basecamp-automation

Automate Basecamp project management, to-dos, messages, people, and to-do list organization via Rube MCP (Composio). Always search tools first for current schemas.

1.22x

Quality

69%

Does it follow best practices?

Impact

94%

1.22x

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/basecamp-automation/SKILL.md

Quality

Content

68%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 highly actionable, with exact tool sequences, typed parameters, enums, and API pitfalls that Claude could not know otherwise, and it is cleanly organized. Its two weaknesses are redundancy — the Known Pitfalls section largely restates per-workflow pitfalls — and the absence of validation checkpoints around the destructive/batch operations (access revocation, full-body message updates).

Suggestions

Consolidate the "Known Pitfalls" section: integer IDs, HTML-only content, and prefer-app_url each appear 3-4 times across workflows, Common Patterns, and Known Pitfalls — state each fact once and reference it.

Add validation checkpoints for destructive and batch operations: confirm with the user before revoking access via PUT_PROJECTS_PEOPLE_USERS, verify the full corrected body before a replace-all PUT_BUCKETS_MESSAGES update, and re-list project people after access changes.

Trim the Quick Reference table of near-duplicate rows (e.g., the "(alt)" rows that repeat an existing tool with the same params) since the workflows already document fallback ordering.

Dimension	Reasoning	Score
Conciseness	The body is dense with Basecamp/Rube-specific facts Claude cannot know (tool slugs, integer IDs, HTML-only content, draft-status 400s), but the same pitfalls are repeated three to four times across per-workflow "Pitfalls" lists, the "Known Pitfalls" section, and "Content Formatting" (integer IDs, HTML-not-Markdown, prefer app_url). This matches anchor 3 — mostly efficient but could be consolidated and tightened — rather than anchor 2 since none of it explains concepts Claude already knows.	3 / 5
Actionability	Guidance is fully executable for an MCP-tool skill: exact tool slugs with ordering tags ([Prerequisite]/[Required]/[Alternative]), parameter names with types and formats ("due_on: Due date in YYYY-MM-DD format"), the complete fixed color enum, a concrete HTML example ("<div><strong>Important:</strong> Complete by Friday</div>"), and explicit fallback ordering between duplicate tools. Per the rubric's scoring note, absence of code in an instruction-only skill is not penalized when the guidance is this concrete.	5 / 5
Workflow Clarity	Sequences are clearly numbered with role tags and some checkpoints exist (verify connection is ACTIVE before workflows, check existing to-do lists to avoid duplicates), but the destructive and batch operations lack validation steps — PUT_PROJECTS_PEOPLE_USERS can revoke access in bulk with no confirm-before-revoke or post-change verification step, and full-body message PUTs have no verify-before-replace checkpoint. Per the judging guideline, missing validation in destructive/batch workflows caps workflow clarity at 3.	3 / 5
Progressive Disclosure	The single SKILL.md is well-sectioned (prerequisites, setup, five workflows, common patterns, quick reference table) with the external toolkit doc clearly linked, and no bundle files exist to reference. It scores 4 rather than 5 because at ~230 lines the per-workflow parameter detail and Quick Reference table are borderline content that could live in a one-level-deep reference file, and the rubric's 5-exception for well-organized single files applies only under 50 lines.	4 / 5
	Total	15 / 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.

The description is distinctive and reasonably specific thanks to the named product and enumerated capability areas, but it lacks any explicit "when to use" trigger clause, which both caps completeness and weakens its value for skill selection. The uniform verb "Automate" also leaves the actions slightly generic despite the concrete object list.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions Basecamp, to-dos or tasks, message boards, or managing project members and access."

Replace the single verb "Automate" with distinct concrete actions per capability (e.g., "Create to-do lists and to-dos, post messages to message boards, grant or revoke project access, manage people").

Drop the procedural sentence "Always search tools first for current schemas" from the description — it is runtime instruction, not capability description, and its token budget is better spent on trigger terms.

Dimension	Reasoning	Score
Specificity	The description enumerates several concrete capability areas ("to-dos, messages, people, and to-do list organization") tied to a named product, which goes beyond the 1-2 actions of anchor 3. However, a single generic verb "Automate" carries all of them rather than distinct action verbs (create, post, grant), so it does not reach anchor 5's comprehensive concrete-action coverage.	4 / 5
Completeness	The "what" is clearly stated (automating Basecamp project management, to-dos, messages, people via Rube MCP), but there is no "Use when..." clause or equivalent trigger guidance — the trailing "Always search tools first for current schemas" is an operating instruction, not a when-to-use trigger, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	"Basecamp", "to-dos", "messages", "people", and "project management" are terms users would naturally say, giving good keyword coverage. It falls short of anchor 5 because common synonyms and variations are missing (e.g., "tasks", "to-do lists", "message board", "assignees").	4 / 5
Distinctiveness Conflict Risk	"Basecamp" names a specific product with a clear niche (further scoped by "via Rube MCP (Composio)"), so it would not plausibly trigger for any other skill — matching anchor 5's clear niche with distinct triggers and minimal conflict risk.	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: davepoon/buildwithclaude
Path: plugins/all-skills/skills/basecamp-automation/SKILL.md
Commit: c9856ea

Reviewed: 6 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.