CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

jira-issues

Create, read, update, and delete Jira issues. Use when managing Stories, Tasks, Bugs, or Epics - includes field updates and metadata.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

—

The risk profile of this skill

SKILL.md
Quality
Evals
Security

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 highly actionable, with complete, executable TypeScript and curl examples for every operation, but it pays for that with significant duplication between the two formats and a ~355-line monolithic body. More importantly, the destructive delete and batch bulk-create workflows lack any validation, verification, or error-recovery steps, capping workflow clarity despite the clear step sequence.

Suggestions

Eliminate the duplication between the TypeScript implementations and the curl examples — keep one canonical form per operation and drop the other, cutting the body roughly in half.

Add validation checkpoints: verify creation with a follow-up GET, warn/confirm before the destructive DELETE, and handle partial failures in bulkCreateIssues (e.g., catch per-issue errors and report which succeeded or failed) instead of relying on bare Promise.all.

Move the ADF format reference, the full JiraIssue interface, and bulk-operation details into a separate reference file (e.g., references/adf.md or references/bulk.md) and link to them from a leaner SKILL.md overview.

DimensionReasoningScore

Conciseness

The body is mostly efficient code with no explanation of concepts Claude already knows, but it is notably duplicated: every operation appears as both a TypeScript implementation and a curl block, the ADF format is shown twice, and "Required Fields by Issue Type" repeats the same three required fields per type. It fits "mostly efficient but could be tightened" rather than the severely padded anchor (2), though the ~355-line length pushes against that boundary.

3 / 5

Actionability

Guidance is fully executable: complete TypeScript functions, copy-paste-ready curl commands with auth headers and JSON bodies, an endpoint summary table, and a concrete ADF JSON example cover the common create/get/update/delete cases. Nothing is pseudocode or abstract, so it clearly matches the top anchor.

5 / 5

Workflow Clarity

Steps 1-6 present a clear sequence, but there are no validation or verification checkpoints anywhere: the destructive delete operation has no confirmation or post-check, and the batch bulk-create has no partial-failure handling or verification of created issues. The rubric explicitly caps destructive/batch workflows without validation at 3, which takes precedence over the otherwise good sequencing.

3 / 5

Progressive Disclosure

The body has good section headers and external links, but it is a single ~355-line file with no bundle files at all: the ADF reference, the full interface definitions, and bulk-operation details are all inlined content that could live in separate reference files. It sits above the buried-references/no-structure anchors (1-2) but below the "most content appropriately placed" anchor (4).

3 / 5

Total

14

/

20

Passed

Description

92%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 strong description that pairs a concrete statement of capabilities (full CRUD plus field updates on Jira issues) with an explicit, naturally-phrased "Use when" trigger clause naming the issue types users actually mention. The only improvement space is broader synonym coverage (e.g., "ticket", "backlog") in the trigger terms.

DimensionReasoningScore

Specificity

"Create, read, update, and delete Jira issues" lists four concrete CRUD actions plus "includes field updates", matching the comprehensive multi-action anchor. "Metadata" alone is slightly generic, but there is no coverage gap within issue management, so it does not fall to the minor-gaps anchor (4).

5 / 5

Completeness

It explicitly answers both "what" ("Create, read, update, and delete Jira issues... includes field updates") and "when" ("Use when managing Stories, Tasks, Bugs, or Epics") with a concrete trigger phrase, matching the top anchor. Not 4 because the "when" clause is explicit and specific rather than only serviceable.

5 / 5

Trigger Term Quality

"Use when managing Stories, Tasks, Bugs, or Epics" provides good, natural keyword coverage that users would actually say. Common synonyms like "ticket", "backlog", or "assign" are missing, which keeps it just below the comprehensive-synonyms anchor (5) but above the some-relevant-keywords anchor (3).

4 / 5

Distinctiveness Conflict Risk

"Jira issues" carves out a clear niche and the triggers (Stories, Tasks, Bugs, Epics) are Jira-specific issue types, giving minimal conflict risk with non-Jira skills. Not 4 because there is no meaningful overlap risk with adjacent skills based on the description alone.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

NeverSight/learn-skills.dev

Path

data/skills-md/01000001-01001110/agent-jira-skills/jira-issues/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.