CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

jira-safe

Implement SAFe methodology in Jira. Use when creating Epics, Features, Stories with proper hierarchy, acceptance criteria, and parent-child linking.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./data/skills-md/01000001-01001110/agent-jira-skills/jira-safe/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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.

A dense, knowledgeable reference with genuinely executable Jira REST v3 code and correct Next-Gen vs Classic guidance, undermined by verbosity (tutorials on INVEST and Given-When-Then that Claude already knows, triplicated Next-Gen/Classic tables), a monolithic single-file structure, and a destructive bulk-delete workflow with no validation checkpoint. The technical content is strong; the organization and safety/validation discipline lag behind.

Suggestions

Move the full ADF JSON templates (Epic/Story) into one-level-deep reference files (e.g. references/templates.md) and keep only a compact example inline, cutting SKILL.md to a navigable overview.

Delete or drastically compress the 'SAFe Best Practices' section (INVEST criteria, Given-When-Then, 'As a persona' story format) — this is standard knowledge Claude already has — and consolidate the Next-Gen vs Classic differences, which currently appear in three separate table sections.

Add a validation checkpoint to 'Bulk Delete Issues': a dry-run/JQL count confirmation and per-delete response checking (it currently ignores DELETE responses and uses an undefined 'headers' variable), and define the shared 'headers' once for all functions.

DimensionReasoningScore

Conciseness

The body includes ~85-line inline ADF JSON templates and sections explaining concepts Claude already knows (INVEST criteria, Given-When-Then format, 'As a... I want...' story format), plus the Next-Gen vs Classic differences repeated across three separate table sections. Mostly efficient and dense with real API detail, but clearly could be tightened and trimmed.

3 / 5

Actionability

Largely executable, near copy-paste-ready code with auth headers, error handling, and rate limiting ('const headers = { Authorization: Basic ... }', 'if (!epicResponse.ok) throw ...'). Minor gaps: findEpicLinkField() and bulkDeleteIssues() reference an undefined 'headers' variable, and bulkDeleteIssues() never checks delete responses, so it is not fully runnable as written.

4 / 5

Workflow Clarity

Sequences are clearly numbered within functions ('1. Create Epic', '2. Create Stories linked to Epic') and 'Always detect project type first' is a good upfront step, but the destructive 'Bulk Delete Issues' batch operation has no validation, confirmation, or dry-run step — the rubric explicitly caps workflow clarity at 3 for destructive/batch workflows without validation, which takes precedence here.

3 / 5

Progressive Disclosure

The skill is a single monolithic ~450-line file with no bundle files (references/, scripts/, assets/ are absent). Section headers are clear and navigation is reasonable, but the bulk of the content (full ADF JSON templates, per-project-type field tables, API functions) is inlined and would be better split into one-level-deep reference files.

3 / 5

Total

13

/

20

Passed

Description

75%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 solid description that clearly states what the skill does and gives an explicit 'Use when' trigger clause with concrete, domain-specific terms. It sits just below top marks on every dimension for the same reason: trigger coverage is narrower than ideal — no synonyms ('user stories', 'subtasks') and no user-mention phrasing — leaving a few natural entry points unserved.

Suggestions

Broaden the 'Use when' clause with user-mention triggers and synonyms, e.g. 'Use when the user mentions SAFe, asks to write user stories or acceptance criteria, or needs to link Jira issues in an Epic-Feature-Story hierarchy.'

Mention Subtasks explicitly (the body devotes a template and a link type to them) so the description covers the full hierarchy it actually supports.

DimensionReasoningScore

Specificity

'Creating Epics, Features, Stories with proper hierarchy, acceptance criteria, and parent-child linking' lists several concrete actions in the Jira domain. Not 5 because coverage has gaps (no subtasks, editing, searching, or deletion); not 3 because it goes well beyond 1-2 actions.

4 / 5

Completeness

Both parts are present: 'Implement SAFe methodology in Jira' (what) and 'Use when creating Epics, Features, Stories...' (when). Not 5 because the 'when' clause omits user-mention triggers and synonyms (e.g. 'when the user mentions SAFe, wants to write user stories, or link Jira issues'), so it is explicit but narrower than the top anchor.

4 / 5

Trigger Term Quality

Contains natural terms users would say ('Epics', 'Features', 'Stories', 'Jira', 'SAFe', 'acceptance criteria', 'parent-child linking'). Not 5 because common variations are missing ('user stories', 'subtasks', 'tasks', 'backlog', 'linking issues'); not 3 because coverage is good rather than partial.

4 / 5

Distinctiveness Conflict Risk

The SAFe-in-Jira framing with named issue types is a clear niche with distinct triggers. Not 5 because it could still overlap with a generic Jira-issue-management skill ('creating Epics... with hierarchy' without SAFe context); not 3 because the overlap risk is minor.

4 / 5

Total

16

/

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-safe/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.