michaelegnermichaelegner/architecture-intelligence-platform/.claude/skills/specification-driven-implementation/SKILL.mdspecification-driven-implementation
Skill10 starsChanged 28 days agoApache-2.0View on GitHub
Use when implementing substantial work against an AIP release or increment specification (docs/specifications/<release>/specification.md or its iN-*.md increment specs) - producing a reviewed plan before changing production code, persisting it, implementing without altering normative semantics, and reconciling the result against the retained plan. Not needed for small maintenance changes that don't touch public contracts, identity, evidence, qualification, reconciliation, or release semantics.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- address-reviewSkill
- post-merge-syncSkill
- release-publicationSkill
- specification-driven-implementationSkill
- address-reviewSkill
- post-merge-syncSkill
- release-publicationSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 15
Read that file in full and follow it exactly.
≈ “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
Specification-driven implementation
This is the Claude Code discovery entry point for this repository's specification-driven implementation workflow. It intentionally carries no procedure of its own.
The canonical, full procedure — the nine phases, the stop conditions, the plan template, and the
reconciliation template — lives at
.agents/skills/specification-driven-implementation/SKILL.md.
Read that file in full and follow it exactly. Do not treat this file as a separate or abbreviated version of the workflow — if the two ever appear to disagree, the canonical file is correct and this file is stale and should be fixed to match it, not the other way around.
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.