daily-brief

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

Quality

63%

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 ./.claude/skills/daily-brief/SKILL.md

Quality

Content

73%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 a strong, highly actionable workflow with excellent validation and feedback-loop engineering, scoring top marks on workflow clarity. Its main weakness is conciseness: several aspirational sections and a very large inline template add tokens that could be offloaded to reference files.

Suggestions

Remove or sharply compress the Performance Metrics, Learning and Adaptation, and Philosophy sections; they describe aspirations Claude already understands rather than executable instructions.

Move the full daily-brief output template into a references/ file (e.g., templates/daily-brief.md) and keep only the frontmatter schema and one short example inline in SKILL.md.

Trim the duplicate verification language between the 'Verification Standards' and 'Loop Engineering' sections into a single consolidated verifier spec to reduce token cost.

Dimension	Reasoning	Score
Conciseness	The core process, dedup, verifier, and loop-engineering sections are dense and useful, but the Performance Metrics, Learning and Adaptation, and Philosophy sections are conceptual padding and the ~150-line output template is fully inlined, so it is mostly efficient with unnecessary explanation that could be trimmed.	3 / 5
Actionability	Provides concrete file paths, the literal `date` command, exact frontmatter fields, source tiers, dedup rules, and copy-paste-ready output and special-case blocks, with only minor gaps in the literal execution of search/verification steps.	4 / 5
Workflow Clarity	A clearly sequenced Pre-Flight through Confirm-Completion flow with an explicit per-candidate verifier, dedup and freshness validation, plus a Loop Engineering section detailing feedback loops and layered termination conditions, matches the anchor for explicit validation steps and error-recovery loops.	5 / 5
Progressive Disclosure	Well-sectioned with clear headers and a clearly signaled one-level external reference (loop-engineering SKILL.md); the main organization gap is the large inline output template and meta sections that could live in reference files, fitting the 'good structure, minor gaps' anchor.	4 / 5
	Total	16 / 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 clear about what the skill produces and is reasonably distinct, but it omits any 'when to use' trigger guidance and underuses the natural trigger phrases ('daily brief', 'morning brief') that the body relies on. It sits at the midpoint across most dimensions.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases such as 'daily brief', 'morning brief', 'what's happening', or 'news briefing' to satisfy the 'when' half of completeness.

Swap jargon like 'news intelligence' for natural user wording and list 2-3 more concrete actions (e.g., 'curate', 'verify', 'deduplicate against past briefs') to lift specificity.

Include synonyms or file/path cues (e.g., 'daily news briefing') to broaden trigger-term coverage and further reduce conflict with general research skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('personalized news intelligence') plus two concrete features ('verified sources', '7-day freshness requirement'), but only one action verb ('Generate') and no comprehensive action list, matching the anchor that names the domain with 1-2 concrete actions.	3 / 5
Completeness	Clearly states what the skill does but provides no 'Use when...' clause or equivalent trigger guidance, so per the rubric's completeness cap a missing explicit 'when' caps the score at 3.	3 / 5
Trigger Term Quality	Contains the natural term 'news' but omits the common trigger phrases the body itself lists ('daily brief', 'morning brief', 'what's happening') and leans on jargon ('news intelligence'), fitting the anchor with some relevant keywords but missing common variations.	3 / 5
Distinctiveness Conflict Risk	'Personalized news intelligence with verified sources' carves a fairly distinct niche with only minor overlap risk against generic web-search or research skills, matching the 'mostly distinct' anchor rather than the more generic level 3.	4 / 5
	Total	13 / 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
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
Path: .claude/skills/daily-brief/SKILL.md
Commit: cb4644d

Reviewed: 2 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.