CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

build-champ-triage

Find out why a build has failed

54

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/build-champ-triage/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

The body is a well-structured, concise triage workflow with a clear sequence and good organization; its main weakness is that the investigative steps stay high-level without concrete commands for querying builds and PRs.

Suggestions

Add concrete commands or API patterns for finding the last successful build and listing PRs in a commit range (e.g., gh CLI / Azure DevOps REST calls).

Insert an explicit verification checkpoint (e.g., 'Confirm the successful-build and first-failing-build are on the same branch before bisecting') to harden the workflow against the agent's known mis-numbering issue.

Tighten the Warning Message so it doubles as a validation checklist the workflow references, rather than a separate caveat block.

DimensionReasoningScore

Conciseness

The body is lean and task-focused with clear sections; only the embedded warning box and a few restated guidelines (e.g., "Be minimal in your output, focusing on clarity and conciseness") could be trimmed, fitting the efficient-with-minor-overexplanation anchor.

4 / 5

Actionability

It gives a concrete output format ("GitHub Compare View <commit1>...<commit2>", listed URLs) but the investigation steps ("Investigate the failing jobs", "identify all PRs") lack specific commands or API calls for locating builds and PRs, matching the incomplete-guidance anchor.

3 / 5

Workflow Clarity

Steps 1–7 are clearly numbered and sequenced with prioritization and a fallback (step 7), and the task is investigative rather than destructive/batch so the cap-3 rule does not apply; only minor validation checkpoints are implicit, fitting the clear-sequence-with-minor-gaps anchor.

4 / 5

Progressive Disclosure

At under 50 lines with no need for external references and well-organized sections (Role, Instructions, Variables, Guidelines, Warning Message, Known Scenarios), the skill meets the simple-skill exception that allows a 5 on well-organized structure alone.

5 / 5

Total

16

/

20

Passed

Description

48%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 a terse, third-person-voiced statement of the skill's purpose but lacks trigger guidance and concrete capability detail, leaving it mid-range across dimensions.

Suggestions

Add an explicit 'Use when…' clause naming trigger phrases (e.g., 'Use when a CI build fails, tests fail, or the user asks why a build broke').

Expand the action list to concrete capabilities (e.g., 'investigates failing jobs, bisects builds to find the first failure, identifies merged PRs that caused the break').

Include natural synonyms users say — CI, pipeline, tests failing, broken build — to improve trigger coverage.

DimensionReasoningScore

Specificity

The phrase "Find out why a build has failed" names the domain (build failures) but offers only a single, generic action with no concrete techniques, matching the anchor for minimal/generic actions rather than the 1-2 concrete actions required for a 3.

2 / 5

Completeness

It clearly states what the skill does (triage a failed build) but provides no "Use when…" trigger guidance; per the rubric, a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

"build" and "failed" are natural terms a user might say, but common synonyms and variations (CI, pipeline, tests failing, broken build) are absent, fitting the anchor for some relevant keywords missing common variations.

3 / 5

Distinctiveness Conflict Risk

Build-failure triage is a distinct niche with minimal conflict risk, though it has minor overlap with general debugging skills, matching the "mostly distinct; minor overlap risk" anchor rather than the fully distinctive 5.

4 / 5

Total

12

/

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

microsoft/vscode

Path

.github/skills/build-champ-triage/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.