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`.

75

Quality

94%

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 dense, highly actionable multi-phase workflow with strong sequencing and validation checkpoints for an outward-facing operation. The main weakness is mild verbosity from embedded rationale and a single-file structure that, while well-organized, is long enough that some material could be split out.

Suggestions

Trim justificatory asides (e.g. 'saves the implementer an hour', 'wastes a round trip') to pure imperatives; the rules already make the constraints clear.

Consider moving the Phase 5 issue-body template and/or the Rules list into a reference file (e.g. references/ISSUE_TEMPLATE.md) and linking to it, keeping SKILL.md as a tighter overview.

A few Phase headings repeat guidance also captured in the Rules section (GH_PAGER=cat, --body-file, /tmp/); consolidate to one authoritative spot to reduce token cost.

DimensionReasoningScore

Conciseness

Mostly efficient with copy-paste commands and concrete templates, but several justificatory asides ('saves the implementer an hour', 'wastes a round trip', 'reads like a UI breadcrumb and costs characters without adding information') could be trimmed; not a 5 because the rationale padding is noticeable, not a 3 because the core is genuinely lean and actionable.

4 / 5

Actionability

Provides fully executable, copy-paste-ready guidance throughout: `GH_PAGER=cat gh api repos/.../milestones --jq ...`, `gh issue create --title ... --label feature-request --milestone ... --body-file /tmp/<name>.md`, exact JSON data file paths, and a complete body template.

5 / 5

Workflow Clarity

An eight-phase workflow with explicit validation and confirmation gates — 'Do not proceed until both checks pass', 'stop and tell the user before drafting' on duplicate hits, 'Fix anything the check surfaces before posting', confirm before posting, and a verify-and-clean-up phase that reads the issue back and checks all four metadata fields.

5 / 5

Progressive Disclosure

Well-organized into clearly headed sections (Prerequisites, Mission types, Phases 1–8, Rules) with no nested references and no bundle files to misfile; falls short of 5 only because it is a long monolithic single file whose body template or rules block could arguably live in a separate reference.

4 / 5

Total

18

/

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.

A strong, third-person description that concretely enumerates the skill's actions, supplies abundant natural trigger phrases, and clearly separates the what from the when. Voice and trigger guidance both meet the top anchors.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'mining source documentation, interviewing for scope, repo reconnaissance and duplicate detection... 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`' — giving comprehensive coverage of what the skill does.

5 / 5

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 the user wants to propose new Agent Academy content... Trigger whenever the user says...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers natural phrases a user would actually say — 'write a spec for a mission', 'create an issue for a new lab', 'spec out a lab', 'open an issue for a new module', plus Microsoft Learn URLs — including synonyms and variations.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — proposing Agent Academy mission specs on microsoft/agent-academy — with repo-specific and content-type-specific triggers, making accidental activation by unrelated skills unlikely.

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

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.