CtrlK
BlogDocsLog inGet started
Tessl Logo

linear-automation

Automate Linear tasks via Rube MCP (Composio): issues, projects, cycles, teams, labels. Always search tools first for current schemas.

77

1.97x
Quality

73%

Does it follow best practices?

Impact

95%

1.97x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/linear-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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-sectioned, highly actionable operator's guide for the Rube/Linear toolset with a validated setup flow, held back by wholesale duplication between the workflow, Known Pitfalls, and Quick Reference sections and by the absence of any reference files to offload the tool catalog. Splitting the reference material out and deduplicating the pitfalls would address the two weakest dimensions.

Suggestions

Move the Quick Reference tool table (and per-workflow parameter details) into a references/ file such as references/tool-catalog.md, keeping SKILL.md as a concise overview with clearly signaled links.

Deduplicate the pitfalls: priority integer values and team-scoping guidance each appear in both a workflow's Pitfalls block and the global Known Pitfalls section — state each once.

Add a minimal executable example for the GraphQL workflow (a sample query plus variables) and name the actual pagination cursor field instead of "Check for pagination cursors in responses."

DimensionReasoningScore

Conciseness

The body is almost entirely operational content — tool slugs, parameter names, integer mappings — with no explanation of concepts Claude already knows. It is not a 5 because the "Known Pitfalls" section repeats workflow-level pitfalls verbatim (priority integer values, team scoping) and the Quick Reference table duplicates the workflow tool sequences, so it could be meaningfully tightened.

4 / 5

Actionability

Exact tool slugs (e.g. LINEAR_CREATE_LINEAR_ISSUE), named parameters (team_id, state_id, label_ids), the priority integer mapping, and ordered sequences give mostly executable, copy-paste-ready guidance; as an instruction-only MCP skill, absence of code is not penalized. Minor gaps keep it below 5: the GraphQL workflow gives no example query, and pagination says "Check for pagination cursors" without naming the actual cursor parameter.

4 / 5

Workflow Clarity

The setup sequence includes an explicit validation checkpoint ("Confirm connection status shows ACTIVE before running any workflows") and an error-recovery branch (follow the auth link if not ACTIVE), and workflows tag [Prerequisite]/[Optional] steps. It is not a 5 because core workflows lack post-action verification (e.g., confirming a created issue's ID/state), leaving minor validation gaps.

4 / 5

Progressive Disclosure

There are no bundle files at all, and the 19-row Quick Reference tool catalog plus the full parameter details are exactly the content that belongs in a one-level-deep reference file. Section structure is good, but all reference-grade content is inlined in a single 176-line file, matching anchor 3 rather than 4.

3 / 5

Total

15

/

20

Passed

Description

65%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 compact, names a distinct niche, and covers the right object vocabulary, but it never states when the skill should be used and hides its actual capabilities behind the single generic verb "Automate". Adding an explicit trigger clause and concrete action verbs would lift the two weakest dimensions.

Suggestions

Add an explicit 'Use when...' clause, e.g. "Use when the user mentions Linear or wants to create, update, or search Linear issues, projects, cycles, or labels."

Replace the generic verb "Automate" with concrete actions, e.g. "Create, update, and search Linear issues, projects, cycles, teams, and labels via Rube MCP (Composio)."

Include common synonyms users say, such as "sprints" (cycles) and "tickets" (issues), to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

The description names the domain ("Automate Linear tasks via Rube MCP") and lists objects ("issues, projects, cycles, teams, labels"), but the only verb is the generic "Automate" with no concrete actions like create, update, or search. It matches anchor 3 (domain plus limited concrete actions) rather than 4, which requires several specific action verbs.

3 / 5

Completeness

The "what" is clear (automate Linear objects via Rube MCP/Composio), but there is no "Use when..." trigger clause or equivalent explicit usage guidance anywhere in the description. Per the judging guidelines, a missing 'Use when' clause caps completeness at 3.

3 / 5

Trigger Term Quality

"Linear", "issues", "projects", "cycles", "teams", "labels", and "tasks" are natural terms users would say, giving good keyword coverage. It falls short of anchor 5 because common synonyms and variations ("sprints", "tickets", "backlog") are missing.

4 / 5

Distinctiveness Conflict Risk

"Linear" combined with "Rube MCP (Composio)" carves out a clear product-specific niche with distinct triggers and minimal risk of firing for the wrong skill. It matches anchor 5; anchor 4's "minor overlap risk" would understate how specific the Linear/Rube pairing is.

5 / 5

Total

15

/

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.

Validation — 15 / 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
davepoon/buildwithclaude
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.