Tessl • The management layer for AI agent skills

SkillPublic

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

86%

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.

Exceptionally actionable and rigorous workflow documentation with real validation feedback loops, but it is a ~1,170-line monolith with noticeable rule duplication that hurts token efficiency, and it makes no use of progressive disclosure via bundle reference files.

Suggestions

Move the per-provider sub-agent briefing template and breaking-change checklist into a references/ file (e.g. references/subagent-briefing.md) and reference it from Phase 3, cutting a large inline block from the main file.

State the tooling-vs-provider.yaml skip rule once (in Phase 3) and have the Phase 5 defect-scan checklist reference it by pointer instead of restating the rationale, removing the triple duplication.

Extract the long changelog-format rules in Phase 4b (subject rewriting, collapsing chains, ordering) into a references/changelog-rules.md and keep only the skeleton plus a short summary in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The ~1,170-line body is dense with genuinely non-obvious domain knowledge (no padding with concepts Claude already knows), but several rules are restated multiple times — the tooling/provider.yaml skip rule appears in a NOTE, a WARNING, and the sub-agent brief, and the Phase 5 defect scan largely re-lists Phase 4b rules — so it could be meaningfully tightened.	3 / 5
Actionability	Fully executable throughout: exact breeze/git commands (including tag-sorting gotchas), a copy-paste-ready sub-agent briefing with a fixed pipe output format, the changelog RST skeleton, and a runnable python3 reconciliation script covering the common cases.	5 / 5
Workflow Clarity	Five clearly sequenced phases plus a mirrored incremental flow, with an explicit validation gate (check_changelog_entries.py --fix with a defect-code table and re-run-after-rebase instruction), an idempotency re-check, escalation checkpoints to the release manager, and hard stop conditions for a batch-mutating operation.	5 / 5
Progressive Disclosure	There are no bundle files (no references/, scripts/, or assets/), so the entire skill is one monolithic file; section headers and navigation are strong and the trailing References section is clearly signaled, but content that clearly belongs in separate files (the ~100-line sub-agent briefing with the breaking-change checklist, the changelog-format rulebook, worked examples) is inlined.	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 strong description: concrete, comprehensive, in third person, with an explicit use-when clause tied to a named tool and workflow. The only minor gap is coverage of a few natural synonym phrases a user might say instead.

Dimension	Reasoning	Score
Specificity	The description 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" — with comprehensive coverage of what the skill does.	5 / 5
Completeness	It explicitly answers both what (AI-driven classification of provider PRs, breaking-change inspection, version bumps, changelog entries) and when ("Use during the regular provider release cycle as an alternative to the interactive breeze prompts"), so the missing-when cap does not apply.	5 / 5
Trigger Term Quality	Natural trigger terms are present ("provider release cycle", "prepare-provider-documentation", "interactive breeze prompts", "changelog entries") and anchored on the exact breeze subcommand, but a few common variations users might say (e.g. "release notes", "provider release") are missing.	4 / 5
Distinctiveness Conflict Risk	It names a specific breeze subcommand and the Apache Airflow provider release workflow, giving it a clear niche with essentially no overlap risk against other skills.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1171 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 1 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: apache/airflow
Path: .agents/skills/prepare-providers-documentation/SKILL.md
Revision: 1a50a18

Reviewed: 5 days ago

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.

prepare-providers-documentation

Table of Contents

Is this your skill?