chunk

Use CircleCI Chunk for AI-assisted CI/CD work through either the Chunk web UI or the chunk-cli. Trigger this skill when users ask to set up Chunk, troubleshoot or fix failing builds with Chunk, configure Chunk environments, schedule/proactively run Chunk tasks, or use chunk-cli commands such as init, validate, build-prompt, auth, sandbox, task, and skill install.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 well-structured, lean routing skill that cleanly dispatches to verified one-level-deep references with guardrails and a verification step. The main gaps are minor link duplication and the absence of an explicit error-recovery feedback loop.

Suggestions

Deduplicate the reference links: chunk-ui.md and chunk-cli.md appear in both Workflow step 3 and the Reference Map — keep them in one place to tighten conciseness.

Add one short inline example of a common chunk-cli command (e.g., `chunk validate` or `chunk task run --definition dev --prompt "..."`) so the body is actionable without forcing a reference load for the most frequent case.

Strengthen workflow_clarity with an explicit validate→fix→retry loop (e.g., after `chunk validate` fails, fix and re-run before proceeding) rather than relying on a single terminal verification step.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanations of CI/CD or CircleCI concepts), but the chunk-ui.md and chunk-cli.md links are repeated in both Workflow step 3 and the Reference Map, a minor redundancy that could be trimmed.	4 / 5
Actionability	Concrete routing criteria (UI vs CLI vs mixed) and context-gathering checklists are actionable, but the executable commands themselves live one level deep in the references rather than inline in the body.	4 / 5
Workflow Clarity	A clear four-step sequence (classify → gather context → execute → verify) with a verification checkpoint and safety guardrails, but it lacks an explicit validate→fix→retry feedback loop for the mutating CLI/sandbox operations it routes to.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview that points to two real one-level-deep references (references/chunk-ui.md, references/chunk-cli.md), clearly signaled via the Reference Map, with no nested-reference chaining.	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, third-person description that clearly states the skill's purpose and provides explicit, concrete trigger guidance spanning both UI and CLI paths. Trigger-term coverage is good but could add a few natural synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across both paths — "set up Chunk", "troubleshoot or fix failing builds", "configure Chunk environments", "schedule/proactively run Chunk tasks" — plus named chunk-cli command families (init, validate, build-prompt, auth, sandbox, task, skill install), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers what ("Use CircleCI Chunk for AI-assisted CI/CD work through either the Chunk web UI or the chunk-cli") and when ("Trigger this skill when users ask to…") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ("set up Chunk", "fix failing builds", "configure Chunk environments", "run Chunk tasks") and concrete command names, but lacks common synonyms/variants a user might phrase differently.	4 / 5
Distinctiveness Conflict Risk	Tied to a specific named product ("CircleCI Chunk", "chunk-cli") with distinct triggers, so overlap with unrelated skills is minimal.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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: openai/plugins
Path: plugins/circleci/skills/chunk/SKILL.md
Commit: 1e28582

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.