CtrlK
BlogDocsLog inGet started
Tessl Logo

web-research

Research topics on the web, gather information from multiple sources, and summarize findings.

48

Quality

51%

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 ./apps/desktop/bundled-skills/web-research/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

42%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is concise and well-structured with a clear sequenced workflow, but it is largely abstract guidance lacking concrete, executable instructions or validation feedback loops, which limits its actionability.

Suggestions

Replace abstract steps with concrete, executable guidance — name specific tools, commands, or query techniques for searching and extracting web content.

Add an explicit verification checkpoint with a feedback loop, e.g. 'If sources conflict, search additional authoritative sources before summarizing.'

Trim the generic Requirements section or convert it into concrete, named tool capabilities rather than vague ability statements.

DimensionReasoningScore

Conciseness

The body is mostly lean and well-organized into clear sections, but the generic Requirements lines and lightly padded Best Practices/Examples could be tightened, so not every token earns its place.

2 / 3

Actionability

Guidance like 'Use browser to search multiple sources' and 'Cross-reference facts across sources' is abstract direction with no concrete commands, code, or specific tool invocations — it describes rather than instructs.

1 / 3

Workflow Clarity

The five-step Research Process is clearly sequenced, but verification appears as a plain step with no validation checkpoint or feedback loop for when cross-referencing fails.

2 / 3

Progressive Disclosure

No bundle files exist and the skill is under 50 lines, yet it is well-organized into clearly labeled sections, so the simple-skill allowance permits a full score.

3 / 3

Total

8

/

12

Passed

Description

60%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description names several concrete actions and is concise, but it lacks an explicit 'when to use' trigger clause and offers only a narrow set of natural trigger terms, making it somewhat indistinct from general research capabilities.

Suggestions

Add a 'Use when...' clause naming concrete trigger scenarios, e.g. 'Use when the user asks to research a topic, look up information, or gather findings from multiple web sources.'

Broaden trigger term coverage with natural phrases users actually say, such as 'look up', 'find information about', or 'search the web'.

Sharpen distinctiveness by tying the skill to a specific niche, such as multi-source synthesis with cited findings, to reduce overlap with generic research skills.

DimensionReasoningScore

Specificity

The description lists three concrete actions — 'Research topics on the web', 'gather information from multiple sources', and 'summarize findings' — matching the anchor for multiple specific concrete actions.

3 / 3

Completeness

It clearly states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger for when to use it, capping completeness at 2 per the judging guidelines.

2 / 3

Trigger Term Quality

It includes relevant natural terms like 'research' and 'web', but omits common variations users would say such as 'look up', 'find information about', or 'search the web'.

2 / 3

Distinctiveness Conflict Risk

'Web research' is a fairly generic capability with no domain-specific triggers, so it could overlap with other research or look-up skills, but it is not so generic as to conflict broadly.

2 / 3

Total

9

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
accomplish-ai/coworker
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.