Add create-ecc skill (research-first) and document it

Today: scaffolds one schema-valid, evidence-backed characteristic from a research brief and validates it with ecc-cli check.

Next iteration (see #12): map characteristics to CC4K terms as computable logical definitions so sample classification updates automatically as knowledge evolves (WHO CNS4 -> CNS5).

Author: Ssandor13

README.md

@@ -20,29 +20,36 @@ cargo build --release
 cargo run --release --example
 ```
 
-## 🧩 Scaffolding a new ECC
-
-This repository ships a local [Claude Code](https://github.com/anthropics/claude-code)
-skill, `create-ecc`, that scaffolds a new composable characteristic as a
-schema-valid YAML file. It lives at
-[`.claude/skills/create-ecc/SKILL.md`](.claude/skills/create-ecc/SKILL.md) and
-mirrors the data model in `crates/ecc/src/`.
-
-Given a description of a characteristic, the skill picks the correct folder
-(`ecc/morph` or `ecc/molec`) and identifier type (`ECC-MORPH-NNNNNN` /
-`ECC-MOLEC-NNNNNN`, uppercase with six zero-padded digits), keeps the filename
-number in sync with the identifier, writes the appropriate `state`
-(`draft`/`proposed`/`provisional`/`adopted`) and its required fields, and defines
-the value kind (`binary`, `categorical`, or `numerical`). It then validates the
-result with the checker below.
-
-```text
-# In Claude Code, invoke the skill:
-/create-ecc add a molecular characteristic for MYCN amplification (binary: amplified vs not)
-
-# It produces, for example, ecc/molec/000002-mycn-amplification.yml, then runs
-# the checker from the repo root (the Cargo workspace lives in `crates/`):
-cargo run --manifest-path crates/Cargo.toml -p ecc-cli -- check ecc
+## 🤖 Authoring characteristics with Claude
+
+This repository ships a [Claude Code][claude-code] skill, `create-ecc`, that
+guides an agent through **researching and authoring** a new composable
+characteristic — not just writing YAML, but producing an evidence-backed entry a domain expert would sign off on. It lives at `.claude/skills/create-ecc/SKILL.md` and is discovered automatically by any agent started in this repository.
+
+### What it does
+
+1. **Research first.** Before writing anything, the agent builds an evidence
+   brief: a precise definition and scope, the correct category (`morph` vs
+   `molec`), primary-literature citations with resolvable URLs, how the property is measured/reported (which decides binary vs. enumerated values and any thresholds), and alignment with existing ontologies (NCIt/MONDO). A quality bar rejects thin or unsourced entries.
+2. **Scaffold correctly.** It allocates the next identifier
+   (`ECC-{MORPH|MOLEC}-NNNNNN`, six zero-padded digits) and a matching
+   `NNNNNN-slug.yml` filename in the right folder, and writes a schema-valid entry
+   honoring the `state` lifecycle (`draft` → `proposed` → `provisional` →
+   `adopted`) and `deny_unknown_fields`.
+3. **Validate.** It runs `cargo run -p ecc-cli -- check ecc` and fixes any
+   failures before finishing.
+
+### Usage
+
+Start an agent in the repository root and describe the characteristic, e.g.:
+
+> Use the create-ecc skill to add a molecular characteristic for MYCN
+> amplification.
+
+See [`.claude/skills/create-ecc/SKILL.md`](.claude/skills/create-ecc/SKILL.md)
+for the full workflow and schema reference.
+
+[claude-code]: https://www.anthropic.com/claude-code
 ```
 
 ## 🚧️ Tests