CtrlK
BlogDocsLog inGet started
Tessl Logo

1k-app-upgrade-test

Create test versions to verify app auto-update functionality and version migration.

48

Quality

53%

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-app-upgrade-test/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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 presents a clear, well-sequenced workflow and correctly delegates deep detail to a real reference file, but it is held back by systematic internal duplication and by the absence of any validation checkpoint for a batch operation that rewrites six CI/build config files and pushes a branch. Tightening the duplicated sections and surfacing (or at least pointing to) the validation checklist before the push step would lift most dimensions.

Suggestions

Add an explicit validation checkpoint before Step 5 (or reference the reference file's Validation Checklist), e.g., "Verify all six files updated and BUILD_NUMBER matches across workflows before pushing."

Remove the duplicated content: drop the "Files to Modify" table or Step 4's annotated list (keep one), and fold the Quick Reference formula into Step 2 instead of stating it twice.

Fix the "Related Skills" section, which lists "/1k-dev-commands" twice with different descriptions, and either distinguish the two intended skills or merge into one entry.

DimensionReasoningScore

Conciseness

The Quick Reference section repeats the build-number formula and version pattern that Steps 1-2 already state, the "Files to Modify" table restates Step 4's entire list, and "Related Skills" lists "/1k-dev-commands" twice. This is 'mostly efficient but could be tightened', not 4, because the duplication is systematic rather than a couple of trimmable phrases.

3 / 5

Actionability

Steps 2, 3, and 5 give executable bash, but Step 4 — the core task — offers only directives like "Set VERSION to test version", "Update version in outputs section", and "Update versionCode" with no exact edits in the body. This matches 'some concrete guidance but incomplete; missing key details'; it is not 4 because the body's central step lacks copy-paste-ready content (the exact edits live only in the reference file).

3 / 5

Workflow Clarity

The five steps are clearly sequenced, but this is a batch operation (modifying six configuration files and pushing a branch) with no validation or verification step anywhere in the body — the validation checklist exists only in the reference file. Per the judging guidelines, a batch workflow without validation is capped at 3; it stays at 3 rather than 2 because the sequence itself is well defined.

3 / 5

Progressive Disclosure

The body links one real, one-level-deep reference ([upgrade-test-version.md](references/rules/upgrade-test-version.md)) under a clearly signaled "Detailed Guide" heading with a topics-covered list, and sections are well organized. It falls short of 5 because the body substantially duplicates the reference's workflow (formula, file list, steps) instead of cleanly splitting overview from detail.

4 / 5

Total

13

/

20

Passed

Description

53%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 states a concrete, niche capability but reads as only a partial skill description: it answers 'what' clearly while entirely omitting 'when'. Adding an explicit 'Use when...' clause with natural trigger phrases (e.g., upgrade testing, test build, version migration QA) would materially raise both completeness and trigger-term quality.

Suggestions

Append a trigger clause such as "Use when creating test builds for QA upgrade testing, testing app auto-update or version migration flows, or preparing release candidates with specific build numbers."

Include natural user phrasings and synonyms ("upgrade test", "test build", "release candidate") so the skill triggers on how users actually describe this task.

Name one more concrete action (e.g., "calculate build numbers and create test version branches") to broaden capability coverage without adding vagueness.

DimensionReasoningScore

Specificity

"Create test versions" is one concrete action and the domain ("app auto-update functionality and version migration") is clearly named, matching the anchor for 1-2 concrete actions without comprehensive coverage. It is not a 4 because no further specific capabilities are listed, and not a 2 because the action and domain are concrete rather than generic.

3 / 5

Completeness

The description clearly answers 'what' ("Create test versions to verify app auto-update functionality and version migration") but contains no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is above 2 because the 'what' is specific and concrete.

3 / 5

Trigger Term Quality

"test versions", "auto-update", and "version migration" are relevant keywords a user might say, but common variations such as "upgrade testing", "test build", or "release candidate" are missing. This sits at 'some relevant keywords but missing common variations', below the 'good coverage, a few natural terms missing' anchor.

3 / 5

Distinctiveness Conflict Risk

Upgrade-test version creation is a clear niche with distinct terminology ("test versions", "version migration"), giving minimal conflict risk with unrelated skills. It falls short of 5 because without explicit trigger phrases it could still overlap with general versioning, release, or build-configuration skills.

4 / 5

Total

13

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

relative_links

Relative link issues: 1 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 1 deeper-than-1-level

Warning

Total

13

/

16

Passed

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.