task-brief
Skill4 starsChanged 4 months agoMITView on GitHub
Clarify substantial work with a concise Task Brief when high-impact details cannot be safely inferred before planning or implementation. Use to resolve ambiguity in Goal, Context, Constraints, or Done when; ask only high-impact unknowns; and get user confirmation before continuing.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- THROVIA/Task_Brieftheir own version, first seen Oct 17, 2026
- Baba01hacker666/dummyskillstheir own version, first seen Oct 13, 2026
- nelantone/cogniviatheir own version, first seen Oct 11, 2026
- zarubinvibe/themistheir own version, first seen Sep 8, 2026
- zarubinvibe/themiztheir own version, first seen Sep 8, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- zarubinvibe/themis★ 11same name
- zarubinvibe/themiz★ 11same name
- THROVIA/Task_Brief★ 4same name
- nelantone/cognivia★ 1same name
- Baba01hacker666/dummyskills★ 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 repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- build-incrementalSkill
- code-simplifySkill
- create-or-clone-repositorySkill
- design-firstSkill
- implementation-workflowSkill
- manage-git-worktreesSkill
- plan-driven-developmentSkill
- setup-wiki-backed-project-skillsSkill
- subagent-supervisionSkill
- test-driven-debugSkill
- tidy-firstSkill
- write-personal-wikiSkill
- write-project-wikiSkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 9 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
9
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 8
Use this skill to clarify substantial work before writing an ExecPlan or starting implementation.
- Distinctive: line 14
Ask only for high-impact unknowns that cannot be safely inferred.
- Distinctive: line 16
Wait for user confirmation before creating an ExecPlan or beginning implementation.
- Distinctive: line 45
Do not invent product behavior, public API changes, data/privacy requirements, destructive operations, expensive compute, or acceptance …
- Distinctive: line 49
Ask concise questions only when the answer materially changes the plan or risk.
- Distinctive: line 51
Prefer 1-3 questions. Avoid asking about details that can be discovered locally or safely deferred.
- Distinctive: line 55
Before creating an ExecPlan or implementing substantial work, show the completed Task Brief and ask for confirmation.
- Distinctive: line 57
Do not print a full ExecPlan as part of the Task Brief.
- Distinctive: line 58
Do not modify code while still clarifying the Task Brief.
“Common” is measured: kept by at least 6 in 10 of the 3 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
Task Brief
Use this skill to clarify substantial work before writing an ExecPlan or starting implementation.
Workflow
- Inspect the user's request and relevant repository context.
- Infer details that are reasonably knowable from local files, README, docs, configs, tests, errors, and existing patterns.
- Ask only for high-impact unknowns that cannot be safely inferred.
- Present a short Task Brief to the user.
- Wait for user confirmation before creating an ExecPlan or beginning implementation.
Task Brief Format
**Task Brief**
Goal:
- ...
Context:
- ...
Constraints:
- ...
Done when:
- ...Inference Rules
Infer routine details when evidence is available.
Examples:
- Existing frameworks, package managers, test commands, and code style from repository files.
- Relevant behavior from README, docs, tests, configs, and current errors.
- Reasonable scope from the user's explicit request.
Do not invent product behavior, public API changes, data/privacy requirements, destructive operations, expensive compute, or acceptance criteria.
Questions
Ask concise questions only when the answer materially changes the plan or risk.
Prefer 1-3 questions. Avoid asking about details that can be discovered locally or safely deferred.
Confirmation Gate
Before creating an ExecPlan or implementing substantial work, show the completed Task Brief and ask for confirmation.
Do not print a full ExecPlan as part of the Task Brief. Do not modify code while still clarifying the Task Brief.
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.