CtrlK
BlogDocsLog inGet started
Tessl Logo

explore-feature

Use when a developer wants a release-gate test for a change before merge — e.g. "explore this feature", "add a release-gate test for my PR", "gate this branch", "cover the feature in PR

72

Quality

88%

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

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable body with clear gated sequencing and concrete commands, but slightly verbose in places and its cross-file references (test-plan-template.md, release-gate-contract.md) lack backing bundle files.

Suggestions

Provide the referenced bundle files (test-plan-template.md, release-gate-contract.md) under references/ so the signaled one-level-deep pointers actually resolve.

Tighten the Phase 1 skip-check prose and worktree/socat gotchas into a separate reference or a compact checklist to reduce token weight without dropping the executable commands.

DimensionReasoningScore

Conciseness

Dense and competence-assuming with no padding of known concepts, but the ~220-line body has discursive prose (Phase 1 skip-check rationale, piloting lessons, worktree/socat gotchas) that could be tightened without losing the load-bearing commands.

2 / 3

Actionability

Copy-paste-ready commands throughout — 'git merge-base origin/main HEAD', 'git show origin/main:version.txt', 'curl <baseUrl>/api/is-alive/ver', the socat 'docker run' bridge, 'npm run test:release-gate' — fully executable.

3 / 3

Workflow Clarity

Five numbered phases with two explicit pre-authoring gates ('Two gates here, before expensive authoring') and validation checkpoints (scope-gate yes/no, local-run stack check, confirm green), plus re-validate feedback loops.

3 / 3

Progressive Disclosure

Well-organized sections and signals to 'read test-plan-template.md' and 'release-gate-contract.md' and the writing-e2e-tests skill, but the references/, scripts/, and assets/ bundle dirs are empty so these one-level-deep pointers don't resolve to actual files.

2 / 3

Total

10

/

12

Passed

Description

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.

A strong description: explicit 'Use when' trigger, concrete multi-action capability list, natural quoted trigger phrases, and a distinct niche. Third-person voice is maintained throughout.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Reads a ticket + changed code, writes a happy-path test-plan.md (posted to Jira), and commits one staging-ready @release-gate Playwright test' — matching the multi-action anchor.

3 / 3

Completeness

Explicitly answers both what (reads ticket+code, writes plan, commits test, delegates) and when via the leading 'Use when a developer wants a release-gate test for a change before merge'.

3 / 3

Trigger Term Quality

Rich quoted natural triggers ('explore this feature', 'add a release-gate test for my PR', 'gate this branch', 'cover the feature in PR #7303') that a developer would plausibly say.

3 / 3

Distinctiveness Conflict Risk

Narrow niche — release-gate Playwright test gated to a change's own release, posted to Jira, delegating to writing-e2e-tests — with triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
comet-ml/opik
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.