CtrlK
BlogDocsLog inGet started
Tessl Logo

deep-research

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.

68

Quality

85%

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

82%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, actionable research skill with concrete tool calls and a usable report template. Its main weaknesses are implicit validation checkpoints (the quality checklist is not wired into the workflow) and a body that, while well-organized, could split the report template into a reference for tighter progressive disclosure.

Suggestions

Embed explicit validation checkpoints inside the workflow (e.g. after Step 4, "verify every Key Takeaway claim has >=2 corroborating sources before writing"), rather than relegating checks to a separate Quality Rules list.

Move the full report markdown template and the Examples block into a reference file (e.g. references/report-template.md) and link to it from Step 5, keeping the core workflow leaner.

Tighten the Untrusted Sources section by collapsing the five bullets into three consolidated rules, since several overlap in intent.

DimensionReasoningScore

Conciseness

The body is mostly lean and assumes Claude's competence, with a justified drift warning and minimal concept padding; a few sections (the five Untrusted Sources bullets, the Examples block) could be trimmed slightly.

4 / 5

Actionability

Concrete MCP calls with real parameters (e.g. firecrawl_search(query, limit: 8), web_search_advanced_exa(..., startPublishedDate)) and a copy-paste report template cover the common cases directly.

5 / 5

Workflow Clarity

Six numbered steps are clearly sequenced with a Quality Rules checklist and short/long delivery branching, but validation checkpoints are implicit (checklist sits outside the flow) rather than embedded as explicit verify-then-proceed gates.

4 / 5

Progressive Disclosure

No bundle files exist, so this is a single well-organized file with clear section headers and a drift warning up top; it is appropriately self-contained, though somewhat long for one file with minor organization gaps.

4 / 5

Total

17

/

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.

A strong description: third-person voice, concrete actions, and an explicit Use-when clause with natural triggers. Only minor keyword-coverage and primitive-action gaps keep specificity and trigger quality just below full marks.

DimensionReasoningScore

Specificity

"Searches the web, synthesizes findings, and delivers cited reports with source attribution" names several concrete actions plus the tooling (firecrawl/exa MCPs), but does not enumerate the scrape/crawl primitives, leaving minor coverage gaps.

4 / 5

Completeness

It explicitly states what the skill does (multi-source search, synthesis, cited reports) and when to use it with concrete trigger phrasing, satisfying both halves clearly.

5 / 5

Trigger Term Quality

"Use when the user wants thorough research on any topic with evidence and citations" plus "research" gives good natural keyword coverage, though common variants like "deep dive" or "investigate" are absent.

4 / 5

Distinctiveness Conflict Risk

The firecrawl/exa MCP framing plus cited-report deliverable carves a clear niche with distinct triggers and minimal overlap with other skills.

5 / 5

Total

18

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 3 missing

Warning

Total

14

/

16

Passed

Repository
affaan-m/ECC
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.