CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

linear

Load for any Linear read or write: issues, projects, cycles, milestones, initiatives, labels.

Quality

76%

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 ./.agents/skills/linear/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.

An information-dense, highly actionable CLI reference with strong pre-write validation semantics and real feedback loops for batch and destructive operations. The weaknesses are structural: two links target a `patterns/workflow-actions.md` file absent from the bundle, and long policy sections are inlined in SKILL.md instead of being split into clearly signaled one-level-deep references.

Suggestions

Resolve the broken navigation: either add patterns/workflow-actions.md to the bundle (including the quota-holds section anchor) or move the quota-hold and multi-step workflow details into an existing file under references/ and update both links.

Move the Shared label maintenance and Issue Creation Routing policy prose into a reference file (e.g., references/label-policy.md), keeping a two- to three-line summary with a clearly signaled link in SKILL.md.

Restructure the `issues complete` bullet (Option Behavior section) into a short numbered sequence with its validation checkpoints (parse Done-when checklist, refuse on open boxes, tick with evidence, set state) instead of one run-on paragraph.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious operational rules (refusal lines, format-rename semantics, guard behavior) and contains no padding or explanations of concepts Claude already knows, matching "efficient; minor instances that could be trimmed." It misses anchor 5 because a few passages repeat `issues --help` pointers and several run-on sentences (e.g., the `issues complete` bullet) pack many rules together and could be tightened.

4 / 5

Actionability

Concrete, executable commands are present (e.g., `linear.sh issues list --project "Phase 2" --state "Todo,In Progress" --max`, `linear.sh attachments fetch [URL] --output tmp/[FILENAME]`) along with exact flags, env vars, stderr refusal lines, and per-command `--help` routes. It stops short of anchor 5 because the most common write operations (create, update, complete) never get an example invocation — the reader must consult `--help` to construct them.

4 / 5

Workflow Clarity

Multi-step processes carry explicit validation: the label workflow ("Fetch current labels, compute the final set, validate it against `labels list --max --format=safe`"), "Run `auth-check --strict` before the first mutation", bulk-refusals listed before writes with `partial: true` exit-nonzero semantics, and `issues bulk-get` named as the post-mutation verification path. The destructive/batch cap at 3 does not apply since validation is present throughout; it misses 5 because sections like Issue Creation Routing and the `issues complete` bullet state rules as dense prose rather than a sequenced procedure with checkpoints.

4 / 5

Progressive Disclosure

The two bundle references are real and clearly signaled ([authentication](references/authentication.md), [request journal](references/request-journal.md)), but the body links `patterns/workflow-actions.md` twice (including the "Quota Holds" section anchor) and no `patterns/` directory exists in the bundle — a broken navigation path. Additionally, substantial inline rule/policy content (Shared label maintenance, Issue Creation Routing, Option Behavior minutiae) reads as material that belongs in reference files, matching anchor 3 ("content that should be separate is inline") rather than anchor 4's "most content is appropriately placed."

3 / 5

Total

15

/

20

Passed

Description

73%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.

A short, distinctive, well-triggered description that clearly signals when to load the skill and scopes it to Linear's resources. Its main weakness is that the capabilities are stated only as the generic pair "read or write" rather than naming the concrete actions the skill supports.

DimensionReasoningScore

Specificity

"Load for any Linear read or write: issues, projects, cycles, milestones, initiatives, labels" names the domain and enumerates six resources, but the only actions offered are the generic verbs "read or write" — no concrete operations like create, update, bulk-update, list, or delete. It sits above anchor 2 ("Processes PDF files"-level minimal actions) because of the resource enumeration, but below anchor 4, which requires several specific actions.

3 / 5

Completeness

The "when" is explicit and broad — "Load for any Linear read or write" is equivalent trigger guidance, so the missing-'Use when' cap does not apply — and the resource list scopes the "what". It falls short of anchor 5 because the "what" never states what the skill actually does (a CLI wrapper with create/update/bulk operations); the mechanism is only implied by the verb pair.

4 / 5

Trigger Term Quality

"Linear", "issues", "projects", "cycles", "milestones", "initiatives", "labels" are exactly the nouns a user would say when needing this skill, giving good keyword coverage. A few natural terms are missing (e.g., "tickets", "comments", "attachments", "team", "backlog", "triage"), keeping it below the comprehensive-synonyms anchor 5.

4 / 5

Distinctiveness Conflict Risk

"Linear" pins a clear niche (the Linear issue tracker) and the enumerated resources are Linear-specific vocabulary, so it would not plausibly trigger a GitHub/Jira/general-project skill. Minimal conflict risk matches anchor 5.

5 / 5

Total

16

/

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

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 2 possibly missing (patterns/workflow-actions.md, patterns/workflow-actions.md#quota-holds)

Warning

referenced_paths_exist

Referenced path issues: 3 possibly missing (references/labels.md, references/project-map.md, references/reports.md)

Warning

Total

13

/

16

Passed

Repository

vanillagreencom/kendex

Path

.agents/skills/linear/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.