CtrlK
BlogDocsLog inGet started
Tessl Logo

find-regression-risk

Detects potential regression risks in a PR by cross-referencing lines the PR REMOVES against lines ADDED by recent labeled bug-fix PRs (`i/regression`, `t/bug`, `p/0`, `p/1`) touching the same files. Purely mechanical — no AI/LLM. Emits a CLEAN / OVERLAP / REVERT verdict plus structured findings. Triggers on: "does this PR revert a previous fix", "check PR for regression risk", "find regression risks in PR", "is this change reverting a bug fix". Do NOT use for: assessing ship-readiness of a release branch (use release-readiness), investigating CI failures (use azdo-build-investigator), or general code review (use code-review).

77

Quality

96%

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

93%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 tight, actionable skill body with executable commands, a clear algorithm, and clean sectioning. The only gap is the absence of an explicit error-recovery loop for the invocation workflow, which keeps workflow_clarity at 4.

Suggestions

Add a short error-recovery note for the standalone invocation (e.g., what to do when `gh` is unauthenticated or no recent labeled PRs are found), which would raise workflow_clarity to 5.

Consider noting how to interpret an empty `risks.json` or a non-CLEAN verdict in the Outputs section so downstream agents know the expected post-invocation action.

DimensionReasoningScore

Conciseness

Lean reference doc that assumes Claude's competence — no over-explanation of git/PR/label concepts, an efficient parameters table, and a useful Known Limitations section; every section earns its place.

5 / 5

Actionability

Fully copy-paste-ready PowerShell invocations with real parameter names, paths, and a real PR number, plus concrete output file listings and an executable test command covering the common cases.

5 / 5

Workflow Clarity

The five-step algorithm and standalone single-command invocation are clearly sequenced, and verification exists via verdict classification and the test suite, but there is no explicit error-recovery/feedback loop for tool failures (e.g., gh auth or missing PR).

4 / 5

Progressive Disclosure

A single self-contained, well-organized file with clear section headers and only one-level-deep external repo paths; no nested references and no need for bundle files, so the simple-skill organization exception applies.

5 / 5

Total

19

/

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.

An exemplary description: concrete, third-person, with explicit trigger phrases and proactive disambiguation from related skills. It answers what, when, and when-not without padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — cross-referencing removed vs added lines, label filtering (`i/regression`, `t/bug`, `p/0`, `p/1`), and emitting a CLEAN/OVERLAP/REVERT verdict plus structured findings — giving comprehensive coverage with no real gaps.

5 / 5

Completeness

Clearly answers both 'what' (detects regression risks via line cross-referencing and emits a verdict + findings) and 'when' (explicit Triggers on phrases plus Do NOT use for negative guidance) with concrete trigger phrases.

5 / 5

Trigger Term Quality

Provides explicit `Triggers on:` phrases a user would naturally say ('does this PR revert a previous fix', 'check PR for regression risk', 'find regression risks in PR', 'is this change reverting a bug fix') with synonyms (revert/regression/reverting a bug fix).

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche and actively disambiguates from named sibling skills ('use release-readiness', 'use azdo-build-investigator', 'use code-review'), minimizing conflict risk.

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
dotnet/maui
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.