Tessl • The management layer for AI agent skills

An excellent command reference: fully executable examples, explicit command-selection and flag-placement guidance, and clean one-level-deep links to sibling skills. The only weaknesses are minor — the Backend/Auth section restates details already covered by the root SKILL.md it links to.

Suggestions

Trim the Backend/Auth section to a short pointer to the root SKILL.md, keeping only the precedence one-liner, since the full details are duplicated from the linked file.

Mention the OpenRouter search-fallback caveat once (in the Backend/Auth section) and keep only the snippet/date null behavior in the search section, to avoid repeating the fallback in two places.

Dimension	Reasoning	Score
Conciseness	The body is dense flag tables and executable examples with essentially no explanation of concepts Claude already knows ("Returns titles, URLs, and snippets. Does not generate an AI answer"), matching anchor 4. It is not a 5 because the Backend/Auth section restates precedence and fallback details that the linked root SKILL.md already covers — a minor instance that could be trimmed.	4 / 5
Actionability	Every example is fully executable and copy-paste ready, spanning basic queries, filters, JSON input, stdin pipes, jq extraction ("perplexity-cli ask \"What is TLS?\" \| jq -r '.content'"), and the stderr-discard streaming pattern for agents, covering the common cases — anchor 5.	5 / 5
Workflow Clarity	As a command reference with no multi-step process and no destructive or batch operations, the single action is unambiguous: command selection is explicit ("Use `ask` or `chat` when you need an AI-synthesized response"), global flag placement is stated and demonstrated ("These always go before the subcommand"), and failure behavior is specified ("Neither → exit `2`"). Per the simple-skill guideline this scores 5.	5 / 5
Progressive Disclosure	Per-command sections (Syntax → Arguments → Options → Examples) are well organized, and the outbound references to the root SKILL.md and models/SKILL.md are one level deep, clearly linked, and justified ("See root SKILL.md for backend resolution"). It is not a 5 because the Backend/Auth section duplicates content from the file it points to rather than purely referencing it — a minor organization gap.	4 / 5
	Total	18 / 20 Passed

Description

70%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 precise, tool-specific description that clearly states what the skill provides, but it omits any explicit 'when to use' trigger guidance and does not explain what each command does functionally. Adding a 'Use when...' clause and one clause on command purpose would lift it to the top band.

Suggestions

Add an explicit trigger clause, e.g. 'Use when running perplexity-cli commands or when the user asks for a Perplexity web search or cited AI answer via CLI', to raise completeness beyond the 3 cap.

Briefly state what each command does, e.g. 'search returns web results without an AI answer; ask/chat return AI-synthesized answers with citations', to improve specificity and trigger coverage.

Include natural synonyms such as 'Perplexity API', 'web search', or 'AI answer' so the description matches how users phrase these requests.

Dimension	Reasoning	Score
Specificity	"Full command syntax, all flags, and worked examples" names several concrete deliverables for the three named commands (search, ask, chat), matching anchor 4. It falls short of anchor 5 because it never states what the commands actually do (web results vs AI answer vs streaming), and exceeds anchor 3's '1-2 concrete actions'.	4 / 5
Completeness	The 'what' is clear and concrete ("Full command syntax, all flags, and worked examples for perplexity-cli search, ask, and chat commands") but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. The 'when' is only weakly implied by the tool name, so it is not a 2 — the 'what' is not vague.	3 / 5
Trigger Term Quality	Includes the exact natural terms a user would say when needing this skill ("perplexity-cli", "search", "ask", "chat", "command syntax", "flags"), but misses common synonyms such as "Perplexity API", "web search", or "AI answer" — good coverage with a few natural terms missing, so anchor 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	The unique tool name plus its three subcommand names give a clear niche with distinct triggers and minimal conflict risk — a user wanting perplexity-cli syntax would unambiguously select this skill over any sibling skill.	5 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 suspicious	Warning

	Total	15 / 16 Passed

Repository: slurpyb/perplexity-cli
Path: .claude/skills/web-search-with-perplexity/commands/SKILL.md
Revision: 5624eaa

Reviewed: 14 days ago

Discovery Implementation Validation

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.

perplexity-cli-commands

Table of Contents

Is this your skill?