CtrlK
BlogDocsLog inGet started
Tessl Logo

1k-jira-qa-handoff

Generate Chinese product behavior and QA cases from commits, then sync them to a Jira issue while preserving existing context and Slack links.

60

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./.skillshare/skills/1k-jira-qa-handoff/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 highly actionable, well-sequenced workflow with concrete commands, a copy-ready output template, explicit gates before destructive writes, and real error-recovery paths. Its only real weakness is repetition — the context-preservation and confirmation-gate rules are each restated several times, which inflates token cost without adding guidance.

Suggestions

State the preservation/append rule once (Hard rules) and reference it from Step 4 and Anti-patterns instead of restating it three times.

Collapse the two overlapping Anti-patterns about preservation noise ("Overwriting an existing Jira description..." and "Removing Slack thread URLs...") into a single append-don't-strip entry.

Consider moving the full Output Template to a references/ file (with the title examples kept inline) so SKILL.md stays a lean overview.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence (no concept explanations, no library tutorials), but the Jira-preservation rule is stated three times — in Hard rules, again in Step 4 Path A ("Do not ask the user to re-confirm preservation..."), and twice more in Anti-patterns — which is more than minor padding. Fits the 'mostly efficient but could be tightened' anchor rather than the 'minor instances' anchor.

3 / 5

Actionability

Fully executable throughout: exact git commands per step (git fetch/log/diff/show), a verbatim copy-ready Chinese Output Template with real-style examples, a concrete URL-to-key parsing example, named MCP tools, and a literal ToolSearch query. Not below 5: the common cases (given URL, no URL, unauthenticated MCP, cloudId failure) all have specific instructions.

5 / 5

Workflow Clarity

Five-step checklist the agent copies and ticks off, an explicit approval gate before any Jira write ("Wait for approval or edits before any Jira write"), halt conditions for non-QA-visible changes, Path A/B branching with duplicate-issue prevention, and error-recovery loops (OAuth flow, cloudId gotcha with a retry path). Matches the top anchor with checkpoints, feedback loops, and a checklist; the destructive external write is explicitly gated.

5 / 5

Progressive Disclosure

Single-file skill with no bundle files; all sections are clearly headed and the inline content (template, commands, MCP notes) is core to execution rather than offloadable reference material. Not 5: the file is well over 50 lines and the Hard-rules/Anti-patterns overlap plus the long Output Template are minor organization gaps that tighter splitting or deduplication would address.

4 / 5

Total

17

/

20

Passed

Description

58%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 communicates a concrete, well-differentiated capability chain (commits → Chinese product behavior + QA cases → Jira with preserved context). Its main weaknesses are the complete absence of 'when to use' trigger guidance and thin natural-language keyword coverage, both of which hurt discoverability at invocation time.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to hand off shipped changes to QA, write test cases for a PR, or update a Jira issue after merging."

Add natural user-voice synonyms such as "test cases", "QA handoff", and "Jira ticket" alongside "QA cases" and "Jira issue".

Mention the post-merge moment explicitly (e.g. "after a PR merges") since that is when this skill naturally applies in the described team flow.

DimensionReasoningScore

Specificity

Lists several concrete chained actions — "Generate Chinese product behavior and QA cases from commits", "sync them to a Jira issue", "preserving existing context and Slack links" — matching the 'several specific actions; minor gaps' anchor. Not 5: it omits that it reads diffs directly and the create-vs-update-issue branching.

4 / 5

Completeness

The 'what' is clear (generate Chinese product behavior summary and QA cases, sync to Jira, preserve context), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because the 'when' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Contains relevant domain keywords ("commits", "QA cases", "Jira", "product behavior") but misses natural variations users would actually say such as "test cases", "handoff", or "release notes". Fits the 'some relevant keywords but missing common variations' anchor rather than the good-coverage anchor above.

3 / 5

Distinctiveness Conflict Risk

The niche is distinct — Chinese QA-case generation from commits synced to a PM's Jira task issue — with minimal overlap risk against generic Jira or commit-message skills. Not 5: no explicit trigger phrases, so it relies on keyword overlap ("Jira", "commits") that a broader Jira skill could also match.

4 / 5

Total

14

/

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
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.