CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ov-github-actions-ci

Author, edit, debug, and review the OpenVINO GitHub Actions CI infrastructure — regular (non-agentic) workflows under .github/workflows, reusable job_*.yml workflows, custom composite actions under .github/actions, CI helper scripts under .github/scripts, Dockerfiles under .github/dockerfiles, and the Smart CI / labeler / components configuration. Use when a user wants to add or change a build/test job or step, create or modify a reusable workflow, write or fix a custom action, adjust runners/containers/caches, wire up Smart CI for a component, pin action versions, fix workflow permissions/security, or debug a failing CI workflow's YAML. Do NOT use for gh-aw agentic workflows (*.md with gh-aw frontmatter — use ov-agentic-workflows), for diagnosing a specific product/test failure's root cause in C++/Python code, or for non-CI GitHub configuration.

Quality

96%

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

92%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 dense, high-signal checklist: executable YAML/bash snippets, exact expressions and paths, numbered task procedures, an explicit validation checklist, and a pitfalls list — all repo-specific rather than generic GitHub Actions tutorial content. Its only weakness is mild length, with a few explanatory asides that could be trimmed.

Suggestions

Trim explanatory sentences that restate the rule they follow (e.g. "This makes installs reproducible and pinned. Regenerate the same way whenever deps change." and "When in doubt, prefer Python and keep API interaction minimal.") to tighten the conciseness dimension.

The closing "Skill self-improvement" symlink note about .agents/skills/ vs .claude/skills/ is maintainer meta-commentary rather than task guidance; consider moving it to the repo docs or shortening it to one line.

A few Key Conventions entries (e.g. the full sccache env-var list) duplicate what caches.md already documents; linking instead of restating would shorten the body without losing actionability.

DimensionReasoningScore

Conciseness

Almost everything is repo-specific knowledge Claude cannot know (aks-* pools, the ACR mirror, sccache env vars, Smart CI gating syntax) and framework syntax is delegated to official docs, so there is no generic-concept padding. A few trimmable asides remain ("This makes installs reproducible and pinned", "When in doubt, prefer Python...", the closing symlink note) in a 205-line body, which fits the 4 anchor ("minor instances of over-explanation") better than the 5 anchor's "every token earns its place".

4 / 5

Actionability

Guidance is copy-paste executable throughout: "uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2", "if: fromJSON(needs.smart_ci.outputs.affected_components).<COMPONENT>.{build,test}", the pip-freeze venv block, "actionlint .github/workflows/<file>.yml", and exact env var/path/input names. This matches the 5 anchor (specific examples cover the common cases); it is not 4 because no common task lacks concrete syntax.

5 / 5

Workflow Clarity

Multi-step tasks are explicitly numbered (e.g. "Wire up Smart CI" steps 1-4, "Add / edit a reusable workflow" steps 1-3) and a dedicated "Validation before finishing" checklist provides explicit checkpoints (actionlint with a YAML-parse fallback, pinning, permissions, Smart CI gating, change scope), with a Pitfalls section for error recovery. This matches the 5 anchor; it is above 4 because validation checkpoints are present rather than merely implied.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), and the body correctly positions itself as "a checklist on top of" the repo docs: a topic-indexed table of doc links plus per-task pointers ("Follow adding_tests.md", "Pick the pool from runners.md") that are one level deep and clearly signaled. Detail is split out rather than inlined, matching the 5 anchor (clear overview, well-signaled one-level references, easy navigation).

5 / 5

Total

19

/

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.

The description is a model example: third-person, concrete verb list, full artifact scope, an explicit "Use when" clause with natural trigger phrases, and explicit exclusions that separate it from the sibling agentic-workflows skill and product-code debugging. All four dimensions sit at the top anchor.

DimensionReasoningScore

Specificity

"Author, edit, debug, and review" plus an enumerated task list ("add or change a build/test job or step, create or modify a reusable workflow, write or fix a custom action, adjust runners/containers/caches, ... pin action versions, fix workflow permissions/security, or debug a failing CI workflow's YAML") names multiple concrete actions covering the whole domain. It matches the 5 anchor (comprehensive coverage) rather than 4, since no significant task category is missing.

5 / 5

Completeness

Both halves are explicit: the "what" ("Author, edit, debug, and review the OpenVINO GitHub Actions CI infrastructure" with the full artifact inventory) and a concrete "Use when a user wants to..." trigger list, further sharpened by a "Do NOT use for..." exclusion clause. This clearly matches the 5 anchor with concrete trigger phrases, not the 4 anchor's "'when' could be more explicit".

5 / 5

Trigger Term Quality

Natural user phrasing is comprehensive: "CI", "GitHub Actions", "workflow", "job", "step", "custom action", "runners/containers/caches", "failing CI workflow's YAML", plus file patterns like ".github/workflows" and "job_*.yml". Nothing a user would plausibly say when needing this skill is absent, so it fits the 5 anchor over 4 ("a few natural terms missing").

5 / 5

Distinctiveness Conflict Risk

A clear niche (this repo's GitHub Actions CI) with explicit boundary disambiguation: "Do NOT use for gh-aw agentic workflows ... use ov-agentic-workflows), for diagnosing a specific product/test failure's root cause in C++/Python code, or for non-CI GitHub configuration." Conflict risk is minimal, matching the 5 anchor.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 17 suspicious

Warning

Total

15

/

16

Passed

Repository

openvinotoolkit/openvino

Path

.claude/skills/ov-github-actions-ci/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.