templates/skills/project/standart/decomposition/SKILL.md
Break standard-flow epics into implementation-ready tasks with AC, DoD, sequencing, and critical-path visibility
npx skillsauth add ozerohax/assistagents project-standart-decompositionInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
<when_to_use> <item importance="critical">After epic creation, before implementation starts</item> <item importance="high">When capacity estimation and a sequential delivery plan are required</item> </when_to_use>
<required_preload> <item>shared-base-rules</item> <item>shared-docs-paths</item> <item>decomposition-strategy</item> <item>planning-change-inventory</item> <item>planning-estimation</item> <item>planning-testing-strategy</item> </required_preload>
<document_target>
<rule importance="critical">Create/update files in tasks/{task key}-{task number}-{user friendly name}.md</rule>
</document_target>
<output_format>
<section>Ordered task list</section> <section>Task to epic mapping</section> <section>Task AC and DoD</section> <section>Dependencies and critical path</section> <section>Estimation and scope-cut options</section> </output_format><quality_rules> <rule importance="critical">Every task is testable and has a completion criterion</rule> <rule importance="critical">No large ambiguous tasks without AC/DoD</rule> <rule importance="high">Task order accounts for risks and dependencies</rule> </quality_rules>
testing
Visual regression (baseline diffs, UI stabilization)
testing
Design detailed reproducible test cases (Given/When/Then, one check per case); not smoke/regression checklists
development
Mobile testing (native/hybrid/web, gestures, offline, interruptions)
testing
Load testing (k6/JMeter scenarios, benchmarks)