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.

70

Quality

85%

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

78%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, well-organized diagnostic skill body with clear structure and good progressive disclosure. Its main weakness is actionability: it gives a process framework rather than executable commands or concrete examples, leaving key execution details to the reference.

Suggestions

Add 1–2 concrete commands per common failure class (e.g. `circleci config validate`, `circleci tests run --rerun-failed`, log-grep patterns) so the body is executable without always consulting the reference.

Tighten the Validate step by replacing 'when possible' with a concrete default check and an explicit feedback loop (if validation fails → revise fix → re-validate → only then rerun).

Include one short worked example (a sample failing log line → classified type → minimal fix) to anchor the abstract workflow in a concrete case.

DimensionReasoningScore

Conciseness

Lean and efficient: it assumes Claude's knowledge of CircleCI, avoids explaining concepts or libraries, and every section (inputs, workflow, guardrails, output contract) earns its place.

5 / 5

Actionability

Concrete guidance is present (a five-step workflow and explicit failure-class categories), but it stops short of executable specifics — no commands (e.g. `circleci config validate`, `circleci tests run`), example log signatures, or fix patterns, and 'Run highest-signal local checks when possible' hedges the key action.

3 / 5

Workflow Clarity

A clearly sequenced five-step process with an explicit 'Validate' step and a 'Report residual risk' close, but it lacks an explicit fail→fix→re-validate feedback loop, so it is not a 5.

4 / 5

Progressive Disclosure

Concise overview with well-signaled one-level-deep references ('Read references/transient-vs-deterministic.md when…', 'Read ../config/references/test-results-and-splitting.md when…'); the referenced file exists and content is appropriately split.

5 / 5

Total

17

/

20

Passed

Description

92%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.

A strong, well-structured description that clearly states capability and trigger conditions with concrete, natural language. The only gap is slightly thinner coverage of synonyms and file-extension triggers.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across the domain — 'Diagnose and fix failing CircleCI builds', 'investigate failed CircleCI jobs', 'triage flaky pipelines', 'identify root causes from logs', 'implement minimal fixes in configuration, test setup, or build-related code paths' — giving comprehensive coverage from investigation to fix.

5 / 5

Completeness

Explicitly answers both what ('Diagnose and fix failing CircleCI builds quickly and safely') and when ('Use when users ask to investigate failed CircleCI jobs, triage flaky pipelines, identify root causes from logs, and implement minimal fixes…') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural user-facing terms like 'failed CircleCI jobs', 'flaky pipelines', and 'root causes from logs' are present and strong, but common synonyms/extensions such as 'CI', 'workflows', or '.circleci/config.yml' are missing, so it falls short of comprehensive.

4 / 5

Distinctiveness Conflict Risk

Targets a clear CircleCI-specific niche with distinct triggers ('failed CircleCI jobs', 'flaky pipelines') and minimal overlap risk with other skills.

5 / 5

Total

19

/

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
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.