daily-brief

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

Quality

56%

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

77%

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

The body is highly actionable and exceptionally well-sequenced with strong validation and loop-engineering discipline. Its weaknesses are verbosity from non-instructional sections and a monolithic structure with no progressive disclosure of the large template and metrics content.

Suggestions

Move the 'Performance Metrics', 'Learning and Adaptation', and 'Philosophy' sections into a separate reference file or remove them, since they add tokens without instructing Claude how to act.

Extract the large daily-brief markdown template into a bundled reference (e.g. references/brief-template.md) and link to it one level deep from SKILL.md.

Tighten the 'Strategic Relevance Analysis' and 'Opportunity and Threat Identification' subsections into a compact checklist to reduce token load.

Dimension	Reasoning	Score
Conciseness	Core sections (Process Flow, Verification Standards, Loop Engineering) are substantive and actionable, but the ~500-line body carries padding — 'Performance Metrics', 'Learning and Adaptation', 'Relevance Algorithm Improvement', and 'Philosophy' describe aspirations and concepts Claude doesn't need, keeping it below the lean anchor 3.	2 / 3
Actionability	It gives concrete commands (`date '+%Y-%m-%d %H:%M'`), specific file paths (`00-inbox/MY-PROFILE.md`, `01-daily/briefs/`), tiered source definitions, explicit dedup rules, and a full copy-paste-ready markdown output template with special-case blocks.	3 / 3
Workflow Clarity	A clear five-step sequence (Gather Context → Research → Generate → Special Cases → Confirm) is paired with a pre-flight check, mandatory verification standards, and a Loop Engineering section spelling out the verifier, layered termination conditions, and no-progress/feedback handling.	3 / 3
Progressive Disclosure	Everything lives in one monolithic file with no bundle files; the ~200-line output template and the metrics/learning sections are inline content that could be split into separate references, and the only external pointer is a cross-skill reference rather than a bundled detail file.	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 a clear domain and one primary action but is missing explicit trigger terms and a 'Use when' clause, which are the main drivers of completeness and trigger quality. It is moderately distinctive yet under-specified for reliable invocation.

Suggestions

Add natural trigger phrases a user would say, e.g. 'Use when the user asks for a daily brief, morning news, or wants to stay updated on their interests.'

Expand to a few concrete actions beyond 'Generate' (e.g. verify sources, deduplicate against prior briefs, produce an actionable brief) to lift specificity.

Include an explicit 'Use when...' clause so both the 'what' and 'when' are answered in the description.

Dimension	Reasoning	Score
Specificity	It names the domain ('news intelligence') and one action ('Generate') with qualifiers ('personalized', 'verified sources', '7-day freshness requirement'), but does not list multiple distinct concrete actions, matching anchor 2 rather than the multi-action anchor 3.	2 / 3
Completeness	It clearly states what the skill does but omits any explicit 'Use when...' trigger clause; per the rubric guideline, a missing when-clause caps completeness at 2.	2 / 3
Trigger Term Quality	No natural user-facing trigger terms appear in the description — phrases like 'daily brief', 'news', or 'morning brief' live only in the body, not the description itself, leaving no keywords a user would naturally say.	1 / 3
Distinctiveness Conflict Risk	The 'news intelligence with verified sources (7-day freshness requirement)' niche is fairly specific, yet without explicit triggers it could still overlap with adjacent research/news skills rather than occupying a clearly distinct niche.	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
Path: .claude/skills/daily-brief/SKILL.md
Commit: dfbf9e9

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.