CtrlK
BlogDocsLog inGet started
Tessl Logo

coda-automation

Automate Coda tasks via Rube MCP (Composio): manage docs, pages, tables, rows, formulas, permissions, and publishing. Always search tools first for current schemas.

58

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/coda-automation/SKILL.md

The canonical home for this skill is coda-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

61%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 well-structured and actionable, with clear tool sequences and a useful quick-reference table, but it is held back by redundant pitfall restatements and missing validation checkpoints on its batch/destructive workflows.

Suggestions

Add post-action verification steps to destructive/batch workflows (e.g. re-list rows after UPSERT_ROWS, confirm publish state after CODA_PUBLISH_DOC) to enable validate->fix->retry loops.

Remove the duplicate pitfall content in 'Known Pitfalls' that rehashes the per-workflow 'Pitfalls' bullets, or consolidate them in one place.

Provide an example rows payload and keyColumns mapping for CODA_UPSERT_ROWS to close the main actionability gap.

DimensionReasoningScore

Conciseness

Mostly efficient bullet/sequence formatting, but the 'Known Pitfalls' section restates earlier per-workflow pitfalls (ID Formats, Data Types, Rate Limits) and the Quick Reference table re-lists workflows, adding redundancy that could be trimmed.

3 / 5

Actionability

Concrete tool sequences with exact slugs, parameters, and a task→tool Quick Reference table give mostly executable guidance; minor gaps such as no example row payload for CODA_UPSERT_ROWS.

4 / 5

Workflow Clarity

Sequences are clearly numbered with Required/Optional tags and setup validation exists, but batch/destructive workflows (UPSERT_ROWS, PUBLISH_DOC, ADD_PERMISSION) lack post-action verify/feedback checkpoints, capping workflow clarity at 3 per the destructive-operations rule.

3 / 5

Progressive Disclosure

Well-organized sections with clear navigation and no nested references; all content lives inline in one file, which is reasonable for this MCP tool catalog with no bundle files provided.

4 / 5

Total

14

/

20

Passed

Description

75%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 is specific and clearly niche-scoped to Coda automation, but it omits an explicit 'when to use' trigger clause, which caps its completeness. Trigger term coverage is good but slightly jargon-heavy.

Suggestions

Add an explicit 'Use when...' clause naming concrete user triggers, e.g. 'Use when automating Coda docs, tables, rows, formulas, or publishing tasks via Rube MCP.'

Soften product jargon ('Rube MCP (Composio)') or pair it with plain-language synonyms so natural user phrasing maps to the skill.

DimensionReasoningScore

Specificity

Enumerates concrete actions across the domain — 'manage docs, pages, tables, rows, formulas, permissions, and publishing' — giving comprehensive coverage rather than vague abstraction.

5 / 5

Completeness

Has a clear 'what' (the enumerated Coda operations) but no 'Use when...' trigger clause; the second sentence ('Always search tools first...') is procedural guidance, not a usage trigger, capping completeness at 3.

3 / 5

Trigger Term Quality

Includes natural terms a user would say ('Coda tasks', 'docs', 'pages', 'tables', 'publishing') but leans on product jargon ('Rube MCP (Composio)') and lacks synonyms/common variations, so a few natural terms are missing.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (Coda automation via a specific MCP) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

17

/

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
administrakt0r/AI-Agents-Safe-Coding-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.