CtrlK
BlogDocsLog inGet started
Tessl Logo

abyssale-automation

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

72

16.66x
Quality

58%

Does it follow best practices?

Impact

100%

16.66x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./composio-skills/abyssale-automation/SKILL.md
SKILL.md
Quality
Evals
Security

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 concrete RUBE MCP call patterns and explicit connection-validation checkpoints. Its main weaknesses are repeated "search first" guidance and a missing post-execution validation loop for batch tool calls.

Suggestions

Consolidate the "always search tools first" guidance into one prominent location to remove repetition across five sections.

Add a post-execution validation step for RUBE_MULTI_EXECUTE_TOOL (inspect per-tool results, retry failed tools, confirm completion) to satisfy the batch-operation feedback-loop expectation.

Consider moving the bulk API/pitfall detail into a references file so the SKILL.md overview stays leaner, improving progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly lean and avoids explaining what Abyssale is, but the directive "always search tools first" is repeated across Prerequisites, Setup, Tool Discovery, Core Workflow Step 1, and Known Pitfalls, which could be tightened to one or two well-placed instances.

3 / 5

Actionability

Concrete RUBE_* call blocks with real field names (queries, session, tools, arguments, memory, session_id) give mostly executable guidance; the placeholders ("TOOL_SLUG_FROM_SEARCH", "{/* schema-compliant args */}") are justified by the dynamic-schema premise rather than being vague hand-waving, leaving only minor gaps.

4 / 5

Workflow Clarity

A clear Discover -> Check connection -> Execute sequence with validation checkpoints (confirm ACTIVE before running, pagination continuation) is present; the gap is no post-execution error-checking/retry feedback loop for the batch RUBE_MULTI_EXECUTE_TOOL call, which keeps it at 4 rather than 5.

4 / 5

Progressive Disclosure

No bundle files exist and the skill is self-contained with well-labeled sections plus a Quick Reference table for navigation; it is slightly over the ~50-line simple-skill threshold and has cross-section repetition, so it sits at good-but-not-exemplary structure rather than 5.

4 / 5

Total

15

/

20

Passed

Description

48%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 identifies a specific niche (Abyssale via Rube MCP) but is thin on concrete capabilities and entirely lacks an explicit usage trigger, capping completeness. It is distinct yet shares framing with other Rube/Composio toolkit skills.

Suggestions

Add 2-3 concrete Abyssale actions (e.g. generate banners, create/export designs, manage templates) to lift specificity.

Append an explicit "Use when ..." trigger clause naming natural user phrases (banners, Abyssale designs, dynamic image generation).

Add a synonym or file-format term (e.g. "banners", "visuals") to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

"Automate Abyssale tasks via Rube MCP" names the domain and mechanism but the only action verb is the generic "Automate ... tasks"; no concrete Abyssale operations (e.g. generate banners, create templates) are listed, so it sits at the minimal/generic-action anchor rather than the 1-2 concrete actions of a 3.

2 / 5

Completeness

The "what" is clear (automate Abyssale tasks via Rube MCP) but there is no "Use when..." trigger clause; "Always search tools first for current schemas" is procedural guidance, not a usage trigger, so per the missing-trigger cap it cannot exceed 3.

3 / 5

Trigger Term Quality

It surfaces the natural brand keyword "Abyssale" plus "Rube MCP"/"Composio", but misses common synonyms or variations a user might say (banners, visuals, image generation), fitting the "some relevant keywords but missing variations" anchor.

3 / 5

Distinctiveness Conflict Risk

The Abyssale brand carves a clear niche with low conflict risk, but the shared "Rube MCP / Composio" framing overlaps with sibling toolkit-automation skills, matching the "mostly distinct; minor overlap risk" anchor rather than a 5.

4 / 5

Total

12

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
ComposioHQ/awesome-claude-skills
Reviewed

Table of Contents

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.