aip-tracker

AIP Progress Tracker Skill

Assess implementation progress of Airflow Improvement Proposals by comparing what the Confluence spec promises against what the codebase delivers.

When to Use This Skill

Use this skill when the task involves:

• Tracking AIP implementation status
• Comparing a spec against shipped code
• Producing a cross-AIP progress report

Available Tools

You have access to these tools for gathering evidence:

• fetch_confluence_page(page_id) -- fetch an AIP spec from Confluence
• search_github_prs(query) -- search GitHub PRs/commits for an AIP
• get_repo_file_tree(path_prefix) -- list files under a directory in the repo

Evidence Gathering Strategy

For each AIP, gather evidence from all three sources before assessing:

1. Confluence spec -- call fetch_confluence_page with the AIP's page ID. Extract: deliverables, phases, completion criteria, and status.
2. GitHub PRs and commits -- call search_github_prs with both the AIP number (e.g. "AIP-76") AND topic keywords (e.g. "asset partition"). Deduplicate results.
3. Codebase file tree -- call get_repo_file_tree with the AIP's known directory prefixes. Count source files and test files.

Deliverable Extraction

Extract deliverables from the specification's own structure. Use these sources in priority order:

1. Numbered completion criteria (e.g. "Definition of Done", "Completion Criteria") -- each numbered item is one deliverable.
2. Phase definitions -- each bullet or item under a phase heading is one deliverable.
3. Explicitly enumerated components (classes, operators, API endpoints, CLI commands, UI features) listed in the spec.

Critical: Do NOT split a single spec item into multiple deliverables (e.g. do not count individual files within one component as separate deliverables). Do NOT merge multiple spec items into one. Use the spec's own granularity -- if the spec says "partition mappers" as one item, that is one deliverable, not five separate file-level deliverables.

Assessment Rules