CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

search-strategy

Query decomposition and multi-source search orchestration. Breaks natural language questions into targeted searches per source, translates queries into source-specific syntax, ranks results by relevance, and handles ambiguity and fallback strategies.

Quality

77%

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 ./enterprise-search/skills/search-strategy/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

A strong, highly actionable instruction skill: concrete per-source query syntax, explicit filter mappings, and defined ranking weights make the guidance immediately executable. The workflow is clearly sequenced with good fallback coverage; the only gaps are minor verbosity and the absence of explicit validation checkpoints before synthesis.

DimensionReasoningScore

Conciseness

Mostly lean: concrete syntax examples, filter-mapping tables, and weight tables with no re-explanation of concepts Claude already knows. Minor trims possible — the ASCII pipeline diagram, the 'The core intelligence behind enterprise search' opener, and query broadening shown as both an example block and an ordered list — so it fits the 'efficient; minor instances that could be trimmed' anchor rather than the every-token-earns-its-place anchor.

4 / 5

Actionability

Gives copy-paste-ready query syntax per source ('aurora in:#engineering after:2025-01-15', 'is:thread', 'has:file'), explicit filter-mapping tables (from:sarah → assignee_any), and numeric ranking weights per query type. These are concrete, directly executable instructions covering the common cases, matching the fully-executable anchor.

5 / 5

Workflow Clarity

Clear multi-step sequence (identify query type → extract components → generate sub-queries → parallel execution → merge/rank/dedupe) with fallback and ambiguity handling as recovery paths. It stops short of explicit validation checkpoints (e.g., verifying results answer the query before synthesizing), fitting the 'most checkpoints present; minor validation gaps' anchor rather than the explicit-validation anchor.

4 / 5

Progressive Disclosure

No bundle files exist, so all content is in one well-sectioned SKILL.md with a clearly signaled external reference to CONNECTORS.md. The per-source syntax sections and ranking weight tables are arguably reference material that could live in separate files, which keeps it below the clear-overview-with-split-references anchor, but the single-level structure and clear headers place it above the could-be-better-organized anchor.

4 / 5

Total

17

/

20

Passed

Description

63%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 does the 'what' very well — specific, third-person, comprehensive concrete actions covering the full decomposition-to-fallback pipeline — but it entirely omits the 'when', and its trigger vocabulary skews technical rather than toward phrases users would naturally say. Distinctiveness is decent thanks to the multi-source orchestration framing.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when a question requires searching across multiple connected sources (chat, wiki, email, project tracker) rather than a single tool' — this lifts completeness from 3 to 5.

Replace jargon-heavy triggers with natural user phrasings and synonyms: 'find', 'look up', 'search everywhere / across all our tools', 'enterprise search', alongside the current technical terms.

Name the concrete sources (chat, wiki, email, project tracker, file storage) to sharpen distinctiveness from generic single-source search skills and give users recognizable trigger words.

DimensionReasoningScore

Specificity

Four concrete third-person actions cover the pipeline comprehensively: 'breaks natural language questions into targeted searches per source', 'translates queries into source-specific syntax', 'ranks results by relevance', 'handles ambiguity and fallback strategies'. This matches the comprehensive-coverage anchor; the 4 anchor would require noticeable coverage gaps, which are absent.

5 / 5

Completeness

The 'what' is clearly and concretely stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance; per judging guidelines this caps completeness at 3. It is above the 2 anchor because the 'what' is specific and multi-action, not vague.

3 / 5

Trigger Term Quality

Relevant keywords exist ('search', 'queries', 'questions', 'rank results') but the phrasing is technical ('query decomposition', 'multi-source search orchestration') and misses natural user terms like 'find', 'look up', 'enterprise search', or concrete source names (chat, wiki, Drive). This matches the 'some relevant keywords but missing common variations or synonyms' anchor rather than good-coverage.

3 / 5

Distinctiveness Conflict Risk

'Multi-source search orchestration' and 'source-specific syntax' carve a fairly distinct niche with only minor overlap risk against generic single-source search skills. It falls short of the 5 anchor because no distinct trigger phrases are named and 'search' alone is broad enough to collide with related skills.

4 / 5

Total

15

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

anthropics/knowledge-work-plugins

Path

enterprise-search/skills/search-strategy/SKILL.md

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.