CtrlK
BlogDocsLog inGet started
Tessl Logo

create-mission-spec

Turn a mission or lab idea into a fully researched GitHub issue spec on microsoft/agent-academy, then post it with the GitHub CLI. Use this skill whenever the user wants to propose new Agent Academy content before writing it — course missions (Recruit, Operative, Commander), standalone Special Ops, or Cowork Collective missions. Trigger whenever the user says "write a spec for a mission", "create an issue for a new lab", "I want to propose a Special Ops", "file a mission proposal", "spec out a lab", "open an issue for a new module", or hands over Microsoft Learn URLs and asks to turn them into an Agent Academy lab. This skill handles: mining source documentation, interviewing for scope, repo reconnaissance and duplicate detection across both docs and existing issues, frontmatter and tag validation, writing-style conformance, drafting the issue body, title conventions, milestone and assignee metadata, and posting plus verifying the issue via `gh`.

72

Quality

88%

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

77%

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

A well-structured, highly actionable workflow skill with a clear phased process and strong validation checkpoints. It is somewhat long for a single file with no progressive disclosure via reference files, and a few rules are restated across sections.

Suggestions

Move the full issue-body markdown template and the per-mission-type style-requirements table into a reference file (e.g. references/ISSUE_TEMPLATE.md) and link to it from SKILL.md, reducing the main file's length and improving progressive_disclosure.

De-duplicate rules that appear in both a phase and the Rules section (click/textbox, projectCards deprecation, milestone necessity) by stating them once and cross-referencing, to improve conciseness.

Consider extracting the Phase 4 title-convention rules and Phase 6 writing-style checklist into a reference doc so the core workflow stays lean.

DimensionReasoningScore

Conciseness

Mostly efficient and free of generic-concept padding, but ~310 lines with some deliberate duplication — the 'Never write click or textbox', projectCards deprecation, and milestone-importance rules each appear in both a phase and the Rules section — that could be tightened without loss.

2 / 3

Actionability

Provides copy-paste-ready, fully executable guidance: exact `gh` commands with flags, a fenced markdown body template, precise title format, jq queries, and concrete file paths — matching the 'fully executable code/commands' anchor.

3 / 3

Workflow Clarity

An explicit 8-phase sequence with validation checkpoints ('Do not proceed until both checks pass', stop on duplicate, confirm before posting) and a dedicated verify/cleanup phase with feedback loops, matching the 'clear sequence with explicit validation steps' anchor.

3 / 3

Progressive Disclosure

Well-organized into phases but presented as a single monolithic ~310-line file with no bundle/reference files (references/scripts/assets absent) and content that could be split — the full issue-body template and per-mission-type style table — kept inline, fitting the 'content that should be separate is inline' anchor.

2 / 3

Total

10

/

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, trigger-rich, and complete, naming concrete actions and listing many natural user phrases. It is somewhat long but earns the length with concrete capability detail rather than fluff. No improvements needed.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'mining source documentation', 'repo reconnaissance and duplicate detection', 'frontmatter and tag validation', 'drafting the issue body', 'milestone and assignee metadata', and 'posting plus verifying the issue via `gh`' — matching the 'multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what ('Turn a mission or lab idea into a fully researched GitHub issue spec... then post it with the GitHub CLI') and when ('Use this skill whenever... Trigger whenever the user says...'), with explicit trigger guidance.

3 / 3

Trigger Term Quality

Provides natural user phrases a person would actually say — '"write a spec for a mission"', '"create an issue for a new lab"', '"I want to propose a Special Ops"', '"spec out a lab"', '"open an issue for a new module"' — giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

A clear niche — proposing Agent Academy content on microsoft/agent-academy — with triggers scoped to mission/Special Ops/Cowork Collective proposals, making it unlikely to fire for the wrong skill.

3 / 3

Total

12

/

12

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

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.