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

72%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/skills-catalog/catalog/optional/finance/ramp/SKILL.md

Quality

Content

75%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.

A well-structured, security-conscious wrapper skill: concrete allowlisted sources, an executable fetch command, exhaustive approval gates for financial actions, and a clear fail-closed workflow. Its weaknesses are mild — some repetition across the source-model and safety sections, and a few procedures stated as outcomes rather than concrete steps.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence (no explaining what Ramp or curl is), and every section carries policy weight. There is some redundancy — the provenance concern for the playbooks directory is restated across 'Source model' paragraphs, and 'Safety rules' overlaps the approval-gate list — matching 'minor instances of over-explanation that could be trimmed'.	4 / 5
Actionability	Concrete executable guidance: an exact allowlisted URL set, a copy-paste 'curl -L --fail --silent --show-error ...' command, an explicit checklist of gated actions, and a specified approval payload. Minor gaps remain (e.g. 'manually confirm the playbook is marked Official' and 'set the issue to a real waiting path' are stated without a concrete procedure), so it sits just below fully copy-paste ready.	4 / 5
Workflow Clarity	The 'Typical flow' is a clear 6-step sequence with approval-gate checkpoints ('only until an approval-gated action appears', 'stay within the approved amount, scope, and data set', 'If the next Ramp step expands scope, request another approval') and fail-closed stop conditions for destructive financial operations. It falls short of a 5 only because there is no explicit post-action verification or fix-and-retry feedback loop.	4 / 5
Progressive Disclosure	The single file is well organized with clear section headers (Source model, Before fetching, approval gates, Safety rules, Typical flow, Design note), no nested references, and external Ramp content deliberately fetched at runtime rather than vendored. It scores against the 'good structure; most content appropriately placed' anchor rather than 5, since the ~82-line body is above the simple-skill threshold and a couple of sections (gate list vs. safety rules) could be consolidated.	4 / 5
	Total	16 / 20 Passed

Description

70%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 specific, distinctive, third-person description that names concrete gated action domains. Its main weakness is the absence of any 'Use when...' trigger clause, which both caps completeness and slightly limits natural trigger-term coverage.

Suggestions

Append an explicit trigger clause such as 'Use when a company wants an agent to set up or operate Ramp, apply for a Ramp account, issue Ramp Agent Cards, or run Ramp spend/approval workflows from Paperclip.'

Add natural user phrasing/synonyms users would actually say — e.g. 'Ramp CLI', 'virtual cards', 'Ramp reporting', 'reimbursements' — to improve trigger term coverage.

State the when-side conditionally distinct from the what-side so it reads as both capability and trigger guidance, e.g. 'Use when the user mentions Ramp, agent cards, or company spend approvals.'

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions — 'Fetch and follow Ramp's published agent playbooks inside Paperclip' plus 'approval gates for spend, incorporation, cards, account setup' — going beyond naming the domain. Minor gaps in coverage (Ramp CLI usage, reporting, reimbursements) keep it below the comprehensive anchor.	4 / 5
Completeness	The 'what' is clear (fetch and follow Ramp playbooks with mandatory approval gates), but there is no 'Use when...' clause or equivalent explicit trigger guidance. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3 even though the what-side is strong.	3 / 5
Trigger Term Quality	Natural keywords users would say are present: 'Ramp', 'spend', 'incorporation', 'cards', 'account setup', 'financial actions'. A few natural variations users might say are missing ('Ramp CLI', 'virtual cards', 'Ramp reporting', 'reimbursements'), matching the 'good keyword coverage; a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	The description is tightly scoped to 'Ramp' inside 'Paperclip', a clear niche with distinct triggers; it is unlikely to fire for any other finance or document skill. It matches the 'clear niche with distinct triggers; minimal conflict risk' anchor.	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
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: 1c07b59

Reviewed: 1 day 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.