initiating-coverage

Create institutional-quality equity research initiation reports through a 5-task workflow. Tasks must be executed individually with verified prerequisites - (1) company research, (2) financial modeling, (3) valuation analysis, (4) chart generation, (5) final report assembly. Each task produces specific deliverables (markdown docs, Excel models, charts, or DOCX reports). Tasks 3-5 have dependencies on earlier tasks.

Quality

68%

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 ./plugins/vertical-plugins/equity-research/skills/initiating-coverage/SKILL.md

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 skill is well-structured with excellent workflow clarity and progressive disclosure, and it gives concrete actionable deliverables per task. Its main weakness is conciseness: the same single-task and no-shortcuts directives are repeated many times, inflating the body without adding guidance.

Suggestions

Consolidate the repeated 'one task at a time / no shortcuts / deliver only X' messaging into a single authoritative section and reference it once from each task instead of restating it verbatim.

Trim redundant blocks such as the near-duplicate Success Criteria and Important Notes sections that restate earlier rules, and reduce emoji-heavy checklists where prose would be more token-efficient.

Move the per-task deliverable and shortcut-warning detail that is already implied by the reference files into those references, keeping SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: the 'one task at a time / no shortcuts / deliver only X' messaging is restated near-verbatim across the CRITICAL section, How to Use, every Task section, the Input Verification Protocol, and Success Criteria, and emoji-heavy checklists add padding without new information.	2 / 5
Actionability	Guidance is concrete and specific — exact file names, the 6 model tabs, 40-50 line items, 25-35 charts, mandatory chart IDs, and prerequisite checklists — giving mostly executable direction with only minor reliance on reference files for full detail.	4 / 5
Workflow Clarity	A clear sequence is given with explicit validation checkpoints at every task boundary and feedback loops ('verification fails → stop → complete the prerequisite task → return'), including checklists for the complex multi-task process.	5 / 5
Progressive Disclosure	The body is a clear overview with well-signaled one-level-deep references (references/taskN-*.md, references/valuation-methodologies.md, assets/report-template.md, assets/quality-checklist.md), all of which exist as real files, plus an explicit instruction to load only the relevant reference file per task.	5 / 5
	Total	16 / 20 Passed

Description

67%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 and distinctive about a well-defined equity-research workflow, but it omits any explicit 'Use when' trigger guidance, leaving Claude without a clear invocation signal. Adding a natural-language trigger clause would lift the completeness and trigger-term dimensions.

Suggestions

Append an explicit 'Use when...' clause naming natural trigger phrases users would say (e.g. 'Use when creating an equity research initiation report, initiating coverage on a company, or producing sell-side research deliverables').

Add common synonyms and file extensions to the trigger terms (e.g. 'initiation report', 'coverage report', '.xlsx', '.docx') so the description matches how users actually phrase the request.

Switch any implied second-person intent to third-person voice to keep the description consistent with skill-description conventions.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions and deliverables ('markdown docs, Excel models, charts, or DOCX reports') and enumerates all five tasks ('company research, financial modeling, valuation analysis, chart generation, final report assembly'), giving comprehensive coverage of capabilities.	5 / 5
Completeness	It clearly answers 'what' the skill does but provides no explicit 'Use when...' or trigger guidance for when Claude should invoke it; per the rubric, a missing 'when' clause caps completeness at 3.	3 / 5
Trigger Term Quality	It contains some relevant keywords ('equity research initiation reports', 'financial modeling', 'valuation') but omits natural variations a user would say such as 'initiation report', 'coverage', 'sell-side report', or file extensions, so common synonyms are missing.	3 / 5
Distinctiveness Conflict Risk	The narrow niche of 'institutional-quality equity research initiation reports' with a named 5-task workflow is clearly distinct from other skills and unlikely to trigger for the wrong skill.	5 / 5
	Total	16 / 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
skill_md_line_count	SKILL.md is long (784 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: anthropics/financial-services
Path: plugins/vertical-plugins/equity-research/skills/initiating-coverage/SKILL.md
Commit: 3865222

Reviewed: 9 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.