Name: research-finance
Rating: 67.2 (1 reviews)
Author: alirezarezvani

research-finance

Use when managing the money for an internal R&D program or portfolio — building a multi-period program budget with the F&A (indirect) split, tracking burn rate and runway against value-inflection milestones, or routing R&D cost items to a capitalize-vs-expense determination. Every budget output surfaces its assumptions block; capitalize-vs-expense is decision-support only and routes to a named finance owner — it never books an entry or decides accounting treatment. Distinct from finance/financial-analysis (corporate DCF, close, valuation) and research/grants (funding discovery — this manages money already won).

Quality

82%

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

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

Quality

Content

72%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 highly actionable with a well-sequenced workflow and strong guardrails, but it ships without the referenced scripts/references/assets bundle and lacks an explicit validation checkpoint for its batch operations.

Suggestions

Include the referenced bundle (scripts/*.py, references/*.md, assets/rd_program_budget_template.md) so the in-body references resolve to real files; otherwise collapse the file-pointer language into inline guidance.

Add an explicit validate/verify step to the Workflow (e.g. re-run with --output json and confirm assumptions + named-owner fields are present before assembling the review packet) to satisfy the batch-operations feedback-loop expectation.

Move the five-question forcing-question library into a reference file and keep a one-line pointer in SKILL.md to tighten token budget.

Dimension	Reasoning	Score
Conciseness	Dense and mostly assumes Claude's competence — no padding of basic finance concepts — but the five-item forcing-question library and the repeated distinct-from framing (also in the description) could be trimmed or pushed to a reference.	4 / 5
Actionability	Fully executable, copy-paste-ready commands with real flags and profiles (e.g. "program_budget_planner.py --input program.json --profile {pharma-rd\|...} --fa-rate <negotiated rate>"), plus a Quick examples block covering the common cases.	5 / 5
Workflow Clarity	A clear five-step sequenced workflow with concrete commands, but the batch-processing tools (budget planner over line items, capex router over cost items) lack an explicit validate/verify-then-retry checkpoint; validation is only implicit in the Assumptions and Anti-patterns prose, so the batch-operations cap of 3 applies.	3 / 5
Progressive Disclosure	Sections are well organized and references are clearly signaled one level deep (references/*.md canon, scripts table, assets template), but the referenced bundle files do not exist in the staged skill — navigation to the deeper content is broken, so the progressive-disclosure promise is not actually fulfilled.	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.

A high-quality description: concrete capabilities, an explicit Use-when trigger, and clear boundary-setting against sibling skills. Trigger-term coverage is strong but not exhaustive of domain synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "building a multi-period program budget with the F&A (indirect) split", "tracking burn rate and runway against value-inflection milestones", "routing R&D cost items to a capitalize-vs-expense determination" — with comprehensive coverage of the skill's scope.	5 / 5
Completeness	Opens with an explicit "Use when managing the money for an internal R&D program or portfolio" trigger and lists three concrete capabilities, clearly answering both what it does and when to invoke it.	5 / 5
Trigger Term Quality	Strong natural keywords ("program budget", "burn rate", "runway", "capitalize-vs-expense", "F&A") that users would say, with one synonym ("F&A (indirect)"); a few natural variants like "indirect cost rate" / "NICRA" / "R&D spend" are absent and no file extensions apply, so it stops short of fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	Explicitly carves a niche ("manages money already won" for internal R&D) and names what it is NOT — "Distinct from finance/financial-analysis (corporate DCF, close, valuation) and research/grants (funding discovery)" — minimizing wrong-skill triggers.	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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 14 missing	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/research-finance/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.