ramp

Fetch and follow Ramp's published agent playbooks inside Paperclip, with mandatory approval gates for spend, incorporation, cards, account setup, and other financial actions.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable governance skill with clear sequenced workflows and explicit validation/approval checkpoints. Its only weakness is mild verbosity in the provenance rationale and some overlap between the approval-gate and safety sections.

Suggestions

Tighten the playbooks-provenance paragraph and Design note to the essential trust boundary statement, removing restated motivation.

Consolidate overlapping items between 'Mandatory Paperclip approval gates' and 'Safety rules while following Ramp' to reduce redundancy.

Optional: move the gated-action enumeration into a checklist-style reference so the main flow stays scannable.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands and gated-action lists, but the playbooks-provenance paragraph and Design note restate rationale that could be tightened, and the approval-gate and Safety-rules sections overlap somewhat.	2 / 3
Actionability	Provides a concrete curl command, an explicit approval payload field list, enumerated gated actions, and a step-by-step typical flow — fully actionable instruction-level guidance.	3 / 3
Workflow Clarity	Multi-step 'Before fetching' and 'Typical flow' sequences are clearly ordered with approval-gate checkpoints, a 'stop and escalate' feedback loop, and fail-closed handling for risky financial operations.	3 / 3
Progressive Disclosure	A single intentionally non-vendored file with well-organized, clearly headed sections and no external bundle references; for a skill that needs no external references, this meets the well-organized-sections bar.	3 / 3
	Total	11 / 12 Passed

Description

82%

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 specific, distinctive description with strong trigger terms, weakened only by the absence of an explicit 'Use when...' trigger clause. Adding a when-to-use clause would raise completeness.

Suggestions

Append an explicit trigger clause such as 'Use when a company asks an agent to set up or use Ramp, issue agent cards, run spend approvals, or incorporate via Ramp.'

Include a few natural user phrasings (e.g. 'apply to Ramp', 'create a Ramp virtual card') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Fetch and follow Ramp's published agent playbooks' plus 'approval gates for spend, incorporation, cards, account setup, and other financial actions' — matching the multi-action anchor.	3 / 3
Completeness	Answers 'what' clearly but lacks an explicit 'Use when...' clause, so 'when' is only implied; per the guidelines a missing trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Uses natural terms a user or issue would say — 'Ramp', 'spend', 'cards', 'incorporation', 'account setup', 'approvals', 'financial actions' — giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Ramp-specific niche with distinct financial-spend triggers makes it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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: paperclipai/paperclip
Path: packages/skills-catalog/catalog/optional/finance/ramp/SKILL.md
Commit: 14f20be

Reviewed: 4 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.