample search-perspective keyword set — alongside the references.

Consider a one-line explicit validation/retry statement near Phase 1 candidate verification so the feedback loop is visible inline rather than only via the citation-protocol reference.

DimensionReasoningScore

Conciseness

Efficient and assumes Claude's competence — it never explains known concepts (what a survey or MECE is) — but the opening overview and a few discursive stance-setting passages could be trimmed slightly.

4 / 5

Actionability

Provides concrete, specific guidance (three-to-five named search perspectives, the six-gate table, per-field evidence standards), with detailed protocols appropriately delegated to reference files rather than inlined.

4 / 5

Workflow Clarity

Clear sequence (Step 0 brief → Phase 1 scout → Phase 2 synthesize → presentation) with explicit validation via the six gates, severity ratings, failure routes, and a feedback loop ('Iterate until every gate is CLEAR and the self-adversarial pass stops finding corrections').

5 / 5

Progressive Disclosure

SKILL.md is an overview pointing to seven real, clearly signaled one-level-deep reference files (e.g. references/citation-protocol.md); verified the reference files contain no nested references, so navigation stays flat and easy.

5 / 5

Total

18

/

20

Passed

Description

100%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, third-person description that pairs a comprehensive list of concrete capabilities with an explicit, natural-language 'Use when' trigger clause. It is specific, complete, and clearly distinct from sibling research/writing skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'freezes research questions', 'searches from multiple adversarial perspectives', 'verifies every citation', 'synthesizes evidence into a MECE taxonomy with in-sentence cross-comparison', 'answers the research questions in an evidence-first report' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' (the listed actions) and 'when' via a concrete 'Use when the user asks for a literature review, a survey of a field, research landscape mapping, or a deep dive...' clause.

5 / 5

Trigger Term Quality

Includes natural phrases users actually say with synonyms — 'literature review', 'survey of a field', 'research landscape mapping', 'deep dive into what is known about a topic'.

5 / 5

Distinctiveness Conflict Risk

Clear niche (survey-grade literature investigation) with distinct triggers; minimal conflict risk, reinforced by named sibling-skill boundaries in the body.

5 / 5

Total

20

/

20

Passed

Validation

100%

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
Reviewed

Table of Contents

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.