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

92%

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

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a well-sequenced, validated workflow and clean one-level-deep references to real bundled scripts. Its main weakness is length: substantial inline keyword, advice, and mapping tables duplicate detail that the scripts already encode and could be trimmed or externalized.

Suggestions

Move the exhaustive sentiment keyword lists and theme/advice mapping tables into a reference file (e.g. references/sentiment_rules.md) and link to it, keeping SKILL.md to the scoring rule and theme names.

Externalize the Excel-filename-to-course mapping table into the extract_feedback.py script or a reference doc so the SKILL.md only states that filenames are mapped to course names.

Tighten the Phase 6 verification checklist by collapsing the Common Formatting Issues section, since each fix already points to a specific script function.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient operational detail, but it inline-duplicates content that lives in the bundled scripts (exhaustive sentiment keyword lists, the theme/advice mapping tables, the Excel filename map, grade-threshold strings), which could be tightened or moved to reference files.	2 / 3
Actionability	Provides copy-paste-ready commands, exact MCP tool parameters with pagination details, JSON output shapes, scoring rules, and slug formulas — fully executable guidance throughout.	3 / 3
Workflow Clarity	A clear 6-phase sequence with Phase 6 as an explicit verification checklist and a fix-and-re-export feedback loop ('verify again until all checks pass'), satisfying the validation-checkpoint anchor.	3 / 3
Progressive Disclosure	The SKILL.md is an overview that points to real, clearly-signaled, one-level-deep bundle scripts (extract_feedback.py, analyze_sentiment.py, generate_charts.py, build_markdown.py, export_pdf.py) verified present in ./scripts/.	3 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, complete, and distinctive: it enumerates concrete actions, provides explicit natural-language triggers for both what and when, and is anchored to a narrow Agent Academy niche. No weaknesses worth flagging.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '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' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers both what (the full action list) and when via 'Use this skill when...' and 'Also triggers when...' clauses, satisfying the explicit-trigger anchor.	3 / 3
Trigger Term Quality	Covers natural phrases a user would say — 'Agent Academy report', 'feedback analysis', 'course completion report', 'Agent Academy survey data', 'course grades', 'sentiment analysis', 'exporting Agent Academy results to PDF'.	3 / 3
Distinctiveness Conflict Risk	The 'Agent Academy' niche is highly specific with distinct triggers, making conflict with other skills unlikely.	3 / 3
	Total	12 / 12 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: a5e6b52

Reviewed: about 14 hours 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.