CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-academy-mission-builder

Scaffold and author content for the microsoft/agent-academy GitHub repo. Use this skill whenever the user wants to create a new mission, lab, or module for Agent Academy — whether that's a course mission (Recruit, Operative, Commander) or a standalone Special Ops mission. Trigger whenever the user says "write a mission", "scaffold a lab", "create a Special Ops", "new Agent Academy module", or describes an agent-building concept they want to turn into a hands-on lesson. Also trigger when the user says "add a module to agent academy", "I want to contribute a mission", or asks about badge creation for Special Ops. This skill handles: repo structure lookup, duplicate detection, mission naming, markdown scaffolding, step-by-step content drafting, cross-linking, tag/category suggestions, difficulty rating, and badge image generation for Special Ops missions.

73

Quality

91%

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

82%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.

The body is a well-sequenced, highly actionable 8-phase workflow with complete templates, concrete commands, and a duplicate-check validation step. It assumes Claude's competence and uses references appropriately, with only minor verbosity and the absence of explicit error-recovery loops in the final delivery phase.

Suggestions

Add an explicit validate-then-retry feedback loop to Phase 7 (e.g., verify the generated markdown renders and frontmatter is valid before delivering) to lift workflow_clarity to a 5.

Move the two large markdown templates into separate reference files (e.g., references/course-mission-template.md and references/special-ops-template.md) and link to them from the body to improve progressive_disclosure.

Trim the 'mission briefing officer' analogy paragraph — it is illustrative but adds tokens that do not directly advance the task.

DimensionReasoningScore

Conciseness

Mostly lean and assumes Claude's competence, but the two full markdown templates plus the 'mission briefing officer' analogy and some explanatory phrasing ('Think of this skill like...') add tokens that could be trimmed slightly. It does not over-explain basic concepts, keeping it above the midpoint.

4 / 5

Actionability

Provides complete, copy-paste-ready markdown templates for both mission types, concrete file path conventions, specific commands (web_search, web_fetch with exact URLs and search queries), and explicit step-drafting rules (bold UI names, code-format values, placeholder conventions).

5 / 5

Workflow Clarity

A clear 8-phase sequence (Phase 0–7) with an explicit duplicate-check checkpoint in Phase 1 ('If there's a close duplicate, surface it clearly') and a delivery checklist. However, the badge generation and file-write steps in Phase 7 lack an explicit validate-then-retry feedback loop, so it sits just below the anchor that requires explicit error-recovery loops.

4 / 5

Progressive Disclosure

Well-organized phased structure with one-level-deep references to a real bundle (references/tags.md) and clearly signaled repo-relative reference files (WRITING_STYLE.md, docs/recruit/index.md). The two full templates are inlined rather than split into separate files, which is a minor organization gap keeping it just below a 5.

4 / 5

Total

17

/

20

Passed

Description

100%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.

The description is excellent: third-person voice, comprehensive concrete capabilities, explicit and varied trigger phrases, and a clearly scoped niche tied to a specific repo. It fully answers what the skill does and when to use it.

DimensionReasoningScore

Specificity

Lists many concrete actions — 'repo structure lookup, duplicate detection, mission naming, markdown scaffolding, step-by-step content drafting, cross-linking, tag/category suggestions, difficulty rating, and badge image generation' — giving comprehensive, specific coverage rather than vague language.

5 / 5

Completeness

Explicitly answers both what ('Scaffold and author content for the microsoft/agent-academy GitHub repo') and when ('Use this skill whenever the user wants to create a new mission... Trigger whenever the user says...'), with concrete trigger phrases attached.

5 / 5

Trigger Term Quality

Includes numerous natural trigger phrases a user would actually say ('write a mission', 'scaffold a lab', 'create a Special Ops', 'new Agent Academy module', 'add a module to agent academy', 'I want to contribute a mission') plus the entity name Agent Academy, covering synonyms and variations.

5 / 5

Distinctiveness Conflict Risk

Scoped tightly to the microsoft/agent-academy repo and Agent Academy missions/Special Ops, a clear niche unlikely to trigger for unrelated skills.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing, 3 suspicious

Warning

Total

15

/

16

Passed

Repository
microsoft/agent-academy
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.