CtrlK
BlogDocsLog inGet started
Tessl Logo

ubuntu-review-new

Validates and reviews an Ubuntu package in the NEW queue, merge request, bug, or PPA for compliance with Ubuntu and Debian NEW rules before sponsoring or acceptance.

58

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./groups/ubuntu-engineering/skills/ubuntu-review-new/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 well-structured, concise review workflow with concrete commands and clear checkpoints, undermined by references to two check files that do not exist in the skill bundle.

Suggestions

Provide the missing bundle files source-new-checks.md and bin-new-checks.md (referenced in step 2) so the delegation actually resolves.

Add an explicit validate→fix→retry feedback loop around step 2 (e.g. re-run lintian/copyright checks after each fix) to raise workflow clarity.

Trim soft prose like "Be relentless and objective." to tighten conciseness toward 5.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude knows the listed tools, with only minor padding (e.g. "Be relentless and objective"); not quite the every-token-earns-its-place level of 5.

4 / 5

Actionability

Concrete executable commands are given (pull-lp-source, dget, ./queue fetch, rmadison, wrap-and-sort) with clear delegation to reference files; minor gaps remain because the core checks live in referenced files.

4 / 5

Workflow Clarity

A clear numbered sequence (steps 0–4) with explicit per-step *Criterion:* checkpoints and a conditional PPA branch; falls short of 5 because error-recovery feedback loops are not spelled out.

4 / 5

Progressive Disclosure

Structure and one-level-deep signaled references ([source-new-checks.md], [bin-new-checks.md]) are good, but those referenced files are not present in the bundle, so navigation would fail.

3 / 5

Total

15

/

20

Passed

Description

65%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 specific, third-person description with a clear niche and good domain trigger terms, but it omits any explicit "Use when…" trigger guidance, which caps completeness.

Suggestions

Append a "Use when…" clause naming concrete trigger situations, e.g. "Use when reviewing a package in the Ubuntu NEW queue, sponsoring an upload, or checking a PPA/merge request/bug for NEW compliance."

Add a few natural synonyms users might say (e.g. "sponsor", "new package", "archive acceptance") to broaden trigger-term coverage toward 5.

DimensionReasoningScore

Specificity

"Validates and reviews" names two concrete actions against a well-specified domain (Ubuntu NEW queue, merge request, bug, PPA), but the action list is not comprehensive enough for a 4.

3 / 5

Completeness

The "what" is clear (validates/reviews for Ubuntu and Debian NEW compliance) but there is no "Use when…" clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Natural domain terms a contributor would say ("Ubuntu package", "NEW queue", "PPA", "sponsoring") are present with good coverage; a few common variations/synonyms are missing, so not a 5.

4 / 5

Distinctiveness Conflict Risk

A clear niche (Ubuntu/Debian NEW queue review) with distinct triggers and minimal overlap with other skills; well above the 4 anchor.

5 / 5

Total

15

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing

Warning

Total

15

/

16

Passed

Repository
canonical/copilot-collections
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.