nima-karami/agentic-development

A lab for turning research into reusable Claude Code
**skills** (and tools) for agentic development.
The loop: dump deep-research on an agentic-development topic, read it critically,
then distill it into a self-contained, tested skill that improves day-to-day work
with coding agents.
Layout
The two-source convention
Every research topic has an **A** and a **B** synthesis from independent
researchers. A tends to be cautious and evidence-grounded; B tends to be confident
and prescriptive (and B's specific citations are sometimes unreliable — verify
before trusting). Skills are designed from where the two agree.
Skills
| Skill | Distilled from | What it does |
|-------|----------------|--------------|
| solidify-repo | agent-human-repo | Audits a repo for human/agent collaboration — instruction files, deterministic checks, a one-command verify harness, and a three-layer security gate (SAST + dependency/supply-chain audit + secret scanning) — and applies fixes with per-category approval. Pulls stack-specific tool picks from a curated tooling reference. |
| architecture-critic | agent-driven-architecture-design | Fresh-context adversarial review of a written design *before* code: a 7-dimension rubric, severity-tagged findings, and a PROCEED/REVISE verdict. |
| feature-spec | agent-driven-feature-spec | Turns a vague feature idea into a right-sized spec before implementation — triage tiers to avoid over-production, fixed checklists for uniform coverage, and a machine-parseable handoff block for autonomous pipelines. |
| guided-learning | accelerated-human-cognition | Teaches by turn-taking instead of lecturing: asks for a prediction first, works from one concrete case, checks understanding by having the learner produce something, and never answers its own check question. For concepts and for onboarding to an unfamiliar codebase. |
| autonomous-build-loop | long-running-agents | Conductor that drives a whole wishlist to *verified* completion in one long/unattended run — composes the other skills per phase, keeps state on disk for resumability, and scales pipeline depth to each feature's tier. |
Using a skill
Skills are authored and version-controlled here, but only take effect once copied