jira-safe
Implement SAFe methodology in Jira. Use when creating Epics, Features, Stories with proper hierarchy, acceptance criteria, and parent-child linking.
77
71%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/01000001-01001110/agent-jira-skills/jira-safe/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, well-crafted description that clearly identifies its domain (SAFe in Jira), lists specific actions (creating Epics, Features, Stories with hierarchy and acceptance criteria), and includes an explicit 'Use when' clause with natural trigger terms. The description is concise yet comprehensive, and its specificity to SAFe methodology in Jira makes it highly distinctive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creating Epics, Features, Stories, establishing proper hierarchy, writing acceptance criteria, and parent-child linking. These are all concrete, actionable tasks. | 3 / 3 |
Completeness | Clearly answers both 'what' (implement SAFe methodology in Jira with hierarchy, acceptance criteria, and linking) and 'when' (explicit 'Use when creating Epics, Features, Stories with proper hierarchy, acceptance criteria, and parent-child linking'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'SAFe', 'Jira', 'Epics', 'Features', 'Stories', 'hierarchy', 'acceptance criteria', 'parent-child linking'. These are terms practitioners naturally use when working with SAFe in Jira. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of SAFe methodology + Jira + specific artifact types (Epics, Features, Stories) creates a very clear niche. Unlikely to conflict with generic project management or coding skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with complete, executable code examples covering the full SAFe hierarchy in Jira, but it is severely bloated. The ADF JSON templates alone consume enormous token budget and are repeated across multiple examples. Content is poorly organized as a single monolithic file with redundant Next-Gen vs Classic comparisons appearing in multiple sections, and destructive operations like bulk delete lack validation safeguards.
Suggestions
Extract the verbose ADF JSON templates into a separate reference file (e.g., ADF_TEMPLATES.md) and keep only a concise helper function or summary in SKILL.md.
Consolidate the Next-Gen vs Classic comparison into a single authoritative table instead of repeating it across 3+ sections.
Add a confirmation/dry-run step to the bulk delete function, and add a validation checkpoint after epic creation before creating child stories.
Remove explanations Claude already knows (e.g., INVEST criteria definitions, what SAFe hierarchy means) and keep only the Jira-specific implementation details.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines. The ADF (Atlassian Document Format) JSON templates are massively bloated and could be abstracted into a helper function or referenced file. The Next-Gen vs Classic comparison tables are repeated multiple times with overlapping information. Claude already understands REST APIs, JSON structures, and basic JavaScript patterns. | 1 / 3 |
Actionability | The skill provides fully executable JavaScript code for every operation: creating epics, stories, subtasks, bulk deletion, and error handling. The API calls are copy-paste ready with proper headers, authentication, and response handling. The ADF templates are complete and valid. | 3 / 3 |
Workflow Clarity | The create functions show a clear sequence (create epic → create stories → create subtasks) with error handling and rate limiting. However, there are no validation checkpoints — for example, no step to verify the created epic exists before creating child stories, and the bulk delete function has no confirmation or dry-run step despite being a destructive operation. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of content with no bundle files to offload detail. The massive ADF JSON templates, the repeated Classic vs Next-Gen comparison tables, and the full API implementation code should be split into separate reference files. Everything is inline with no layered structure. | 1 / 3 |
Total | 7 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- NeverSight/skills_feed
- Commit
aa009ea
- 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.