comprehensive-analysis

Deep-dive 7-day analysis across all data sources for weekly reviews, board prep, and strategic planning

Quality

66%

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 ./.claude/skills/comprehensive-analysis/SKILL.md

Quality

Content

63%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.

This is a richly detailed orchestration skill with concrete, executable agent prompts and a clear phased workflow. Its main weaknesses are repetitive boilerplate across agent prompts and broken/unsatisfied references to an external daily-brief.md that is not bundled.

Suggestions

Extract the five large agent prompt blocks into separate reference files (e.g. references/github-deep-analyst.md) and link to them, reducing SKILL.md to an overview and fixing the monolithic structure.

Either bundle daily-brief.md or inline the '23 cross-reference patterns' and Phase 3.7/Phase 4 patterns instead of referencing a missing file.

Add an explicit validation checkpoint between Phase 1 and Phase 2 (e.g. verify each agent returned structured data within token budget before synthesis) to satisfy the batch-operation feedback-loop bar.

Dimension	Reasoning	Score
Conciseness	The body is mostly concrete commands and analysis checklists, but each of the five agent prompts restates boilerplate ('Analysis period', 'Return structured data AND insights') and the Voice & Tone section adds tone fluff ('celebrate!', 'teammate energy') that could be trimmed.	3 / 5
Actionability	Highly actionable with real `gh` commands, HogQL queries, named MCP tools, and glob patterns, but [CUSTOMIZE] placeholders and repeated 'same pattern as daily brief' references to a non-bundled file leave minor gaps.	4 / 5
Workflow Clarity	Three clearly sequenced phases with parallel agent launch, plus fallback behavior and a context-overflow feedback loop; validation is present but light, so it stops short of the explicit validate-fix-retry checklist at the top band.	4 / 5
Progressive Disclosure	Headers organize the ~345-line body, but all content is inlined in SKILL.md with no bundle files, and repeated references to 'daily-brief.md' point to a file that is not part of the bundle.	3 / 5
	Total	14 / 20 Passed

Description

70%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 a solid single-sentence statement that covers what the skill does and when to use it, with natural trigger terms. It is held back from the top band by generic action wording ('analysis') and the absence of an explicit 'Use when' clause.

Suggestions

Replace the generic verb 'analysis' with the concrete outputs the skill produces (e.g. 'generates executive, team, and product reports synthesizing GitHub, Linear, Slack, and PostHog data').

Add an explicit trigger clause such as 'Use when the user asks for a weekly review, board prep, or comprehensive 7-day analysis.'

Mention the sibling daily-brief distinction inline (e.g. 'for 7+ day windows; use /daily-brief for daily intel') to further reduce overlap risk.

Dimension	Reasoning	Score
Specificity	Names the domain ('Deep-dive 7-day analysis across all data sources') and several use contexts, but the only concrete action stated is generic 'analysis' rather than multiple specific actions the skill performs.	3 / 5
Completeness	Answers both what ('Deep-dive 7-day analysis across all data sources') and when ('for weekly reviews, board prep, and strategic planning'), but lacks an explicit 'Use when...' phrasing that would make the trigger guidance fully concrete.	4 / 5
Trigger Term Quality	Includes natural phrases a user would say — 'weekly reviews', 'board prep', 'strategic planning', 'deep dive' — giving good keyword coverage, though a few common synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	The 7-day window and 'deep-dive' framing carve a clear niche distinct from a daily brief, with only minor overlap risk against closely related intelligence skills.	4 / 5
	Total	15 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: huytieu/COG-second-brain
Path: .claude/skills/comprehensive-analysis/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.