consulting-analysis

Use this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis, industry research, competitive intelligence, investment due diligence, or any consulting-grade analytical report. This skill operates in two phases — (1) generating a structured analysis framework with chapter skeleton, data query requirements, and analysis logic, and (2) after data collection by other skills, producing the final consulting-grade report with structured narratives, embedded charts, and strategic insights.

Quality

86%

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

Quality

Content

77%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 skill body is highly actionable and exceptionally well-sequenced with validation and feedback loops, making it strong on actionability and workflow clarity. It is held back by verbosity (duplicated checklists and well-known framework definitions) and by being a large monolithic file with no progressive disclosure into reference bundles.

Suggestions

Move the framework-definition catalog (SWOT/PESTEL/Porter/BCG/etc. tables) into a references/frameworks.md file and reference it from SKILL.md, since these are concepts Claude already knows and inflate the body.

Remove the duplicate Phase 1 Quality Checklist (lines ~290 and ~580) — keep a single canonical checklist to cut redundancy.

Extract the complete worked example (Phase 1 + Phase 2 Gen-Z skincare walkthrough) into a references/examples.md file, leaving only a brief pointer in the main body.

Dimension	Reasoning	Score
Conciseness	The core workflow is efficient, but several padded sections remain — the framework-definition tables (SWOT, PESTEL, Porter's, BCG Matrix, etc.) re-explain concepts Claude already knows, and the Phase 1 quality checklist is duplicated near lines 290 and 580 — fitting the 'mostly efficient but includes some unnecessary explanation' 3 anchor rather than the noticeably-verbose 2.	3 / 5
Actionability	It provides fully executable, copy-paste-ready templates — concrete output-format markdown blocks, data-requirement table schemas, a chart-generation workflow with explicit file-path conventions ('charts/chapter_{N}_{chart_index}.png'), and a worked Gen-Z skincare example — matching the 'fully executable; covers common cases' 5 anchor.	5 / 5
Workflow Clarity	Both phases are clearly sequenced (Step 1.1–1.6, Step 2.1–2.5) with explicit validation checkpoints (input validation in 2.1, chart validation in 2.3, structure self-check in 2.5) and feedback loops ('If any chart generation fails... fall back to comparison tables'; flag missing P0 data), matching the 5 anchor's explicit validation and error-recovery loops.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and the body is a single ~620-line monolith with inlined reference-style content (the framework catalog and full worked example) that could live in separate files; internal headers give it structure, but the absence of any signaled external references fits the 'some structure, content that could be separate is inline' 3 anchor better than the well-split 4 anchor.	3 / 5
	Total	16 / 20 Passed

Description

96%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 strong: it concisely states concrete two-phase capabilities, packs in natural domain trigger terms, and explicitly covers both what the skill does and when to use it. The only soft spot is slight overlap risk with generic research/writing skills.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions across both phases — 'generating a structured analysis framework with chapter skeleton, data query requirements, and analysis logic' and 'producing the final consulting-grade report with structured narratives, embedded charts, and strategic insights' — giving comprehensive coverage rather than the minor gaps of a 4.	5 / 5
Completeness	It explicitly answers both 'what' (two-phase framework + final report generation) and 'when' ('Use this skill when the user requests to generate, create, or write professional research reports...'), matching the concrete-trigger-phrases anchor at 5.	5 / 5
Trigger Term Quality	It enumerates natural user phrasings across many domains ('research reports', 'market analysis', 'consumer insights', 'brand analysis', 'financial analysis', 'industry research', 'competitive intelligence', 'investment due diligence'), matching the comprehensive-synonym coverage of the 5 anchor rather than the few-missing-terms 4 anchor.	5 / 5
Distinctiveness Conflict Risk	The consulting-grade, two-phase framing carves a clear niche with distinct triggers, but the broad 'research reports' phrasing leaves minor overlap risk with general research/writing skills, fitting the 'mostly distinct; minor overlap' 4 anchor better than the minimal-conflict 5 anchor.	4 / 5
	Total	19 / 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 (632 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 5 missing	Warning

	Total	14 / 16 Passed

Repository: bytedance/deer-flow
Path: skills/public/consulting-analysis/SKILL.md
Commit: 2a261d2

Reviewed: about 17 hours 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.