or run

tessl search
Log in

perplexity

tessl install https://github.com/softaworks/agent-toolkit --skill perplexity

github.com/softaworks/agent-toolkit

Web search and research using Perplexity AI. Use when user says "search", "find", "look up", "ask", "research", or "what's the latest" for generic queries. NOT for library/framework docs (use Context7) or workspace questions.

Average Score

92%

Content

92%

Description

90%

SKILL.md
Review
Evals

Generated

Validations

Total score

14/16
CriteriaScore

skill_md_line_count

SKILL.md line count is 129 (<= 500)

frontmatter_valid

YAML frontmatter is valid

name_field

'name' field is valid: 'perplexity'

description_field

'description' field is valid (225 chars)

description_voice

'description' uses third person voice

description_trigger_hint

Description includes an explicit trigger hint

compatibility_field

'compatibility' field not present (optional)

allowed_tools_field

'allowed-tools' field not present (optional)

metadata_version

'metadata' field is not a dictionary

metadata_field

'metadata' field not present (optional)

license_field

'license' field is missing

frontmatter_unknown_keys

No unknown frontmatter keys found

body_present

SKILL.md body is present

body_examples

Examples detected (code fence or 'Example' wording)

body_output_format

Output/return/format terms detected

body_steps

Step-by-step structure detected (ordered list)

Content

Suggestions 1

Total score

11/12
DimensionScore

conciseness

The content is lean and efficient, using tables, bullet points, and minimal prose. No unnecessary explanations of what Perplexity or search tools are—assumes Claude's competence throughout.

3/3

actionability

Provides fully executable TypeScript code examples with specific parameters, clear decision trees for tool selection, and concrete examples of correct vs incorrect usage patterns.

3/3

workflow_clarity

Clear priority-ordered tool selection chain with explicit decision criteria. The 'Which Perplexity tool?' quick reference and examples section provide unambiguous guidance for each scenario.

3/3

progressive_disclosure

Content is well-organized with clear sections, but everything is inline in a single file. References to other tools (Context7, Graphite MCP, etc.) are mentioned but not linked to their respective skill files.

2/3

Suggestions

Add links to related skill files (e.g., '[Context7 MCP](./context7.md)') to improve navigation between related tools

Overall Assessment

This is a high-quality skill that excels at conciseness and actionability. The tool selection chain and concrete examples make it immediately usable. The only weakness is that cross-references to related skills (Context7, Graphite MCP, Nx MCP) could be linked rather than just mentioned.

Description

Suggestions 1

Total score

11/12
DimensionScore

specificity

Names the domain (web search/research) and the tool (Perplexity AI), but lacks specific concrete actions beyond generic 'search and research'. Doesn't specify what types of results it returns or capabilities like summarization, source citation, etc.

2/3

completeness

Clearly answers both what (web search using Perplexity AI) and when (explicit trigger terms listed). Also includes helpful exclusion criteria ('NOT for library/framework docs, use Context7') which aids skill selection.

3/3

trigger_term_quality

Excellent coverage of natural trigger terms users would actually say: 'search', 'find', 'look up', 'ask', 'research', 'what's the latest'. These are common, natural phrases for web search requests.

3/3

distinctiveness_conflict_risk

Highly distinctive with explicit boundary conditions. The exclusion of library/framework docs (directing to Context7) and workspace questions creates clear delineation from other skills, reducing conflict risk significantly.

3/3

Suggestions

Add 2-3 specific concrete actions to improve specificity, e.g., 'retrieves current information, summarizes findings with sources, answers factual questions about recent events'

Overall Assessment

This is a well-crafted skill description with strong trigger terms and excellent completeness including explicit exclusion criteria. The main weakness is the lack of specific concrete actions beyond generic 'search and research' - it could benefit from listing specific capabilities like 'retrieve current information', 'summarize findings', or 'cite sources'.