CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

linear-claude-skill

Manage Linear issues, projects, and teams

Quality

59%

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 ./skills/linear-claude-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 strong on concrete, executable commands and covers setup, conventions, security, and project lifecycle well, but it is badly padded — the same 'When to Use This Skill' boilerplate appears five times and command docs are duplicated — and its bulk/batch workflows lack the validation checkpoints the rubric requires. Referenced bundle files are clearly signaled but cannot be verified and some detailed reference material is inlined instead.

Suggestions

Delete the four duplicate 'When to Use This Skill' boilerplate blocks (keep at most one, merged into a proper intro) and consolidate the duplicated project-status/link-initiative documentation into a single section or into projects.md.

Add a validation step to batch operations, e.g., after `status Done ENG-101 ENG-102 ENG-103`, verify with `linear issues list` or re-query the issues before reporting success.

Move the detailed project management command reference out of SKILL.md into projects.md, keeping only quick-start commands inline, and ensure all referenced files (api.md, sdk.md, sync.md, troubleshooting.md, docs/labels.md) actually ship with the skill.

DimensionReasoningScore

Conciseness

The boilerplate block "Manage Linear issues, projects, and teams / Use this skill when working with manage linear issues, projects, and teams" is repeated verbatim five times throughout the body, and the project-status/link-initiative command documentation appears twice (in 'Project Management Commands' and again in 'Projects & Initiatives'). This is noticeably verbose with several padded sections — worse than 'some unnecessary explanation'.

2 / 5

Actionability

Mostly executable guidance: concrete `npx tsx scripts/linear-ops.ts ...` commands with real arguments, a valid-states table, MCP JSON config, and a full project lifecycle example. Minor gaps keep it from a 5: the MCP invocation `update_issue with id="issue-uuid", state="Done"` is illustrative rather than copy-paste ready, and several examples use ENG-XXX placeholders.

4 / 5

Workflow Clarity

Sequences are clearly laid out (setup check → test connection, the 7-step project lifecycle), but batch operations such as `status Done ENG-101 ENG-102 ENG-103` and bulk project updates include no validation or verification step, which caps workflow clarity at 3 per the batch-operations rule. Not a 4 because the checkpoint gaps affect the risky bulk paths, not just minor cases.

3 / 5

Progressive Disclosure

There is good intent — a reference table and one-level-deep 'See X for Y' pointers to api.md, sdk.md, sync.md, projects.md, troubleshooting.md — but the detailed project-status/link-initiative command reference is inlined in the body (duplicating what projects.md should carry), the repeated 'When to Use' blocks break section flow, and none of the referenced files exist in the bundle to verify. This fits 'some structure but could be better organized' better than the anchor-4 'most content is appropriately placed'.

3 / 5

Total

12

/

20

Passed

Description

52%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 short and names a distinct product niche, so conflict risk is minimal, but it is under-specified: the generic verb "Manage" conveys no concrete capabilities, and it entirely lacks a 'Use when...' trigger clause. It reads closer to a category label than a skill description.

Suggestions

List the concrete operations the skill performs, e.g., "Create, update, and triage Linear issues, manage project status, and link projects to initiatives" instead of the single generic verb "Manage".

Add an explicit trigger clause: "Use when working with Linear issues, tickets, projects, or team backlogs, or when the user mentions Linear."

Include natural synonyms users would say (tickets, bugs, backlog, roadmap) to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description names the domain ("Linear") and its objects ("issues, projects, and teams") but the only action verb is the generic "Manage", matching the anchor 'Names the domain but actions are minimal or generic'. It is not a 3 because no concrete action (e.g., create, update, triage, link) is explicitly stated.

2 / 5

Completeness

The 'what' is present and moderately clear (managing Linear issues/projects/teams) but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not a 2 because the 'what' does name concrete domain objects rather than being entirely vague.

3 / 5

Trigger Term Quality

"Linear", "issues", "projects", and "teams" are terms users would naturally say, but common variations and synonyms (tickets, bugs, backlog, roadmap, sprint, cycles) are missing. This is 'some relevant keywords but missing common variations or synonyms', below anchor 4's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

"Linear" explicitly names a specific product, giving the description a clear niche with minimal conflict risk — it would not trigger for non-Linear work. This matches the anchor 'Clear niche with distinct triggers; minimal conflict risk'.

5 / 5

Total

13

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (543 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 40 missing

Warning

Total

13

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

skills/linear-claude-skill/SKILL.md

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.