affinda-automation

Automate Affinda tasks via Rube MCP (Composio). Always search tools first for current schemas.

4.52x

Quality

54%

Does it follow best practices?

Impact

77%

4.52x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./composio-skills/affinda-automation/SKILL.md

Quality

Content

67%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-structured, actionable guide with clear sequencing and validation checkpoints. Its main weakness is redundancy between the Tool Discovery/Step 1 and Prerequisites/Setup sections, which could be consolidated for better token efficiency.

Suggestions

Merge the standalone "Tool Discovery" section into "Step 1: Discover Available Tools" to remove the duplicated RUBE_SEARCH_TOOLS example.

Consolidate "Prerequisites" and "Setup" so the connection/search requirements appear once rather than twice.

Add an explicit error-recovery loop after execution (e.g., on schema or auth failure, re-run RUBE_SEARCH_TOOLS and retry) to push workflow clarity toward anchor 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the "Tool Discovery" section duplicates "Step 1: Discover Available Tools" and "Prerequisites" overlaps "Setup", creating noticeable content that could be tightened, fitting anchor 3 rather than the leaner anchor 4.	3 / 5
Actionability	Concrete RUBE call templates with real parameters (queries, session, tool_slug/arguments) give mostly executable guidance; the placeholders ("TOOL_SLUG_FROM_SEARCH", "your_session_id") are justified by the explicit "never hardcode slugs" design, leaving only minor gaps consistent with anchor 4.	4 / 5
Workflow Clarity	A clear three-step sequence (discover, check connection, execute) with explicit validation (confirm ACTIVE before executing) and a Known Pitfalls checklist is present; feedback loops for error recovery are light but batch-operation validation exists, so it fits anchor 4 rather than the explicit-loop anchor 5.	4 / 5
Progressive Disclosure	Content is well-organized into labeled sections, self-contained with no nested references (no bundle files exist), and the only external pointer is a single toolkit-docs URL; minor organization gaps from the duplicated discovery/setup sections keep it at anchor 4 rather than 5.	4 / 5
	Total	15 / 20 Passed

Description

41%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 correctly identifies a distinct niche but is too generic in its stated actions and omits any explicit usage trigger. Adding concrete Affinda capabilities and a "Use when..." clause would substantially improve it.

Suggestions

Replace the generic "Automate Affinda tasks" with 2-3 concrete capabilities Affinda provides (e.g., parse invoices/receipts, extract resume data, classify documents) to raise specificity.

Add an explicit trigger clause such as "Use when the user wants to automate Affinda document parsing or process Affinda extractions via Composio."

Include natural synonyms users might say (e.g., "invoice parsing", "resume extraction", "document AI") alongside the Affinda brand to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Affinda tasks via Rube MCP (Composio)") but the only action stated is generic ("Automate Affinda tasks"); "Always search tools first" is a procedural note, not a concrete capability, so it fits anchor 2 rather than anchor 3 which requires 1-2 concrete actions.	2 / 5
Completeness	It gives a clear "what" (automate Affinda via Rube MCP) but provides no "Use when..." trigger guidance, so per the rubric's cap a missing explicit trigger clause holds completeness at anchor 3.	3 / 5
Trigger Term Quality	Beyond the single brand keyword "Affinda", the terms ("Rube MCP", "Composio", "search tools") are technical jargon with no natural user-facing phrases or synonyms, matching anchor 2 (one or two generic keywords, missing natural phrases) rather than the fuller coverage of anchor 3.	2 / 5
Distinctiveness Conflict Risk	"Affinda" is a distinct branded niche scoped further by "via Rube MCP (Composio)", giving minimal conflict risk with only minor overlap against sibling Composio toolkit skills, fitting anchor 4.	4 / 5
	Total	11 / 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: ComposioHQ/awesome-claude-skills
Path: composio-skills/affinda-automation/SKILL.md
Commit: be2a406

Reviewed: 7 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.