CtrlK
BlogDocsLog inGet started
Tessl Logo

aip-tracker

Track Airflow Improvement Proposal (AIP) implementation progress by comparing Confluence specs against codebase evidence. Use when asked to assess, report on, or compare AIP status.

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 highly actionable, well-sequenced instruction skill with concrete tool calls, a copy-paste report template, and a mandatory self-verification checklist providing strong feedback loops. Its main leverage point is trimming the minor redundancy between the rules and verification sections.

Suggestions

De-duplicate the rules shared between 'Assessment Rules' and 'Self-Verification' by having the checklist reference the rules rather than restate them, shaving tokens without losing the feedback loop.

Consider moving the full output-format template into a referenced file (e.g. report_template.md) if the skill grows, keeping SKILL.md as a lean overview.

DimensionReasoningScore

Conciseness

Largely lean, task-specific guidance with no explanation of concepts Claude already knows; the only redundancy is the percentage/rule restatement between Assessment Rules and the Self-Verification checklist, but most every line earns its place.

4 / 5

Actionability

Provides concrete tool signatures (fetch_confluence_page(page_id), search_github_prs(query), get_repo_file_tree(path_prefix)), an explicit prioritized extraction procedure, hard rules with examples, and a copy-paste output template that fully covers the common cases.

5 / 5

Workflow Clarity

Clear multi-step sequence (gather evidence from all three sources -> extract deliverables -> assess with evidence -> format -> self-verify) with an explicit MANDATORY validation checklist and a fix-before-returning feedback loop for this batch/report operation.

5 / 5

Progressive Disclosure

Well-organized into clear sections with no nested references and a single self-contained document; at ~140 lines it is longer than the simple-skill threshold, and a small amount of content (e.g. the full output template or extended rule rationale) could optionally live in a reference file, but nothing is improperly buried.

4 / 5

Total

18

/

20

Passed

Description

82%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, well-scoped description that clearly states both capability and trigger conditions for a distinct niche. It could enumerate more concrete actions to lift specificity from adequate to comprehensive.

Suggestions

Add 1-2 more concrete actions to the 'what' clause (e.g. 'extract deliverables, cite PR/file evidence, and flag stale Confluence specs') to raise specificity toward comprehensive coverage.

Broaden the trigger phrase with common synonyms users may say, such as 'AIP progress report', 'spec vs. code', or 'AIP status check'.

DimensionReasoningScore

Specificity

Names the domain ('Track AIP implementation progress') and one concrete action ('comparing Confluence specs against codebase evidence'), but does not enumerate multiple distinct actions (e.g. extracting deliverables, citing PR evidence, flagging stale specs) for comprehensive coverage.

3 / 5

Completeness

Explicitly answers both what ('Track AIP implementation progress by comparing Confluence specs against codebase evidence') and when ('Use when asked to assess, report on, or compare AIP status') with a concrete trigger clause.

5 / 5

Trigger Term Quality

Includes natural trigger phrases users would say ('assess, report on, or compare AIP status') plus the domain term AIP; good coverage, though a few likely synonyms (e.g. 'AIP progress', 'AIP report', 'spec vs code') are absent.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (Airflow Improvement Proposals, Confluence-vs-codebase comparison) with distinct triggers, making conflict with other skills minimal.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
apache/airflow
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.