CtrlK
BlogDocsLog inGet started
Tessl Logo

report-writing

How to scope, draft, and revise a Markdown report artifact via generate_report

61

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

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/report-writing/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise, highly actionable with concrete tool parameters, and presents a clearly sequenced decision flow with explicit guardrails and an error-handling hook. As a short, well-organized single-purpose skill it needs no external bundle files and uses progressive disclosure appropriately.

DimensionReasoningScore

Conciseness

The body is lean with no filler explaining what reports are or basic concepts; every line is actionable guidance (enum values, default settings, parameter names), matching the score-3 anchor of a tight, competence-assuming skill.

3 / 3

Actionability

Guidance gives exact, copy-pasteable tool inputs (`source_strategy` values, `report_style="detailed"`, `parent_report_id`, `user_instructions`) with example change-list phrases; for an instruction-only skill this meets the score-3 actionable bar.

3 / 3

Workflow Clarity

A clearly numbered decision flow is paired with explicit guardrail checkpoints (step 4 "Never paste the report back", and the KB-no-results hook to surface gaps rather than fabricate), matching the score-3 anchor of a clear sequence with validation/feedback steps.

3 / 3

Progressive Disclosure

The skill is under 50 lines with no external references needed and is organized into well-labeled sections (When to use, Decision flow, Hooks), satisfying the rubric's allowance for simple skills to score 3 on well-organized structure alone.

3 / 3

Total

12

/

12

Passed

Description

45%

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 states concrete actions and a tool-specific niche but omits any user-facing trigger guidance, which caps completeness and leaves trigger-term quality weak. Adding a "Use when the user asks to write/draft/expand a report..." clause would lift the two weakest dimensions.

Suggestions

Add an explicit "Use when..." trigger clause with natural user phrasings such as "write a report", "draft a memo", "produce a brief", or "expand the previous report".

Include common trigger-term variations directly in the description (e.g. report, memo, brief, deliverable) so the description matches what users actually say, not just the tool name.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions ("scope, draft, and revise") tied to a named artifact and tool ("Markdown report artifact via generate_report"), matching the score-3 anchor for listing several specific actions rather than only naming a domain.

3 / 3

Completeness

It clearly answers what (scope/draft/revise a report via generate_report) but provides no "Use when..." trigger in the description; per the rubric guideline, a missing explicit trigger clause caps completeness at 2.

2 / 3

Trigger Term Quality

The description contains only the technical tool name `generate_report` and "Markdown report artifact" with no natural phrasings a user would say (e.g. "write a report", "draft a memo"), fitting the score-1 anchor of jargon/no natural keywords.

1 / 3

Distinctiveness Conflict Risk

Tying the skill to a specific tool (`generate_report`) gives it a niche, but "report writing" is broad and the description lacks distinct trigger phrases, so it could overlap with general document skills as in the score-2 anchor.

2 / 3

Total

8

/

12

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
MODSetter/SurfSense
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.