CtrlK
BlogDocsLog inGet started
Tessl Logo

search-specialist

Expert web researcher using advanced search techniques and

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/search-specialist/SKILL.md

The canonical home for this skill is search-specialist in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 compact, well-organized instruction set for web research with a clear workflow and concrete technique pointers. Its main weaknesses are the absence of worked query examples and a dangling reference to a playbook file that does not exist.

Suggestions

Add 1-2 worked query examples showing exact syntax (e.g. `"exact phrase" -exclude site:arxiv.org after:2024`) to lift actionability.

Fix or remove the broken reference: the body points to `resources/implementation-playbook.md` but no such file (or `references/` directory) exists — either create it under `references/` or drop the line.

Tighten the generic 'Instructions' boilerplate ('Clarify goals, constraints, and required inputs', 'Apply relevant best practices and validate outcomes') into search-specific steps.

DimensionReasoningScore

Conciseness

The body is lean and well-sectioned with no padding about what search engines or libraries are; the only minor trimmable bits are generic boilerplate lines like 'Apply relevant best practices and validate outcomes.'

4 / 5

Actionability

It names concrete techniques ('Use specific phrases in quotes', 'Exclude irrelevant terms with negative keywords', 'allowed_domains for trusted sources', 'Create 3-5 query variations') but stops short of executable, worked examples of query syntax or tool invocations, leaving key details implied.

3 / 5

Workflow Clarity

The 'Approach' section gives a clear 5-step sequence (understand → vary queries → broad-then-refine → verify facts → track contradictions) with verification built into steps 4-5, but lacks an explicit error-recovery feedback loop or checklist for a 5.

4 / 5

Progressive Disclosure

Content is organized into clear sections appropriate for a simple skill; the single external reference ('open resources/implementation-playbook.md') is well-signaled but points to a non-existent file and uses 'resources' rather than the conventional 'references' path, a minor navigation gap rather than a structural failure.

4 / 5

Total

15

/

20

Passed

Description

36%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 is truncated mid-sentence and gives only a vague capability statement with no usage triggers, so it fails to answer when Claude should invoke the skill. It is broadly on-topic but under-specified and not copy-ready.

Suggestions

Complete the sentence and add concrete actions, e.g. 'Synthesizes information from the web using advanced search techniques — query optimization, domain filtering, and cross-source verification.'

Add an explicit trigger clause: 'Use when the user needs web research, fact-checking, source gathering, or trend analysis.'

Include natural synonyms users say ('research this', 'find information online', 'look up') to improve trigger matching.

DimensionReasoningScore

Specificity

Names the domain ('web researcher') but the only action phrasing is the generic 'using advanced search techniques'; no concrete actions like extract, synthesize, or verify are listed, and the sentence is truncated mid-clause ('...and').

2 / 5

Completeness

Provides only a vague 'what' ('expert web researcher using advanced search techniques') and is cut off mid-sentence; there is no 'when'/'Use when...' clause at all, matching the 'vague what and no when' anchor rather than a 3.

2 / 5

Trigger Term Quality

Contains some natural terms ('web researcher', 'search') but misses common variations users actually say like 'research this', 'find information online', or 'look up', and the truncation cuts off any further keywords.

3 / 5

Distinctiveness Conflict Risk

'Web researcher' names a somewhat specific niche but is vague enough to overlap with general research or web-skimming skills, and the truncation leaves no distinctive trigger phrases to separate it.

3 / 5

Total

10

/

20

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
administrakt0r/AI-Agents-Safe-Coding-Skills
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.