customer-research

Multi-source research on a customer question or topic with source attribution. Use when a customer asks something you need to look up, investigating whether a bug has been reported before, checking what was previously told to a specific account, or gathering background before drafting a response.

Quality

79%

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 ./customer-support/skills/customer-research/SKILL.md

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 content provides a clear, actionable, well-sequenced research workflow with concrete prompts and decision trees. Its main weakness is conciseness — overlapping templates and restated concepts inflate the token budget without adding proportional value.

Suggestions

Consolidate the research-brief template (section 3) and the knowledge-base documentation template (Research Documentation section) into a single shared structure to remove duplication.

Trim the "Confidence Levels" section, which restates what High/Medium/Low confidence means with example quotes that Claude can already infer from the confidence-by-tier table.

Move the source-tier reference table and the two inline templates into a referenced file (e.g. references/research-templates.md) and keep SKILL.md as a lean overview with one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but includes duplicative material — the research-brief template and the knowledge-base documentation template overlap, and sections like "Confidence Levels" and "Knowledge Capture" restate concepts Claude already knows at length.	3 / 5
Actionability	Guidance is concrete and instruction-ready with copy-paste prompts (e.g., "I couldn't find this in connected sources..."), a named escalation path, and a structured output template; minor gaps exist since tool invocations are necessarily dynamic.	4 / 5
Workflow Clarity	A clear six-step sequence (Parse → Search → Synthesize → Handle insufficient → Customer-facing → Knowledge capture) with checkpoints for contradictions, confidence assignment, and an escalate-vs-answer decision tree; a few validation checkpoints are implicit.	4 / 5
Progressive Disclosure	The single SKILL.md is well-organized with clear headers, but two full inline templates and the source-tier tables are bulk content that could be split into referenced files; no bundle files are provided or signaled.	4 / 5
	Total	15 / 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 conveys both what the skill does and when to invoke it, with concrete natural-language trigger phrases and a well-scoped niche. It is strong overall, with only minor room to add more keyword synonyms and a fuller enumeration of concrete actions.

Dimension	Reasoning	Score
Specificity	"Multi-source research on a customer question or topic with source attribution" names the domain plus several concrete trigger scenarios; minor gaps versus the comprehensive multi-action enumeration at anchor 5.	4 / 5
Completeness	It explicitly states the "what" (multi-source research with attribution) and a concrete "Use when..." clause with multiple trigger phrases, matching the anchor that requires both with concrete triggers.	5 / 5
Trigger Term Quality	Phrases like "a customer asks something you need to look up", "investigating whether a bug has been reported before", and "gathering background before drafting a response" give good natural-term coverage with synonyms, though a few common variations are absent.	4 / 5
Distinctiveness Conflict Risk	Customer-research triggers (bug reported before, account history, drafting responses) form a fairly distinct niche with only minor overlap risk against general web-search skills.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: anthropics/knowledge-work-plugins
Path: customer-support/skills/customer-research/SKILL.md
Commit: 8444efc

Reviewed: 6 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.