agent-academy-report

Generate a full Agent Academy feedback report — extracting feedback from Excel files and GitHub issues, analyzing sentiment, generating charts, and producing a single styled PDF with a cover page, management summary, and detailed analysis. Use this skill when the user asks to generate an Agent Academy report, create a feedback analysis, build a course completion report, or wants to analyze Agent Academy survey data. Also triggers when the user mentions Agent Academy feedback, course grades, sentiment analysis of Agent Academy data, or exporting Agent Academy results to PDF.

Quality

83%

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

73%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 well-structured, actionable pipeline skill with excellent workflow clarity and verification loops. Its main weakness is conciseness: large lookup tables and keyword lists duplicate logic embedded in the bundled scripts and could be delegated to reference files.

Suggestions

Move the sentiment keyword lists, theme→regex tables, and theme→advice mappings into a reference file (e.g. references/sentiment_config.md) since they are already encoded in the bundled scripts; summarize only what the agent needs to know.

Tighten the Phase 5 cover-page and badge sections by referencing a short table instead of narrating every hardcoded element and CSS rule.

Consolidate the Excel filename→course map and the chart color/short-name tables into a single reference appendix to reduce inline token weight in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational guidance, but the ~538-line body inlines large keyword lists, color tables, sentiment patterns, and theme→advice mappings that duplicate logic already in the bundled scripts, adding padding.	3 / 5
Actionability	Concrete executable commands per phase with exact script paths, MCP parameters, and specific file outputs; mostly copy-paste ready, with minor gaps around the interactive GitHub fetch step.	4 / 5
Workflow Clarity	Clear 6-phase sequence with an explicit verification phase (Phase 6 visual checklist), re-export feedback loops, and concrete fix locations — strong checkpoints and error recovery for a batch pipeline.	5 / 5
Progressive Disclosure	Well-organized into phases pointing to real bundled scripts (verified present in ./scripts/), with one-level-deep, clearly signaled references; substantial configuration detail is inlined rather than delegated to reference files.	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 high-quality description: concrete, comprehensive, and clearly answering both what the skill does and when to invoke it with explicit trigger guidance. Minor room to add synonyms or file extensions for trigger terms, but otherwise exemplary.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — extracting feedback from Excel files and GitHub issues, analyzing sentiment, generating charts, and producing a styled PDF with a cover page, management summary, and detailed analysis — for comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both what (full pipeline of extract/analyze/chart/PDF with named deliverables) and when ('Use this skill when...' and 'Also triggers when...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural trigger coverage including 'Agent Academy report', 'feedback analysis', 'course completion report', 'survey data', 'course grades', 'sentiment analysis', and 'exporting results to PDF'; a few synonyms and file-extension variants are missing.	4 / 5
Distinctiveness Conflict Risk	Tightly scoped to the 'Agent Academy' domain with domain-specific trigger terms; very low risk of firing for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (539 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: microsoft/agent-academy
Path: .github/skills/agent-academy-report/SKILL.md
Commit: 6300950

Reviewed: 2 days 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.