CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ov-agentic-workflows

Author, edit, compile, validate, and debug any OpenVINO gh-aw agentic workflow (e.g. ci-doctor, ci-doctor-mq, and any future ones) and their shared safe-output jobs under .github/workflows/shared/agentic-workflows. Use when a user wants to create a new agentic workflow; change an existing one's prompt, triggers, tools, permissions, or safe-outputs; add or edit a shared job/step; recompile a .lock.yml; update a workflow's persisted-state JSON schemas; or test a workflow via workflow_dispatch. Do NOT use for regular (non-agentic) GitHub Actions workflows, plugin/runtime code, or diagnosing a specific live CI failure.

Quality

86%

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

75%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.

An actionable, well-structured skill with concrete commands, explicit validation checkpoints, and clean one-level references to authoritative docs. Its main weakness is verbosity: the detailed known-workflow pitfalls contradict the skill's own keep-it-a-short-checklist guidance and could largely move to the referenced documentation.

Suggestions

Trim the 'Known pitfalls from existing workflows' entries to one-line summaries that link to the relevant section of docs/dev/ci/github_actions/agentic_workflows.md, keeping only the general pitfalls inline — the body currently duplicates doc-level detail its own 'Keep it concise' rule warns against.

Add explicit error-recovery feedback loops to the common-task workflows (e.g. 'if schema validation fails, fix the artifact and re-validate before proceeding') to match the validation-checkpoint pattern the rubric's top workflow-clarity anchor expects.

State concrete pass criteria for the finishing checklist (e.g. the exact gh aw version-match check or the CI recompile-diff expectation as a verifiable command) so each pitfall item is checked rather than re-read.

DimensionReasoningScore

Conciseness

Everything is repo-specific with no filler explanations, but at ~200 lines the body inlines substantial doc-level detail (the multi-paragraph rerun-strings and compiler-drift pitfalls) that its own 'Keep it concise' rule says should live in the linked doc — matching 'mostly efficient but could be tightened' better than 'minor instances of over-explanation'.

3 / 5

Actionability

Guidance is copy-paste ready: exact commands ('gh aw compile', the python3 jsonschema validation one-liner, 'gh release view --repo github/gh-aw --json tagName --jq .tagName', pinned gh-aw install), precise file paths, and per-task numbered steps cover the common cases for an instruction-only skill.

5 / 5

Workflow Clarity

Each common task has a clear numbered sequence with explicit validation checkpoints ('Validate a sample artifact against the schema', 'Verify both versions match') and a closing 'Pitfalls to check before finishing' checklist, but explicit error-recovery feedback loops (e.g. 'if validation fails, fix and re-validate') are only implicit, so it falls short of the top anchor.

4 / 5

Progressive Disclosure

Well-organized sections with clearly signaled one-level-deep references to docs/dev/ci/github_actions/agentic_workflows.md and the gh-aw documentation, and an explicit preference for linking over duplicating. The minor gap is that the long inline known-pitfalls detail is itself content that could be split out into the referenced doc.

4 / 5

Total

16

/

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, highly specific description with explicit positive and negative trigger guidance and concrete named artifacts, file paths, and operations. The only weakness is slightly incomplete coverage of natural user phrasings beyond the canonical ci-doctor/gh-aw vocabulary.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Author, edit, compile, validate, and debug', 'recompile a .lock.yml', 'update a workflow's persisted-state JSON schemas', 'test a workflow via workflow_dispatch' — with named artifacts and locations, matching the comprehensive-coverage anchor rather than the 'minor gaps' level below it.

5 / 5

Completeness

It explicitly answers both 'what' (author/edit/compile/validate/debug agentic workflows and their shared safe-output jobs) and 'when' via a concrete 'Use when a user wants to...' clause enumerating six trigger scenarios, plus a 'Do NOT use for...' exclusion.

5 / 5

Trigger Term Quality

Good natural-term coverage including 'agentic workflow', 'ci-doctor', 'ci-doctor-mq', 'gh-aw', '.lock.yml', 'safe-outputs', and 'workflow_dispatch', but a few plausible user phrasings (e.g. CI investigator/bot, remediation) are absent, fitting the 'good coverage, a few natural terms missing' anchor rather than the comprehensive one.

4 / 5

Distinctiveness Conflict Risk

The negative boundary ('Do NOT use for regular (non-agentic) GitHub Actions workflows, plugin/runtime code, or diagnosing a specific live CI failure') carves out a clear niche with distinct triggers and minimal conflict risk.

5 / 5

Total

19

/

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: 4 suspicious

Warning

Total

15

/

16

Passed

Repository

openvinotoolkit/openvino

Path

.claude/skills/ov-agentic-workflows/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.