CtrlK
BlogDocsLog inGet started
Tessl Logo

1k-jira-qa-handoff

Generates a Chinese product-behavior summary + test cases from git commits and syncs them to the PM's Jira task issue (update or create), preserving any existing Slack URLs and prior context. Use after the PM commits/PRs code. Triggers on "同步 Jira / 写到 Jira / 给 QA 写测试用例 / PM 交付 / jira QA handoff / 创建 Jira issue / 更新 Jira"; or when the user supplies a Jira URL with "总结改动" / "写测试用例".

76

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 a well-sequenced, highly actionable workflow with explicit validation checkpoints and error-recovery loops for the destructive Jira write. It is token-efficient and assumes Claude's competence, with only minor redundancy in the preservation messaging across sections.

Suggestions

Consolidate the 'preserve existing context / append don't replace' rule: state it once in Hard rules and reference it from Path A and Anti-patterns rather than restating it three times.

Consider extracting the verbatim Chinese Output Template into a references/ file (e.g. template.md) and linking to it, which would let SKILL.md serve as a tighter overview and exercise one-level-deep progressive disclosure.

Tighten the Atlassian MCP notes by merging the 'Cloud ID gotcha' guidance into the auth step rather than presenting it as a separate recovery aside.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (bullet-driven hard rules, decision tables, copy-paste commands), but the preservation rule is restated across Hard rules, Path A step 3, and Anti-patterns — minor redundancy that could be consolidated. Not a 5 because not every token earns its place; not a 3 because it is mostly efficient with no generic-concept padding.

4 / 5

Actionability

Fully executable guidance: copy-paste git commands ('git log origin/x..HEAD --pretty=format:"%h %s" --no-merges'), a verbatim Chinese output template, a code-change-to-handoff decision table, and concrete MCP discovery steps covering the common update/create cases.

5 / 5

Workflow Clarity

A tickable 5-step checklist with an explicit confirmation gate (Step 3 preview → approve → write), clear Path A/B branching, and feedback loops for error recovery (cloudId gotcha, >10-commit scope-down). The destructive Jira-overwrite operation has strong validation (append-not-replace, replace only when empty, ask on type/conflict), so the destructive-cap does not apply.

5 / 5

Progressive Disclosure

A single self-contained file with well-organized sections (Hard rules, When to skip, Workflow, Output Template, MCP notes, Anti-patterns, Related skills) and clearly signaled peer-skill links. Not a 5 because there is no one-level-deep reference structure to exercise — everything is inlined — yet the content is appropriately placed with no monolithic-wall or buried-reference problems.

4 / 5

Total

18

/

20

Passed

Description

100%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 concrete, complete, and distinctive: it states multiple specific actions, provides comprehensive natural trigger phrases in both Chinese and English, and explicitly covers both what the skill does and when to use it. Voice is appropriately third person throughout.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Generates a Chinese product-behavior summary + test cases from git commits and syncs them to the PM's Jira task issue (update or create), preserving any existing Slack URLs and prior context' — covering generation, sync (update/create), and context preservation comprehensively.

5 / 5

Completeness

Explicitly answers both what (generate summary + test cases, sync to Jira, preserve context) and when ('Use after the PM commits/PRs code'; explicit 'Triggers on…' phrases), matching the anchor for clear what-and-when with concrete triggers.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage in both languages — '同步 Jira / 写到 Jira / 给 QA 写测试用例 / PM 交付 / jira QA handoff / 创建 Jira issue / 更新 Jira' plus '总结改动' / '写测试用例' — with synonyms a user would naturally say.

5 / 5

Distinctiveness Conflict Risk

A clear niche — Chinese product-behavior summary from git commits synced to a PM's task-type Jira issue for QA — with distinct bilingual triggers, giving minimal conflict risk with other skills.

5 / 5

Total

20

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
OneKeyHQ/app-monorepo
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.