CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

e2e

Story-to-e2e-test workflow that takes a Jira [QE] Story, discovers the project's e2e testing infrastructure, plans test scenarios, writes e2e tests matching project conventions, validates them, and manages review via GitHub PRs. Use when implementing [QE] stories produced by the design workflow. Activated by commands: /ingest, /plan, /revise, /code, /validate, /publish, /respond.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is e2e in flightctl/ai-workflows

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 an exemplar of lean orchestration: concise, unambiguous dispatch to command files and a controller, with an explicit stop-on-failure rule and clearly purpose-labeled references. Its weaknesses are minor — a slightly ambiguous default branch, and references whose target files cannot be verified in the provided bundle.

Suggestions

Clarify the default branch: instead of 'execute the first phase the user requests', state what to do when the user names no phase (e.g., default to /ingest and ask for a Jira issue key).

Enumerate the available commands in the body (or link a commands/ index) so the dispatch rule 'read commands/{command}.md' is actionable without relying on the description.

Include a one-line example of an accepted Jira issue key or URL format to make the /ingest dispatch condition concrete.

DimensionReasoningScore

Conciseness

The ~15-line body is pure dispatch logic plus a failure rule — 'If a step fails or produces unexpected output (e.g., Jira MCP errors, test failures, build errors), stop and report the error to the user' — with zero padding or explanation of concepts Claude already knows. Every token earns its place, matching the lean-and-efficient anchor.

5 / 5

Actionability

Guidance is concrete and executable for an instruction-only skill: exact file reads with explicit dispatch conditions ('If the user invoked a specific command (e.g., /plan, /code), read commands/{command}.md and follow it'). It falls short of fully executable because 'execute the first phase the user requests' is ambiguous when no phase was named, and the body gives no example of a Jira issue key or URL.

4 / 5

Workflow Clarity

The Quick Start lays out a clear dispatch sequence and includes an explicit stop-on-failure checkpoint with retry/escalation ('Do not advance to the next phase. Offer to retry the failed step or escalate'). It is not a 5 because the actual phase-by-phase sequencing and per-phase validation are deferred to skills/controller.md, which is not shown, so within the written body most checkpoints are present but the full sequence is implicit.

4 / 5

Progressive Disclosure

References are well-signaled, one level deep, and purpose-stated ('For principles, hard limits, safety, quality, and escalation rules, see guidelines.md'). Minor gaps keep it below a 5: 'commands/{command}.md' is a pattern rather than a listed file, the body never enumerates which commands exist (they appear only in the description), and no bundle files (references/, scripts/, assets/) are present to verify the referenced paths resolve.

4 / 5

Total

17

/

20

Passed

Description

92%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.

A strong description: it names a concrete, comprehensive pipeline in third person, gives an explicit 'Use when' clause tied to a specific upstream workflow, and adds command-level triggers. The only notable gap is the absence of natural synonyms such as 'end-to-end' that users might say instead of 'e2e'.

DimensionReasoningScore

Specificity

The description lists six concrete pipeline actions — 'takes a Jira [QE] Story, discovers the project's e2e testing infrastructure, plans test scenarios, writes e2e tests matching project conventions, validates them, and manages review via GitHub PRs' — giving comprehensive coverage of the workflow. It clearly matches the anchor for multiple specific concrete actions rather than the anchor 4 case of minor coverage gaps.

5 / 5

Completeness

Both questions are explicitly answered: the 'what' is the full story-to-PR pipeline, and the 'when' is concrete — 'Use when implementing [QE] stories produced by the design workflow' — reinforced by the activation command list. This matches the anchor for clearly and explicitly answering both with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural keyword coverage: 'e2e test', 'Jira [QE] Story', 'e2e testing infrastructure', 'GitHub PRs', plus explicit command triggers (/ingest, /plan, /code, /validate, /publish). It falls short of anchor 5 because common synonyms like 'end-to-end test' or tool names (Playwright, Cypress) are absent.

4 / 5

Distinctiveness Conflict Risk

The skill occupies a clear niche: Jira [QE] stories produced by a specific design workflow, with seven dedicated slash commands as triggers. Overlap risk with generic testing or code-review skills is minimal, matching the anchor for a distinct niche with minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

amir-yogev-gh/ai-workflows

Path

e2e/SKILL.md

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.