kb-research

Structured approach to finding and synthesizing information from the user's knowledge base

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./surfsense_backend/app/agents/chat/multi_agent_chat/main_agent/skills/builtin/kb-research/SKILL.md

Quality

Content

86%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 lean, well-structured, and gives concrete tool-driven instructions with a fabrication safeguard and an output checklist. The only meaningful gap is the lack of an explicit validate-and-retry loop and exact search/citation syntax.

Dimension	Reasoning	Score
Conciseness	At ~17 lines with no padding and no explanation of concepts Claude already knows, every line earns its place ('run one targeted KB search', 'Use grep to find supporting passages', 'never fabricate'). This matches anchor 5 ('Lean and efficient; assumes Claude's competence').	5 / 5
Actionability	The guidance names specific tools and concrete actions ('Open the most relevant 2-3 documents fully via read_file', 'Cite every claim with the [n] label'), which is executable for an instruction-only skill. It sits at anchor 4 rather than 5 because exact search/citation syntax is not fully specified.	4 / 5
Workflow Clarity	A clear 4-step numbered sequence pairs with a fabrication guard ('Not found in your knowledge base' callout) and a 'What good output looks like' checklist. This matches anchor 4 ('Clear sequence with most checkpoints present; minor validation gaps') and falls short of anchor 5's explicit validate-fix-retry feedback loop.	4 / 5
Progressive Disclosure	The skill is under 50 lines, needs no external references (none of references/scripts/assets exist), and is organized into three clearly labeled sections. Per the simple-skkill exception, this matches anchor 5 ('well-organized sections' with no need for external files).	5 / 5
	Total	18 / 20 Passed

Description

53%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 concise and third-person but stops at naming a domain plus two generic actions, with no explicit trigger guidance. Adding a 'Use when...' clause and concrete natural-language triggers would lift completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to find, look up, or research something inside their knowledge base, or to synthesize across their notes and documents.'

Replace the generic verbs with concrete capabilities, e.g. 'find, summarize, and cross-reference information across the user's knowledge base'.

Add natural trigger phrases a user would actually say ('find', 'look up', 'research', 'my notes', 'what we discussed') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('information from the user's knowledge base') and two actions ('finding and synthesizing'), but the actions are generic verbs rather than concrete capabilities. It matches anchor 3 ('Names domain and 1-2 concrete actions, but not comprehensive') and falls short of anchor 4's 'several specific actions'.	3 / 5
Completeness	It states a clear 'what' ('finding and synthesizing information from the user's knowledge base') but provides no 'when' / 'Use when...' trigger clause, which the guidelines cap at 3. It does not reach anchor 4, which requires an explicit (even if imperfect) 'when'.	3 / 5
Trigger Term Quality	The only natural keyword present is 'knowledge base'; the user-facing trigger phrases ('find/look up/research', 'my notes') appear only in the body, not the description. This matches anchor 3 ('Some relevant keywords but missing common variations or synonyms') and is below anchor 4's broader coverage.	3 / 5
Distinctiveness Conflict Risk	Scoping to 'the user's knowledge base' carves out a distinct niche with minimal conflict risk versus general web or file search. It sits at anchor 4 ('Mostly distinct; minor overlap risk') rather than 3, because the KB framing is genuinely specific, but lacks the fully concrete triggers of anchor 5.	4 / 5
	Total	13 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: MODSetter/SurfSense
Path: surfsense_backend/app/agents/chat/multi_agent_chat/main_agent/skills/builtin/kb-research/SKILL.md
Commit: d96e29d

Reviewed: 8 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.