CtrlK
BlogDocsLog inGet started
Tessl Logo

breaking-changes

Audit pull requests for breaking changes in the C# MCP SDK. Examines PR descriptions, review comments, and diffs to identify API and behavioral breaking changes, then reconciles labels with user confirmation. Use when asked to audit breaking changes, check for breaking changes, or review a set of PRs for breaking impact.

75

Quality

93%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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-organized, token-efficient workflow document that splits detail appropriately into one referenced file and gates its only destructive operation (label changes) behind user confirmation. The main weakness is vague GitHub-API invocation guidance and the absence of an explicit error-recovery loop in the analysis step.

Suggestions

Replace 'Use the GitHub API to get the full list of PRs merged within the specified range' with a concrete command or endpoint example (e.g. a `gh pr list --state merged --search ...` invocation) so the retrieval step is fully executable.

Add a brief validation/retry checkpoint in Step 1 or 2 (e.g. re-confirm a borderline classification against references/classification.md before presenting it) to introduce an explicit error-recovery feedback loop into the analysis pass.

In Step 3, note what to do if the user is unsure or declines to confirm a label change, so the reconciliation flow has a defined terminal state rather than an implicit abort.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it never explains what a PR or breaking change is conceptually, and every section (Input, Process steps, Output) earns its place with no padding, matching the 'every token earns its place' anchor.

5 / 5

Actionability

Concrete commit-range formats with examples, explicit classification categories, impact dimensions, and a spelled-out reconciliation flow give mostly actionable guidance; the gap is that GitHub API access is stated only as 'Use the GitHub API' with no specific endpoint or gh command, leaving a minor execution detail to Claude.

4 / 5

Workflow Clarity

Four clearly sequenced steps with an interactive user-confirmation checkpoint governing the destructive label add/remove operations and an input-validation prompt when no range is given; falls short of a 5 because there is no explicit error-recovery or re-validation loop for the analysis pass itself.

4 / 5

Progressive Disclosure

The body is a clear overview that defers the detailed classification guide to a single one-level-deep, well-signaled reference (references/classification.md, verified to exist) with an inline link and a description of what it contains, matching the clear-overview anchor.

5 / 5

Total

18

/

20

Passed

Description

100%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.

The description is concise yet comprehensive: it names the domain, lists several concrete actions, provides explicit natural-language triggers with synonyms, and occupies a clearly distinct niche. It hits every anchor for the top score across all dimensions.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Audit pull requests', 'Examines PR descriptions, review comments, and diffs', 'identify API and behavioral breaking changes', 'reconciles labels with user confirmation' — covering the workflow comprehensively, matching the anchor for multiple specific concrete actions.

5 / 5

Completeness

Explicitly answers both 'what' (audit/examine/identify/reconcile) and 'when' (concrete 'Use when...' trigger clause), matching the anchor for clearly answering both with concrete trigger phrases.

5 / 5

Trigger Term Quality

'Use when asked to audit breaking changes, check for breaking changes, or review a set of PRs for breaking impact' provides natural user phrasings with synonyms (audit/check/review); these are exactly what a user would say when needing this skill.

5 / 5

Distinctiveness Conflict Risk

Scoped to 'breaking changes in the C# MCP SDK' with 'breaking-change' label reconciliation — a clear niche with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

20

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
modelcontextprotocol/csharp-sdk
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.