CtrlK
BlogDocsLog inGet started
Tessl Logo

research-agent

Market research specialist that searches the web for market data, competitor intelligence, and industry reports, with curated fallback data when offline. Use when gathering external evidence for strategic decisions.

59

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./modules/skills/src/main/resources/META-INF/skills/research-agent/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 concise, well-organized instruction-style skill with commendable anti-fabrication guardrails, but it is more mission statement than runbook: no concrete search command or example, no report format, an undelivered 'curated fallback data' resource, and an implicit rather than explicit search-to-fallback-to-report workflow.

Suggestions

Add an executable example of the DuckDuckGo search (command or code snippet) and a concrete template for the 'structured research report' (e.g. fields for finding, source URL, date retrieved).

Deliver the 'curated industry data' fallback — either bundle it as a references/fallback-data.md file with a clear pointer from SKILL.md, or remove the claim.

Make the workflow explicit and ordered: 1) attempt web search, 2) if unavailable, load curated fallback and label it, 3) summarize with cited URLs, 4) verify every statistic has a source before presenting.

DimensionReasoningScore

Conciseness

The body is lean, assumes competence, and contains no tutorial filler — but the two-sentence intro restates the frontmatter description almost verbatim, and the first Skills bullet ('Search the web for market data, news, and competitor information') repeats the intro a third time. This is 'efficient; minor instances that could be trimmed' (anchor 4) rather than the every-token-earns-its-place level of anchor 5.

4 / 5

Actionability

Guardrails are concrete ('Always cite sources with URLs', 'Limit results to the requested count (1-5)') and a specific source is named ('You scrape DuckDuckGo'), but no executable command, URL, or code example for the search is given, the 'curated industry data' fallback is never located or provided, and 'structured research reports' has no template or format. This matches anchor 3 (some concrete guidance but incomplete, missing key details) — above anchor 2 because guardrails and the named tool give real, if partial, direction.

3 / 5

Workflow Clarity

The intended sequence (search web → fallback to curated data when offline → extract/summarize → produce cited report) is present but spread across the intro and Skills bullets with no explicit ordering, and the fallback condition is only implicit. There are no validation checkpoints (e.g. how to confirm a source URL resolves or that data is current), fitting anchor 3 (sequence present but checkpoints missing or implicit).

3 / 5

Progressive Disclosure

For a sub-50-line skill the section structure (# role, ## Skills, ## Guardrails) is clean and flat with no nested references, which per the simple-skill note could merit a 5. However, the body promises a 'curated industry data' fallback resource that exists nowhere — not inline and not as a bundled reference file — so a claimed resource is undiscoverable, dropping it to anchor 4 (good structure, minor organization gaps).

4 / 5

Total

14

/

20

Passed

Description

78%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 clearly separates this skill's market-research niche and includes an explicit 'Use when' clause. The 'when' trigger is purpose-level rather than phrase-level, and a few natural synonyms are missing, keeping it just short of top marks on completeness and trigger coverage.

Suggestions

Make the 'when' clause more concrete with user-recognizable trigger phrases, e.g. 'Use when the user asks for market data, competitor information, industry reports, or company research to support a strategic decision.'

Add common synonyms such as 'competitor analysis', 'market analysis', or 'competitive landscape' to broaden natural trigger coverage.

Consider mentioning the summarization/report output (e.g. 'and summarizes findings into a cited research report') so the 'what' covers the skill's full capability set.

DimensionReasoningScore

Specificity

The description lists several concrete actions — 'searches the web for market data, competitor intelligence, and industry reports, with curated fallback data when offline' — naming the domain plus multiple specific capabilities, but omits downstream actions the skill performs (extracting, summarizing, structured reporting), so it is not comprehensive. It is above anchor 3 (only 1-2 actions) because four distinct capabilities are named, but below anchor 5 due to the coverage gaps.

4 / 5

Completeness

Both parts are present: a clear 'what' ('searches the web for market data, competitor intelligence, and industry reports, with curated fallback data') and an explicit 'when' ('Use when gathering external evidence for strategic decisions'). However, the when-clause is somewhat abstract — it states a purpose rather than concrete user trigger phrases like 'when the user asks for market data, competitor info, or industry reports' — matching anchor 4 rather than 5.

4 / 5

Trigger Term Quality

Natural phrases like 'market research', 'market data', 'competitor intelligence', and 'industry reports' map well to what a user would say, but common variations such as 'competitor analysis', 'market analysis', 'competitive landscape', or 'company research' are missing. This matches anchor 4 (good coverage, a few natural terms missing) rather than 5, which requires synonyms/extensions-level saturation.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche (market research / competitor intelligence / industry reports) with distinct trigger terms, unlikely to fire for unrelated skills. It fits anchor 5 (clear niche, distinct triggers, minimal conflict risk); the only conceivable overlap is with a generic web-search skill, which the market-research framing clearly disambiguates.

5 / 5

Total

17

/

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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
Atmosphere/atmosphere
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.