mission-brief
Skill3 starsChanged 2 months agoMITView on GitHub
Write a Voltron Mission Brief (objective, scope, out of scope, success criteria, constraints) as Markdown plus a schema.org JSON-LD knowledge graph. Use when the user asks to "write a mission brief", "draft the brief", "scope this mission", or at Step 1 of the Voltron mission flow, and whenever a brief must be exported as structured or machine-readable output.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- tylerjrbuell/Wardenstheir own version, first seen Nov 15, 2026
- tikalk/adlc-team-skillstheir own version, first seen Nov 8, 2026
- sunholo-data/ailangtheir own version, first seen Nov 6, 2026
- thanatchon36/skillstheir own version, first seen Oct 15, 2026
- sumo91/mission-brieftheir own version, first seen Sep 5, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- tikalk/adlc-team-skills★ 145same name
- sunholo-data/ailang★ 38same name
- sumo91/mission-brief★ 14same name
- tylerjrbuell/Wardens★ 2same name
- thanatchon36/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- browser-actionsSkill
- mission-planSkill
- mission-reportSkill
- skills-registrySkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 28
Every identifier in this and later mission documents is built on it, so fix it now and never change it mid-mission.
- Distinctive: line 31
Ask before creating a top-level directory in someone's repo.
- Distinctive: line 44
If the objective is vague, ask ONE clarifying question before drafting.
- Distinctive: line 46
Every success criterion must name how it is checked.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Mission Brief — Markdown + Knowledge Graph
Emits the first of the three Voltron mission documents in both human and machine form.
Read the format reference first: ${CLAUDE_PLUGIN_ROOT}/kb/mission-knowledge-format.md.
It defines the JSON-LD envelope, the URN identifier scheme, the schema.org type mapping, and
the pre-write validation steps. Do not improvise identifiers or types — the three mission
documents merge into one graph only because they share that scheme.
What a brief contains
| Section | Content | Graph node |
| Objective | One sentence. What the mission achieves, not how. | Project.description |
| Scope | Bulleted, concrete, each item independently checkable. | ItemList of DefinedTerm |
| Out of Scope | What a reader might reasonably assume is included but isn't. | ItemList of DefinedTerm |
| Success Criteria | Observable, testable. "Returns 200", not "works well". | DefinedTerm per criterion |
| Constraints | Assumptions, deadlines, tech limits, things held fixed. | ItemList of DefinedTerm |
Procedure
- Derive the slug from the objective: kebab-case, drop articles, truncate to 48 chars. Every identifier in this and later mission documents is built on it, so fix it now and never change it mid-mission.
- Confirm the output directory with the user — default
./voltron-missions/{date}-{slug}/. Ask before creating a top-level directory in someone's repo. - Write
mission-brief.md. Lead with a one-line objective, then the five sections as headed lists. Keep it under a page; a brief that needs scrolling has scope problems. - Write
mission-brief.jsonld. Emit theProjectnode, theReportnode for the brief itself, and oneDefinedTermper scope item, criterion, and constraint. Reference the Lions inmemberonly once assignments exist — at brief stage the mission has no members yet, so omitmemberrather than guessing. - Validate per the KB's pre-write checklist: parse the JSON, resolve every
@idreference, confirm the enumerations. - Report both paths to the user and state that the brief is Step 1 of 3.
Writing rules
- If the objective is vague, ask ONE clarifying question before drafting. A brief built on a guess sends every downstream Lion in the wrong direction, and the plan inherits the error.
- Every success criterion must name how it is checked. If you cannot say how it is checked, it belongs in Scope, not Success Criteria.
- Out of Scope is not optional. An empty Out of Scope means the boundary was never tested.
- State assumptions in Constraints explicitly rather than leaving them implied.
Relationship to the other mission documents
The brief establishes urn:voltron:mission:{slug} and its success criteria. mission-plan
attaches assignments to it and mission-report records their outcomes, both by @id
reference. Write the brief first; if a plan already exists without one, write the brief from
the plan's about node rather than inventing a second mission identifier.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.