Name: dossier
Rating: 66.4 (1 reviews)
Author: alirezarezvani

dossier

Decision-grade entity research skill — produces a hypothesis-tested dossier on a specific company, person, nonprofit, or government org, not a generic profile. Forcing intake makes the user state their hypothesis upfront (what they already believe and want to verify or disprove) so the dossier tests it rather than confirms it. Output is an editable Word document (.docx) with verdict on the hypothesis, identity facts, 12-month activity timeline, network and reputation signals, red flags, conversation hooks tied to specific findings, and source-provenance audit log. Uses WebSearch + WebFetch + free APIs (SEC EDGAR, GitHub, ProPublica) as workhorses; optional BYOK MCPs enhance coverage. Use when the user asks for background research, diligence, or meeting prep on a specific entity (e.g., 'prep me for a meeting with [person/company]', 'due diligence on [company]'). Honors sensitivity exclusions for journalism + personal-vetting contexts.

Quality

81%

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

The canonical home for this skill is dossier in alirezarezvani/claude-skills

Quality

Content

70%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 well-sequenced, actionable, validated workflow with strong checklists and error recovery. Its main weaknesses are some repeated/over-explained prose and referenced bundle files that are absent, which undermines progressive disclosure.

Suggestions

Add the missing bundle files referenced in the body (references/hypothesis_testing_discipline.md, references/subject_type_source_matrix.md, references/conversation_hook_quality.md, and the three scripts/*.py files) so the signaled one-level-deep navigation actually resolves.

De-duplicate the 'skip it and it becomes a Wikipedia summary' framing — state the non-generic-anchor point once in the opening and once at Q4 rather than three times.

Trim the per-question 'Why I'm asking' rationales and incidental asides (e.g., 'There are 47 John Smiths') to tighten token efficiency without losing the forcing-function mechanics.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete phases and tables, but repeats the 'skip it and it becomes a Wikipedia summary' non-generic-anchor message three times and includes 'Why I'm asking' rationales plus asides like 'There are 47 John Smiths' that could be trimmed.	3 / 5
Actionability	Provides verbatim intake questions, per-type source matrices, the >=30% disconfirming rule, an executable docx hyperlink code snippet, and a concrete validation command, with only minor gaps in the script-invocation specifics.	4 / 5
Workflow Clarity	Ten numbered phases are clearly sequenced with dependency-annotated intake (Q1->Q2->Q3->Q4/Q5->Q6), a stop condition, an error-handling table with recovery feedback loops, an anti-patterns checklist, and an explicit Phase 10 validation step (zip integrity + section presence).	5 / 5
Progressive Disclosure	The body is well-structured and signals one-level-deep references (hypothesis_testing_discipline.md, subject_type_source_matrix.md, conversation_hook_quality.md, plus three scripts), but the referenced references/ and scripts/ bundle files do not actually exist, breaking the navigation the disclosure pattern relies on.	3 / 5
	Total	15 / 20 Passed

Description

92%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 specific, complete, and distinctive, clearly stating both what the skill produces and when to invoke it with concrete trigger examples. The only minor gap is trigger-term synonym coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete outputs — 'verdict on the hypothesis, identity facts, 12-month activity timeline, network and reputation signals, red flags, conversation hooks tied to specific findings, and source-provenance audit log' plus 'editable Word document (.docx)' — giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (hypothesis-tested dossier with named components) and 'when' ('Use when the user asks for background research, diligence, or meeting prep on a specific entity (e.g., ...)') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrasings users would say — 'background research, diligence, or meeting prep', 'prep me for a meeting with [person/company]', 'due diligence on [company]' — but omits common synonyms like 'background check', 'company research', or 'profile'.	4 / 5
Distinctiveness Conflict Risk	'Decision-grade entity research with hypothesis-testing' on specific entity types is a clear niche with distinct triggers and minimal overlap risk with other skills.	5 / 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
relative_links	Relative link issues: 6 missing	Warning
referenced_paths_exist	Referenced path issues: 16 missing	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/dossier/SKILL.md
Commit: 19392f7

Reviewed: ~2 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.