CtrlK
BlogDocsLog inGet started
Tessl Logo

pr

Rules and checklist for preparing PRs, creating changesets, and releasing packages in the monorepo.

55

Quality

62%

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 ./.agents/skills/pr/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

A compact, well-organized skill with executable commands, but it names processes (changeset creation, release expectations) it never actually instructs on, and lacks an explicit validation loop for the PR workflow.

Suggestions

Show how to fill out a changeset and what semver bump to choose instead of only listing `pnpm changeset`, or push that detail into a referenced file.

Make the PR workflow an explicit ordered sequence with a validation checkpoint: run format/lint/typecheck/test, fix failures and re-run until green, then add the changeset.

Collapse the redundant intro line and "What It Does" section, or fold the checklist into the sequenced workflow to remove overlap.

DimensionReasoningScore

Conciseness

The body is lean and avoids explaining concepts Claude already knows, but the intro line, "What It Does", and the checklist overlap, so it could be tightened.

2 / 3

Actionability

Provides copy-paste commands (pnpm format, lint, typecheck, test, changeset) but never delivers the promised detail on filling out a changeset or on release/merge expectations, leaving key gaps.

2 / 3

Workflow Clarity

A checklist and the command-block order imply a sequence, but there is no explicit validation feedback loop (run checks → fix → re-run) for batch/release operations, which caps this at 2.

2 / 3

Progressive Disclosure

Under 50 lines with clearly organized sections and a single well-signaled one-level reference to ../changelog/SKILL.md, satisfying the simple-skill exception for a top score.

3 / 3

Total

9

/

12

Passed

Description

67%

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 specific and well-scoped to a distinct monorepo release niche, but it states capabilities without any explicit trigger guidance for when to invoke the skill.

Suggestions

Add an explicit 'Use when…' clause naming user-facing triggers (e.g., 'Use when preparing a pull request, creating a changeset, or releasing packages in the monorepo').

Broaden trigger-term coverage with natural variations such as 'pull request', 'version bump', 'publish', and 'changelog'.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "preparing PRs, creating changesets, and releasing packages" — matching the multi-action anchor rather than the partial-coverage anchor below.

3 / 3

Completeness

Clearly states what the skill does, but "when" guidance is absent with no "Use when…" clause or equivalent trigger, which caps completeness at 2 per the judging guidelines.

2 / 3

Trigger Term Quality

Includes natural terms a user would say ("PRs", "changesets", "releasing packages", "monorepo") but omits common variations like "pull request", "version bump", "publish", or "changelog", so coverage is incomplete.

2 / 3

Distinctiveness Conflict Risk

The monorepo changeset-based release workflow is a clear niche with distinctive triggers, making it unlikely to route to the wrong skill.

3 / 3

Total

10

/

12

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: 1 suspicious

Warning

Total

15

/

16

Passed

Repository
kubb-labs/kubb
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.