sdd-conventions
Skill0 starsChanged 37 days agoMITView on GitHub
Use when designing or reviewing a chosen architecture, design pattern, component boundary, API, module, refactor, Phase → Milestone → Task hierarchy, task breakdown, hosted task mapping, repository hosting-token storage or authentication recovery, workflow branch identities and artifact locations, review/revision campaign records, or code change; also use during code review and when comparing design options. Assess cohesion, dependencies, testability, complexity, and SOLID, DRY, and KISS where relevant.
In this repository14 other files it gives its agents.
- sdd-designSkill
- sdd-docsSkill
- sdd-forgeSkill
- sdd-implementSkill
- sdd-integrate-featureSkill
- sdd-manageSkill
- sdd-orientSkill
- sdd-planSkill
- sdd-reportSkill
- sdd-specifySkill
- sdd-steerSkill
- sdd-tasksSkill
- sdd-tddSkill
- sdd-verifySkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
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 8
Use the relevant convention only when its concern occurs in the current work.
- Distinctive: line 12
Modularity: Read modularity when creating or assessing boundaries among system blocks, components, document nodes, code modules, or …
- Distinctive: line 13
Design heuristics: Read design heuristics when evaluating a chosen design or pattern, reviewing an implementation or refactor, or comparing …
- Distinctive: line 14
Task hierarchy: Read task hierarchy when defining or reviewing Phase → Milestone → Task identity and parentage in TASKS, or projecting that …
- Distinctive: line 16
Backend object lifecycle: Read backend object lifecycle for phase-gated projection, explicit review units, issue/milestone closure, report …
- Distinctive: line 18
Workflow identity: Read workflow identity when allocating revision/feature campaign identities, naming workflow branches, or locating …
- Distinctive: line 20
Development-document QC: Read development-document QC when authoring/reviewing SPEC, PLAN or TASKS, evaluating delivery decomposition, …
- Distinctive: line 22
Review campaigns: Read review campaigns when organizing review/revision plans and reports, assigning campaign/finding identities, or …
- Distinctive: line 24
Hosting tokens: Read hosting tokens when discovering, storing, or supplying repository credentials, or recovering shell/backend …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Shared conventions
Use the relevant convention only when its concern occurs in the current work. Respect applicable project instructions and established contracts. This skill supplies reusable criteria; it does not perform repository orientation, own project artifacts, execute a workflow, or authorize mutation.
Available conventions
- Modularity: Read modularity when creating or assessing boundaries among system blocks, components, document nodes, code modules, or executable tasks, including code review.
- Design heuristics: Read design heuristics when evaluating a chosen design or pattern, reviewing an implementation or refactor, or comparing options using SOLID, DRY, or KISS.
- Task hierarchy: Read task hierarchy when defining or reviewing Phase → Milestone → Task identity and parentage in TASKS, or projecting that hierarchy to hosted issues, labels, and milestones.
- Backend object lifecycle: Read backend object lifecycle for phase-gated projection, explicit review units, issue/milestone closure, report placement and interruption recovery.
- Workflow identity: Read workflow identity when allocating revision/feature campaign identities, naming workflow branches, or locating active and retained workflow artifacts.
- Development-document QC: Read development-document QC when authoring/reviewing SPEC, PLAN or TASKS, evaluating delivery decomposition, establishing stage readiness, or reassessing affected feature/steering documents.
- Review campaigns: Read review campaigns when organizing review/revision plans and reports, assigning campaign/finding identities, or retaining findings and evidence alongside governing project documents.
- Hosting tokens: Read hosting tokens when discovering, storing, or supplying repository credentials, or recovering shell/backend authentication.
Add a convention here only when it defines a clear invariant used by multiple workflows, can be applied without absorbing their stage-specific procedures, and does not own an artifact or operational workflow. Give each added concern its own focused reference and explicit trigger. Otherwise place it with the skill that owns the work.
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.

