CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

breaking-change-doc

Generate breaking change documentation for merged dotnet/runtime PRs. USE FOR: creating breaking change docs, "document this breaking change", "write breaking change issue for PR #NNNNN", processing PRs labeled needs-breaking-change-doc-created. DO NOT USE FOR: general code review (use code-review skill), bug fixes, API proposals (use api-proposal skill).

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/breaking-change-doc/SKILL.md
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 well-sequenced, highly actionable workflow with strong validation checkpoints and authorization gates, plus valuable non-obvious domain knowledge about .NET version detection. Its weaknesses are redundancy in the publication-authorization rules and a fully monolithic structure with no reference files despite ~390 lines of content.

Suggestions

Consolidate the publication-authorization rules currently restated in 'Trigger modes', 'Post the comment', and 'Draft-only mode' into a single authorization section that the other places reference, cutting significant repetition.

Split the area-label-to-feature-area mapping table and the Step 2 version-detection branch/tag logic into a references/ file (e.g., area-mapping.md and version-detection.md), keeping SKILL.md as a lean overview with well-signaled one-level-deep pointers.

Add the concrete gh search commands for Step 3's duplicate-issue check and Step 4's example-issue fetch so every step is copy-paste executable, and include one abbreviated example of a finished issue body.

DimensionReasoningScore

Conciseness

Mostly efficient and filled with genuinely non-obvious domain knowledge (release-branch cadence, tentative backport semantics, publication authorization), but the authorization rules are restated across 'Trigger modes', 'Post the comment', and 'Draft-only mode', and Step 2's detection rationale is dense enough to tighten. Fits anchor 3 ('could be tightened') rather than anchor 4 given the visible redundancy.

3 / 5

Actionability

Provides copy-paste-ready invocations (Get-VersionInfo.ps1, Build-IssueComment.ps1 with full argument examples) and concrete gh api commands with exact output field semantics. Minor gaps: Step 3's duplicate search and Step 4's example-issue fetch describe the operation without giving the command, and no example issue body is shown. Anchor 4 ('concrete code or commands with minor gaps'), not anchor 5.

4 / 5

Workflow Clarity

Steps 0-6 are clearly sequenced with explicit validation checkpoints: stop on an existing duplicate issue, report and fall back on an Error field in the version JSON, confirm tentative backports before relying on them, and require an area-* label or fail with a clear ask. The troubleshooting table adds error-recovery guidance, matching the anchor 5 pattern of explicit validation steps and feedback loops.

5 / 5

Progressive Disclosure

The bundle contains no references/, scripts/, or assets/ files; everything, including the 16-row area-label mapping table, the version-detection internals, and troubleshooting, is inline in one ~390-line SKILL.md. Section headers are good, but content that clearly belongs in separate reference files is inlined, matching anchor 3 rather than anchor 4's 'most content appropriately placed across files'.

3 / 5

Total

15

/

20

Passed

Description

82%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 with explicit what/when structure, natural quoted trigger phrases, an automation label trigger, and clear DO NOT USE FOR boundaries that disambiguate neighboring skills. The main gap is that it conveys only one core capability, leaving the filing destination (dotnet/docs issue) and PR-comment side effect unstated.

DimensionReasoningScore

Specificity

Names the domain ('breaking change documentation for merged dotnet/runtime PRs') and 1-2 concrete actions ('Generate breaking change documentation', 'write breaking change issue'), but the USE FOR items are trigger phrasings of one task rather than several distinct capabilities, and it omits that the doc is filed as an issue in dotnet/docs and that a PR comment is posted. This matches anchor 3 (domain plus 1-2 concrete actions, not comprehensive) rather than anchor 4, which requires several specific listed actions.

3 / 5

Completeness

Explicitly answers what ('Generate breaking change documentation for merged dotnet/runtime PRs') and when with concrete trigger phrases ('USE FOR: creating breaking change docs, "document this breaking change"...'), and adds DO NOT USE FOR boundaries. This is exactly the anchor 5 pattern of both what and when with concrete triggers.

5 / 5

Trigger Term Quality

Includes natural quoted phrases users would actually say ('document this breaking change', 'write breaking change issue for PR #NNNNN') plus the automation label 'needs-breaking-change-doc-created'. A few natural variants are missing (e.g., 'file a breaking change issue', 'document the change in PR #...'), so it is good-but-not-comprehensive coverage (anchor 4) rather than anchor 5's full synonym coverage.

4 / 5

Distinctiveness Conflict Risk

A clear niche (breaking change documentation for merged dotnet/runtime PRs) with explicit disambiguation that redirects general code review and API proposals to other skills, minimizing wrong-skill triggering.

5 / 5

Total

17

/

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

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

dotnet/runtime

Path

.github/skills/breaking-change-doc/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.