CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

azsdk-common-pipeline-fixer

Automatically fix Azure SDK CI/CD pipeline failures by applying code changes and verifying locally. USE FOR: "fix pipeline failure", "fix CI", "fix failing tests", "auto-fix and commit the fix", "fix build error", "fix mypy/pylint/type-check/lint errors", "auto-fix pipeline", "resolve pipeline failure". DO NOT USE FOR: pipeline analysis (instead use azsdk-common-pipeline-analysis), API design review, SDK publishing. INVOKES: azure-sdk-mcp:azsdk_package_build_code, azure-sdk-mcp:azsdk_package_run_check, azure-sdk-mcp:azsdk_package_run_tests, azure-sdk-mcp:azsdk_verify_setup.

75

Quality

94%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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, instruction-style skill with a well-sequenced fix-verify-iterate workflow, explicit validation gates, and exact tool identifiers. Its only weaknesses are mild redundancy (the 'never raw shell' rule and prerequisites stated multiple times) and the absence of a sample invocation or commit-message example.

Suggestions

State the 'never raw shell build/test commands' rule once (in Rules) and reference it from step 5 and Troubleshooting instead of repeating it verbatim three times.

Fold the Prerequisites section into the Rules bullet it duplicates, or vice versa, to remove the repetition.

Add one example commit message or a sample azsdk MCP tool invocation to step 6 / the MCP Tools section to make the fix-and-commit step copy-paste ready.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — no concept explanations, no padding — but the rule 'never raw shell build/test commands' appears three times (Rules, step 5, Troubleshooting) and the Prerequisites section restates the first Rule ('azure-sdk-mcp server required. Local clone of the affected SDK language repo'). This is efficient with minor instances that could be trimmed, matching anchor 4 rather than anchor 5's 'every token earns its place'.

4 / 5

Actionability

Concrete, executable guidance throughout: exact tool names with server prefix, an ordered verify sequence ('azsdk_package_build_code → azsdk_package_run_check → azsdk_package_run_tests'), a fix/retry classification taxonomy, and a max-3-attempt bound. It falls short of anchor 5's copy-paste-ready coverage because there is no sample MCP tool invocation or example commit message for step 6 — minor gaps consistent with anchor 4.

4 / 5

Workflow Clarity

Six clearly sequenced steps with an explicit validation checkpoint ('all must pass'), a feedback loop ('On failure, revise and re-verify (max 3 attempts)'), environment-readiness handling via azsdk_verify_setup, and escalation rules for infrastructure/API/credential cases. This matches the top anchor: clear sequence, explicit validation steps, and error-recovery loops.

5 / 5

Progressive Disclosure

The body is under 50 lines with no bundle files and no need for external references, so well-organized sections (Rules, Tools, Steps, Examples, Troubleshooting) suffice per the simple-skill guideline. The single cross-reference to azsdk-common-pipeline-analysis is clearly signaled and one level deep.

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.

An excellent description: concrete capabilities, exhaustive natural trigger phrases, explicit what/when, and explicit de-scoping boundaries that prevent mis-triggering against a sibling analysis skill. Voice is appropriately third-person/declarative.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'fix Azure SDK CI/CD pipeline failures by applying code changes and verifying locally' — and enumerates the exact MCP tools it invokes (build, run_check, run_tests, verify_setup), giving comprehensive coverage of the workflow. It names domain plus actions with no coverage gaps, matching the top anchor rather than the anchor-4 example which has 'minor gaps'.

5 / 5

Completeness

It explicitly answers what ('Automatically fix Azure SDK CI/CD pipeline failures by applying code changes and verifying locally') and when (a USE FOR clause with concrete quoted trigger phrases), matching the anchor-5 example structure. The anchor-4 case ('when' could be more explicit) does not apply since triggers are quoted verbatim.

5 / 5

Trigger Term Quality

USE FOR includes eight natural user phrases with synonyms and variations: 'fix pipeline failure', 'fix CI', 'fix failing tests', 'fix build error', 'fix mypy/pylint/type-check/lint errors', 'auto-fix pipeline', 'resolve pipeline failure', 'auto-fix and commit the fix'. Coverage is comprehensive; no common phrasing is missing.

5 / 5

Distinctiveness Conflict Risk

A clear Azure SDK CI/CD niche with distinct triggers, and the DO NOT USE FOR clause explicitly redirects overlapping requests ('pipeline analysis (instead use azsdk-common-pipeline-analysis)') plus API design review and SDK publishing. Conflict risk is minimal, fitting the top anchor rather than anchor 4's 'minor overlap 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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

Azure/azure-sdk-for-net

Path

.github/skills/azsdk-common-pipeline-fixer/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.