search-specialist

Expert web researcher using advanced search techniques and synthesis. Masters search operators, result filtering, and multi-source verification. Handles competitive analysis and fact-checking. Use PROACTIVELY for deep research, information gathering, or trend analysis.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/search-specialist/SKILL.md

Quality

Content

71%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.

The body is a well-structured, concise overview of search tactics and a clear sequenced workflow, but the instruction-only guidance lacks concrete executable operator syntax, which limits actionability. Progressive disclosure and conciseness are strong for a short single-purpose skill.

Suggestions

Add concrete search operator examples (e.g., `site:gov`, `"exact phrase"`, `-exclude`, `filetype:pdf`, `before:/after:`) under Query Optimization so guidance is executable rather than descriptive.

Trim generic boilerplate in 'Instructions' ('Apply relevant best practices and validate outcomes') and the 'Do not use this skill when' section, which restate the obvious.

Make the verification checkpoint explicit as a feedback loop in the Approach steps (e.g., 'If sources contradict, query variations targeting the disputed fact and re-verify').

Dimension	Reasoning	Score
Conciseness	The body is mostly lean bullet-driven content with little concept over-explanation, but generic boilerplate ('Apply relevant best practices and validate outcomes', the 'Do not use this skill when' section) could be trimmed, fitting the 'efficient; minor over-explanation' anchor.	4 / 5
Actionability	Tactics are named concretely ('Use specific phrases in quotes', 'Exclude irrelevant terms with negative keywords', 'allowed_domains for trusted sources') but lack executable specifics such as actual operator syntax (site:, -term, filetype:), leaving key details missing.	3 / 5
Workflow Clarity	The numbered 'Approach' section sequences 1-5 (understand objective, create query variations, search then refine, verify across sources, track contradictions) with a verification checkpoint at step 4; minor validation gaps keep it just below a 5.	4 / 5
Progressive Disclosure	Under 50 lines with no external bundle files, the skill is well-organized with clear section headers (Focus Areas, Search Strategies, Approach, Output), qualifying for the top anchor per the simple-skill exception.	5 / 5
	Total	16 / 20 Passed

Description

83%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.

The description clearly states both capabilities and proactive trigger contexts in third-person voice, with concrete actions and natural trigger phrases. It is slightly broad in distinctiveness and trigger-term specificity, keeping it just below the top of the scale on those dimensions.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('search operators, result filtering, and multi-source verification', 'competitive analysis and fact-checking'), giving broad coverage with only minor gaps, matching the 'several specific actions; minor gaps' anchor.	4 / 5
Completeness	Explicitly answers what ('Expert web researcher using advanced search techniques and synthesis...') and when ('Use PROACTIVELY for deep research, information gathering, or trend analysis') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural user phrases like 'deep research', 'information gathering', 'trend analysis', and 'fact-checking' — good keyword coverage, though it misses common synonyms/file-type specifics that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	Web research is a mostly distinct niche with clear triggers, but broad terms like 'information gathering' create minor overlap risk with general research/search skills, fitting 'mostly distinct; minor overlap risk'.	4 / 5
	Total	17 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: rmyndharis/antigravity-skills
Path: skills/search-specialist/SKILL.md
Commit: 3eff4af

Reviewed: 7 days ago

Table of Contents

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.