prepare-providers-documentation

Replace the manual commit-by-commit classification step in `breeze release-management prepare-provider-documentation` with AI-driven classification. For each provider with pending changes, analyze every PR (batched into one sub-agent per provider, not one per PR), pay special attention to potentially breaking changes by inspecting the actual diff, scope multi-provider PRs to the current provider's slice, ask the release manager when uncertain, and apply version bumps + changelog entries. Use during the regular provider release cycle as an alternative to the interactive breeze prompts.

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

77%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 deeply actionable, well-sequenced workflow with strong validation and feedback loops for a risky batch operation. Its main weaknesses are monolithic inlining of template/checklist content that belongs in separate reference files and time-sensitive dated examples embedded in the main flow.

Suggestions

Move the breaking-change checklist, the sub-agent prompt template, and the RST changelog skeleton into separate reference files under references/ and link to them one level deep, keeping SKILL.md as an overview.

Relocate dated worked examples (e.g. the 2026-08-01 and 2026-07-22 wave incidents with specific PR numbers) into a dedicated 'Past incidents / known traps' section or reference file so time-sensitive detail does not pad the core workflow.

Trim repeated justifications (e.g. restating the released-only rule multiple times across Phases 3, 4b, and the incremental flow) by stating each rule once and cross-referencing it.

Dimension	Reasoning	Score
Conciseness	Mostly efficient domain-specific guidance, but the ~1086-line body is padded with inline dated worked examples ("2026-08-01 wave", "2026-07-22 wave", specific PR numbers) that are time-sensitive and not isolated in an old-patterns/deprecated section, plus repeated rationale that could be tightened.	3 / 5
Actionability	Fully executable throughout—copy-paste breeze/git/gh commands, an exact RST changelog skeleton, classification and escalation tables, and a precise per-commit output format cover the common cases concretely.	5 / 5
Workflow Clarity	Five sequenced phases (plus a parallel incremental flow) with explicit validation (Phase 5 prek/idempotency checks), feedback loops (re-run discovery after a version bump), and checklists (breaking-change checklist, entry-defect scan) for a destructive batch operation.	5 / 5
Progressive Disclosure	Sections are well-organized and codebase references are signaled at the end, but no bundle files exist and large self-contained blocks (the ~95-line sub-agent prompt, the breaking-change checklist, the RST skeleton) are inlined in SKILL.md rather than split into one-level-deep reference files.	3 / 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 precise, action-dense description with an explicit use-when clause and minimal conflict risk. Its only weakness is trigger-term naturalness, which leans on internal tooling jargon rather than the plain phrases a release manager might say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—"analyze every PR", "inspecting the actual diff", "scope multi-provider PRs to the current provider's slice", "apply version bumps + changelog entries"—giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what (AI-driven classification, diff inspection, scoping, escalation, bumps + changelog) and when ("Use during the regular provider release cycle as an alternative to the interactive breeze prompts") with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Good domain keywords ("provider release cycle", "version bumps", "changelog entries", "prepare-provider-documentation", "interactive breeze prompts") but heavily laced with internal mechanism jargon ("one sub-agent per provider") and a few natural phrasings a release manager would say are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear, narrow niche—replacing a specific `breeze release-management prepare-provider-documentation` step—so it would not trigger for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1086 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: apache/airflow
Path: .agents/skills/prepare-providers-documentation/SKILL.md
Commit: 1f529f3

Reviewed: 1 day 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.