brutal-tickets
Skill2 starsChanged 4 months agoMITView on GitHub
Decompose an approved specification into the smallest useful dependency graph of cohesive, decision-complete implementation scopes. Use when another Brutal planning skill needs executable tasks, or when the user wants an approved plan split into implementation tickets without publishing them yet.
In this repository25 other files it gives its agents.
- brutal-deepresearchSkill
- brutal-grillSkill
- brutal-idea-evalSkill
- brutal-inf-fix-loopSkill
- brutal-planSkill
- brutal-pr-finding-fixerSkill
- brutal-pr-fix-loopSkill
- brutal-project-reviewSkill
- brutal-pr-reviewSkill
- brutal-realitySkill
- brutal-reviewSkill
- brutal-specSkill
- brutal-swarmSkill
- brutal-wayfinderSkill
- brutal-workerSkill
- codex-coopSkill
- design-jepa-modelsSkill
- factory-designSkill
- funcvec-dedupe-fixerSkill
- grill-meSkill
- handoffSkill
- opencode-delegateSkill
- rust-architecture-reviewSkill
- rust-pr-reviewSkill
- supply-chain-analyzerSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
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 23
Treat ordinary implementation order inside one outcome as a checklist, not a ticket dependency.
- Distinctive: line 34
Use the fewest scopes that satisfy these conditions.
- Distinctive: line 39
Use expand-contract inside one cohesive ticket when one migration owns the whole change:
- Distinctive: line 46
Create separate expand, migration, or contract tickets only when those phases must land or roll out independently.
- Distinctive: line 52
Use this body contract:
- Distinctive: line 74
Ask the user to approve the scope boundaries, granularity, blocking edges, coverage, and any merge or split decisions.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Brutal Tickets
Design implementation work that a fresh agent can complete one ticket at a time. Require an approved, decision-complete specification before starting.
Draft Cohesive Scopes
Make one ticket own one coherent outcome. Keep its schema, API, services, callers, UI, migration, cleanup, and tests together when they must be reasoned about, landed, or verified together. Ticket count follows the work; it is not a planning target.
Split a scope only when the parts have different hard blockers, ownership, rollout boundaries, or independently valuable outcomes. File count, crate or layer boundaries, implementation phases, parallelism, and context-window size do not justify a split by themselves.
Treat ordinary implementation order inside one outcome as a checklist, not a ticket dependency. If neither proposed ticket is useful or complete without the other, merge them.
Each ticket must:
- deliver a complete observable or verifiable outcome
- depend only on work that genuinely blocks it
- preserve a green integration state when it lands
- give a fresh agent enough decisions and verification to finish or resume it
Use the fewest scopes that satisfy these conditions. Prefer a checklist inside one ticket over several tickets that only make sense together.
Wide refactors
Use expand-contract inside one cohesive ticket when one migration owns the whole change:
- expand by adding the new form beside the old
- migrate callers in independently green batches sized by blast radius
- contract by removing the old form after every migration batch
Create separate expand, migration, or contract tickets only when those phases must land or roll out independently. Otherwise keep the sequence and its final verification in the same ticket.
Define Each Ticket
Use this body contract:
## Parent
## Phase And Order
## What To Build
## Acceptance Criteria
## Blocked By
## Implementation Notes
## Verification CommandsDescribe end-to-end behavior in What To Build; keep layer-by-layer detail in
implementation notes. Use stable module and interface names rather than guessed
paths. Make acceptance criteria externally observable and verification commands
exact. Express dependencies as ticket titles until backend identifiers exist.
Approval Gate
Present a numbered graph in dependency order with one line per ticket: cohesive scope, delivered outcome, and blockers. Keep complete bodies and the acceptance coverage trace ready for publication, but show them only when the user asks. Ask the user to approve the scope boundaries, granularity, blocking edges, coverage, and any merge or split decisions.
Iterate until approved. The stage completes only when every ticket is decision-complete, every blocking edge is necessary, and the graph covers every spec acceptance criterion. Return the approved graph without publishing it.
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.

