CtrlK
BlogDocsLog inGet started
Tessl Logo

circleci-builds

Diagnose and fix failing CircleCI builds quickly and safely. Use when users ask to investigate failed CircleCI jobs, triage flaky pipelines, identify root causes from logs, and implement minimal fixes in configuration, test setup, or build-related code paths.

68

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and well-organized into clear sections with a sequenced workflow and offloaded reference material, but the guidance stays at a directive/abstract level without concrete commands or an explicit validate-retry feedback loop, and one of its two referenced files does not exist in the bundle.

Suggestions

Add concrete, executable commands to the Workflow (e.g., `circleci step logs`, `gh`/`git` checks, or specific log-grep patterns) so the steps move from directive guidance to copy-paste-ready actionability.

Make the Validate step an explicit feedback loop: 'If validation fails, return to step 2/3 and re-classify or re-patch; only report success once the rerun passes,' with a concrete re-run command.

Fix or remove the broken reference to ../config/references/test-results-and-splitting.md — either inline the needed guidance, point to a real bundled file, or note it as an external doc the user must supply.

DimensionReasoningScore

Conciseness

The ~50-line body is lean and well-sectioned (Overview, Inputs, Workflow, Guardrails, Output Contract) with no padding and no explanation of concepts Claude already knows, matching the level-3 'every token earns its place' anchor rather than the 'could be tightened' level-2 anchor.

3 / 3

Actionability

Guidance is directive rather than concrete — 'Apply the smallest viable fix,' 'Run highest-signal local checks when possible' — with no executable commands (e.g., `circleci`/`gh` CLI invocations or specific log-grep patterns); the classification taxonomy and Output Contract add some concrete structure, but it falls short of the copy-paste-ready level-3 anchor and above the purely-vague level-1 anchor.

2 / 3

Workflow Clarity

A clear 5-step sequence (Identify → Classify → Fix → Validate → Report) with a Validate step exists, but the validation checkpoint is soft ('when possible') and lacks an explicit validate→fix→retry feedback loop, so it sits at the level-2 'sequence present but checkpoints implicit' anchor rather than the explicit-error-recovery level-3 anchor.

2 / 3

Progressive Disclosure

The overview cleanly signals one-level-deep references with read-conditions ('Read references/transient-vs-deterministic.md...'), but the second referenced path '../config/references/test-results-and-splitting.md' is not a real bundle file — only references/transient-vs-deterministic.md exists — so navigation is partially broken, capping it below the clean level-3 anchor and above the monolithic level-1 anchor.

2 / 3

Total

9

/

12

Passed

Description

100%

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 specific, trigger-rich, complete, and distinctive: it states concrete actions, includes a clear 'Use when...' clause with natural user phrasing, and occupies a well-defined CircleCI niche. Voice is appropriately third-person/imperative, incurring no penalty.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Diagnose and fix failing CircleCI builds,' 'triage flaky pipelines,' 'identify root causes from logs,' 'implement minimal fixes in configuration, test setup, or build-related code paths' — matching the level-3 anchor of several specific concrete actions rather than just naming a domain.

3 / 3

Completeness

Explicitly answers both what ('Diagnose and fix failing CircleCI builds quickly and safely') and when via a 'Use when...' clause ('Use when users ask to investigate failed CircleCI jobs, triage flaky pipelines...'), satisfying the level-3 anchor; not capped at 2 because the trigger clause is present.

3 / 3

Trigger Term Quality

Natural terms a user would actually say are well covered — 'CircleCI builds,' 'failed CircleCI jobs,' 'flaky pipelines' — giving good coverage rather than the 'some relevant keywords missing common variations' of level 2.

3 / 3

Distinctiveness Conflict Risk

CircleCI is a specific platform niche with distinct triggers ('failed CircleCI jobs,' 'flaky pipelines'), making it unlikely to fire for the wrong skill; this is a clear niche rather than the 'could still overlap' level-2 anchor.

3 / 3

Total

12

/

12

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
openai/plugins
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.