daily-brief

Generate personalized news intelligence with verified sources (7-day freshness requirement)

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

The content is highly actionable with a clear, well-validated workflow, but it is verbose and monolithic, repeating the verification-first message across several sections. Trimming redundant sections and extracting the large template into a reference file would improve token efficiency and structure.

Suggestions

Cut or condense the "Performance Metrics", "Learning and Adaptation", and "Philosophy" sections, which re-state the verification-first approach already covered in the Process Flow and Loop Engineering sections.

Extract the full brief template into a separate reference file (e.g., references/brief-template.md) and reference it one level deep, leaving only the key frontmatter fields inline.

Consolidate the repeated 7-day freshness statements into a single authoritative statement to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable but is padded with redundant restatements of the verification-first philosophy ("Performance Metrics", "Learning and Adaptation", "Philosophy") and repeats the 7-day freshness rule many times, fitting the level-2 anchor of efficient-with-some-unnecessary content.	2 / 3
Actionability	It gives concrete file paths, an exact command (`date '+%Y-%m-%d %H:%M'`), a full copy-paste-ready brief template with frontmatter, and explicit source-tier/dedup rules, matching the level-3 anchor of fully executable, specific guidance.	3 / 3
Workflow Clarity	The five-step process is clearly sequenced with explicit verification checkpoints, a defined verify-retry loop, layered termination conditions, and a "discard, not soften" feedback rule, matching the level-3 anchor.	3 / 3
Progressive Disclosure	No bundle files are provided and the skill is a single monolithic document; the large inline brief template and several conceptual sections could be split into references, fitting the level-2 anchor of content that should be separate being inline.	2 / 3
	Total	10 / 12 Passed

Description

35%

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 conveys the skill's purpose and niche reasonably well but is missing natural trigger terms and an explicit use-when clause, which limit completeness and trigger quality. Adding a "Use when..." phrase with everyday user keywords would substantially improve it.

Suggestions

Add an explicit trigger clause such as "Use when the user wants a daily news brief, asks what's happening, or wants to stay updated on their interests."

Replace jargon ("personalized news intelligence") with concrete natural-language terms users would say, e.g., "daily brief", "news roundup", "morning brief".

List a couple of concrete actions (curate, verify, deduplicate) to raise specificity beyond a single generic verb.

Dimension	Reasoning	Score
Specificity	"Generate personalized news intelligence with verified sources" names the news domain and a generation action plus verification, but does not enumerate multiple concrete distinct actions, matching the level-2 anchor.	2 / 3
Completeness	It states what the skill does (generate news intelligence) but omits any explicit "Use when..." trigger clause, so per the guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	The description contains no natural user phrases like "daily brief", "news", or "what's happening"; the body lists these triggers but the description itself uses only jargon ("personalized news intelligence"), matching the level-1 anchor.	1 / 3
Distinctiveness Conflict Risk	"News intelligence" carves out a recognizable niche but lacks distinguishing triggers and could overlap with general news/search skills, matching the level-2 anchor.	2 / 3
	Total	7 / 12 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
skill_md_line_count	SKILL.md is long (506 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: huytieu/COG-second-brain
Commit: 5e9851c

Reviewed: 14 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.