CtrlK
BlogDocsLog inGet started
Tessl Logo

1k-sentry

Configure OneKey Sentry and filter events across desktop, mobile, web, and extension.

56

Quality

64%

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-sentry/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 lean, well-organized project map: architecture tree, platform flags, key-file table, and a correctly wired one-level-deep reference for the filtering workflow. Main gaps are a generic Sentry API section Claude already knows, one placeholder snippet, and slight duplication between the inline quick reference and the reference file.

Suggestions

Trim or replace the 'Add Custom Context' section — standard Sentry API usage Claude already knows — with project-specific notes (e.g. which Sentry package/DSN each platform entry uses).

Remove the 'Error Filtering Quick Reference' section or reduce it to a pointer, since the same filter structures are fully documented in references/rules/ignoring-errors.md.

Replace the placeholder 'if (error.value?.includes(\'PATTERN\')) return true;' with a real example pattern from the codebase so the snippet is executable as written.

DimensionReasoningScore

Conciseness

The architecture tree, platform-detection flags, and key-files table are project-specific facts Claude cannot know, so those tokens earn their place; however the 'Add Custom Context' section demonstrates standard Sentry API calls (addBreadcrumb, setUser, setTag) that Claude already knows. This is 'Efficient; minor instances of over-explanation that could be trimmed', not 5.

4 / 5

Actionability

Real file paths, executable TypeScript snippets, and concrete filter structures (FILTERED_ERROR_TYPES Set, FILTER_ERROR_VALUES array) make the guidance mostly copy-paste ready. It falls short of 5 because the quick-reference snippet 'if (error.value?.includes('PATTERN')) return true;' is placeholder pseudocode rather than executable code.

4 / 5

Workflow Clarity

Each task section points to a concrete key file, and the primary workflow (filtering errors) is delegated to a reference containing a sequenced 1-2-3 workflow. The body's own filtering guidance is fragmentary quick-reference snippets without an explicit sequence, matching 'Clear sequence with most checkpoints present; minor validation gaps' rather than 5.

4 / 5

Progressive Disclosure

The single reference (references/rules/ignoring-errors.md) exists in the bundle, is clearly signaled with a markdown link, and is one level deep; the body is well-sectioned under clear headers. It is not 5 because the 'Error Filtering Quick Reference' section duplicates filtering detail that already lives in the reference file, so content placement could be tighter.

4 / 5

Total

16

/

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 is concise, product-specific, and names two concrete actions, but it omits any 'when to use' trigger guidance and lacks natural keyword variations like 'error tracking' or 'ignore errors'. It is serviceable but below the standard of the good examples, which pair a capability list with explicit trigger phrases.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when the user mentions Sentry, error tracking, crash reports, or wants to silence noisy errors in OneKey apps.'

Expand the capability list slightly to cover the skill's real breadth (e.g. adding breadcrumbs, tags, or user context), which would lift specificity from 2 actions to several.

Include natural synonyms users would actually say — 'error tracking', 'crash reports', 'ignore errors' — to improve trigger term coverage.

DimensionReasoningScore

Specificity

"Configure OneKey Sentry and filter events" names the domain plus exactly two concrete actions (configure, filter events) with no broader coverage of capabilities like breadcrumbs, tags, or user context. This matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' rather than 4, which requires several specific actions.

3 / 5

Completeness

The description gives a clear 'what' ("Configure OneKey Sentry and filter events") but contains no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 2 because the 'what' is concrete, not vague.

3 / 5

Trigger Term Quality

Keywords like "Sentry", "OneKey", and "filter events" are relevant, but common natural phrasings users would say — "error tracking", "crash reports", "ignore errors" — are missing. This sits at 'Some relevant keywords but missing common variations or synonyms', not 4, since more than a few natural terms are absent.

3 / 5

Distinctiveness Conflict Risk

"OneKey Sentry" is a product-specific niche unlikely to trigger the wrong skill, giving minor overlap risk only (anchor 4). It falls short of 5 because the description offers no distinct trigger phrases that would cleanly route user intent to it.

4 / 5

Total

13

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

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

Warning

referenced_paths_exist

Referenced path issues: 2 deeper-than-1-level

Warning

Total

14

/

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.