engineering-delivery
Skill0 starsChanged 3 months agoMITView on GitHub
Run production software work from specification through planning, implementation, testing, review, and release. Use for substantial repository changes that require explicit acceptance criteria and verification evidence.
In this repository5 other files it gives its agents.
- code-intelligenceSkill
- engineeringSkill
- skill-security-auditSkill
- supabase-operationsSkill
- video-workbenchSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 16
Read repository instructions, architecture, scripts, and current worktree state.
- Distinctive: line 20
Run focused tests, then broader lint, type checks, build, and security checks in proportion to risk.
- Distinctive: line 30
Do not claim success from agent confidence alone.
≈ “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
Engineering Delivery
This TIKAZ Edition is designed, integrated, refactored, and continuously maintained by TIKAZ. External engineering playbooks are research references, not redistributed content.
Inputs
Accept a repository and an authorized change request with constraints, acceptance criteria, and release boundary. Inspect local repository instructions and current worktree state before changing files.
Workflow
- Read repository instructions, architecture, scripts, and current worktree state.
- Convert the request into scope, constraints, acceptance criteria, and non-goals.
- Plan small implementation slices and identify risky dependencies.
- Implement in the repository's established style.
- Run focused tests, then broader lint, type checks, build, and security checks in proportion to risk.
- Review the final diff for regressions, unnecessary changes, secrets, and missing documentation.
- Report completed work, verification evidence, viewing instructions, and remaining risks.
Output contract
Return the implemented diff, acceptance-criteria mapping, commands and results, viewing instructions, rollback or release note, and unresolved risk. Preserve unrelated user changes.
Validation and fallback
Do not claim success from agent confidence alone. Require user confirmation or objective file, test, build, or runtime evidence. If a required environment, credential, or production authority is missing, deliver the verified local state and name the blocker; do not simulate deployment.
Example and limits
Use engineering-delivery to implement this confirmed feature in small slices, run repository-native checks, and report the exact verification evidence.This Skill does not expand scope, authorize destructive operations, or substitute generic checks for repository-native validation.
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.