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.

1.28x

Quality

68%

Does it follow best practices?

Impact

82%

1.28x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/coda-automation/SKILL.md

Quality

Content

65%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 content is well-structured and actionable, giving concrete tool sequences and parameters across six workflows without over-explaining basics. Its main weaknesses are missing validation checkpoints for batch and destructive operations, and an all-inline structure with no reference files for a skill this long.

Suggestions

Add explicit validation checkpoints to batch and outward-facing workflows: after CODA_UPSERT_ROWS verify the affected rows, and before CODA_PUBLISH_DOC or CODA_ADD_PERMISSION confirm with the user given the public/email consequences.

Move the per-workflow parameter detail and the Quick Reference table into one-level-deep reference files (e.g., REFERENCE.md, WORKFLOWS.md) and link them from a concise overview, so the main SKILL.md stays a lean index.

De-duplicate the 'Known Pitfalls' section against the per-workflow 'Pitfalls' blocks, or fold the global pitfalls into the relevant workflows, to remove the repeated ID-format and data-type content.

Dimension	Reasoning	Score
Conciseness	The body is efficient and avoids explaining concepts Claude already knows, but the 'Known Pitfalls' section partially re-covers ID formats and data types already listed under each workflow, and the Quick Reference table re-lists tool slugs, so it is not the fully lean anchor at 5.	4 / 5
Actionability	Each workflow gives a numbered tool sequence plus named key parameters, which is the executable unit for an MCP-orchestration skill, though no example request payloads or resolved parameter values are shown, leaving minor gaps versus the copy-paste-ready anchor at 5.	4 / 5
Workflow Clarity	Sequences are clearly numbered and the Setup section verifies the connection is ACTIVE, but batch (CODA_UPSERT_ROWS) and outward-facing/destructive operations (CODA_PUBLISH_DOC, CODA_ADD_PERMISSION) lack validation checkpoints, and the rubric caps workflow clarity at 3 when such validation is missing.	3 / 5
Progressive Disclosure	The body is well-sectioned into six workflows plus patterns and a reference table, but at roughly 240 lines everything is inlined with no one-level-deep reference files, and the per-workflow detail and Quick Reference could be split out, matching the 'content that should be separate is inline' anchor at 3 rather than the well-split anchor at 5.	3 / 5
	Total	14 / 20 Passed

Description

71%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 action-rich with a clear Coda niche, but it lacks an explicit 'Use when' trigger clause, which caps its completeness and limits trigger guidance. Strong on capability enumeration, weaker on usage triggers.

Suggestions

Add an explicit 'Use when...' clause naming the user phrases that should activate this skill (e.g., managing Coda docs, querying Coda tables, publishing a Coda document).

Include natural synonyms and surface forms such as 'Coda docs', 'Coda tables', or Coda URLs to broaden trigger coverage toward the comprehensive anchor.

Tighten the operational aside ('Always search tools first for current schemas') into the trigger clause so it reads as usage guidance rather than a disconnected instruction.

Dimension	Reasoning	Score
Specificity	The description enumerates seven concrete capability areas ('docs, pages, tables, rows, formulas, permissions, and publishing'), matching the comprehensive multi-action anchor rather than the 1-2 action anchor at 3.	5 / 5
Completeness	The 'what' is explicit and concrete, but there is no 'Use when...' or equivalent trigger clause; per the guideline a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Natural terms like 'Coda', 'docs', 'tables', 'rows', 'permissions', and 'publishing' map well to user phrasing, but synonyms and file/URL extensions are absent, placing it just below the comprehensive anchor at 5.	4 / 5
Distinctiveness Conflict Risk	'Coda tasks via Rube MCP (Composio)' carves a clear niche, but it could still overlap with generic document or project-management skills, so it is not the minimal-conflict anchor at 5.	4 / 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: davepoon/buildwithclaude
Path: plugins/all-skills/skills/coda-automation/SKILL.md
Commit: a9fa86d

Reviewed: about 19 hours 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.