CtrlK
BlogDocsLog inGet started
Tessl Logo

efficiency-conversion-loop

Run the end-to-end loop for landing a legacy Fenix UI test converted onto the ui/efficiency framework: convert → file a Bugzilla bug → commit with the real bug number → track in Jira (conversion vs. enablement) → open a moz-phab review. Use this when a conversion is written and needs to become a filed bug, a properly-numbered commit, Jira tracking, and a submitted revision — i.e. the "paperwork + submit" workflow around a ui/efficiency conversion, not the test authoring itself (that's the efficiency-test-authoring skill). Also covers keeping the tracker/dashboards in sync after landing.

68

Quality

81%

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

70%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.

A dense, actionable, well-sequenced workflow document with strong validation checkpoints and error-recovery guidance. Its main weaknesses are anecdotal/time-sensitive padding that hurts conciseness, and a monolithic single-file structure with no progressive disclosure into separate reference materials.

Suggestions

Move the anecdotal date example ('on 2026-08-19 …') and the 'three of six were wrong' war story into a separate 'Lessons learned / past incidents' reference file, or trim to a one-line justification, to tighten the main flow.

Split the per-step detail (JSON schemas, jiratool command reference, @Converted annotation spec) into reference files under references/ and keep SKILL.md as a sequenced overview that links out one level deep.

Extract the project-specific IDs table and per-team customization notes into a dedicated config/reference file so the core loop reads as a general procedure rather than a Fenix-specific monolith.

DimensionReasoningScore

Conciseness

Mostly efficient and free of generic concept explanation, but carries anecdotal padding ('three of six were wrong in one sitting this way') and a time-sensitive inline date ('on 2026-08-19 everything needed was already landed…') that is not placed in a deprecated/old-patterns section.

3 / 5

Actionability

Provides concrete, mostly copy-paste-ready guidance — JSON request blocks, exact `python3 jiratool.py create …` and `moz-phab submit …` commands, and the `@Converted` annotation template — with only minor parameterized placeholders (NNNNN, <batch>) as gaps.

4 / 5

Workflow Clarity

A clearly sequenced five-step loop with explicit validation checkpoints (parity audit before filing, 'Check the TestRail ids before you file', green-verdict gate) and feedback loops for error recovery (correcting comment 0, backfilling blocks, re-submitting a rebased stack).

5 / 5

Progressive Disclosure

Well-organized into clear sections with one-level-deep references to external repos/files (tae-conversion/README.md, reconcile_conversion.py), but no bundle files exist and the bulk of the detailed guidance is inlined in a single long SKILL.md rather than split into reference files.

3 / 5

Total

15

/

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, specific description that clearly states the workflow, gives an explicit Use-when trigger, and distinguishes itself from a sibling skill. Third-person voice is used throughout. Trigger vocabulary is domain-specific, which is appropriate but leaves little room for synonyms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions in sequence — 'convert → file a Bugzilla bug → commit with the real bug number → track in Jira → open a moz-phab review' — giving comprehensive coverage of the workflow.

5 / 5

Completeness

Explicitly answers what (the five-step loop) and when ('Use this when a conversion is written and needs to become a filed bug…') with concrete trigger phrasing.

5 / 5

Trigger Term Quality

Natural action phrases ('file a bug', 'commit with the real bug number', 'Jira tracking', 'submitted revision') are present, but the vocabulary is niche jargon with few synonyms or extensions a general user would say.

4 / 5

Distinctiveness Conflict Risk

A narrow, well-defined niche (Fenix ui/efficiency conversion paperwork) that even names the sibling skill it is NOT ('not the test authoring itself — that's the efficiency-test-authoring skill'), minimizing conflict risk.

5 / 5

Total

19

/

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
mozilla/firefox-aidev-plugins
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.