04e197c896
Three things in this commit:
1. Atlas skills now agentskills.io / Hermes-compatible
- Each atlas/skills/claw-*/SKILL.md frontmatter enriched with version,
author, license, and metadata.hermes block (tags, category,
related_skills, boundaries)
- New atlas/skills/DESCRIPTION.md per Hermes category convention
- New atlas/INTEGRATION-hermes.md — step-by-step SOP to install Atlas
onto hermes-agent runtime (cp skills, fetch nuwa upstream, configure
env, wire cron, smoke test). Documents the branding override and
self-improving-loop guardrail.
2. nuwa-skill mirror prep (waiting on org-repo creation)
- scripts/mirror-nuwa-to-moments.sh — one-shot bare-clone + push --mirror
- docs/decisions/0001-mirror-nuwa-skill.md — ADR explaining the why,
the bot-token scope limitation, and the manual one-time repo creation
step required at https://git.moments.top/repo/create
3. README rewrite
- Atlas-forward navigation table ("想做什么 → 看哪里")
- Quickstart sections for browsing, running tests locally, fetching
nuwa upstream (public + air-gapped variants), and Hermes integration
- Preserved all original Vega working agreements
- Roadmap with explicit Atlas / Vega tracks
Bot account (multica-bot) lacks write:organization scope so cannot create
the nuwa-skill repo via API. After human creates the empty repo at
git.moments.top/Moments.top/nuwa-skill, run scripts/mirror-nuwa-to-moments.sh
to populate it.
|
||
|---|---|---|
| .. | ||
| claw-boss-distiller | ||
| claw-customer-radar | ||
| claw-email-parser | ||
| claw-people-observer | ||
| claw-project-tracker | ||
| claw-report-writer | ||
| DESCRIPTION.md | ||
| README.md | ||
Atlas Skills Roster
Atlas is one Agent operating six sub-skills. Each skill is a focused module that takes structured input from the previous stage and produces structured output for the next.
[email-extractor]
↓
canonical Email JSON
↓
[claw-project-tracker] ──→ projects/*.json
↓ ↓
[claw-people-observer] ──→ people/*.json
↓ ↓
[claw-customer-radar] ──→ customers/*.json
↓ ↓
└─────→ [claw-report-writer] ──→ runs/YYYY-MM-DD.json + Brief
↑
[claw-boss-distiller] ──→ boss_skill.md (quarterly)
Skill List
| Skill | Owns | Reads | Writes |
|---|---|---|---|
claw-email-parser |
email extraction (delegates to email-extractor MCP tool) |
raw MIME | canonical Email JSON |
claw-project-tracker |
project state | Email JSON | state/projects/*.json |
claw-people-observer |
people observation (no rating!) | Email JSON + project state | state/people/*.json |
claw-customer-radar |
customer health | Email JSON + project state | state/customers/*.json |
claw-boss-distiller |
mental model distillation | boss outgoing email corpus | boss_skill.md (drafts; boss confirms) |
claw-report-writer |
brief / rollup / monthly rendering | all state | state/runs/*.json + rendered Brief |
Skill Contract Discipline
- Every skill has its own
SKILL.mdwith: purpose, inputs, outputs, judgment rules, failure modes, and a 5-row sample I/O. - Skills do not share state via in-memory variables; they communicate only through
state/. - Skills can be tested in isolation by feeding canned input.
- Skills cite rules: every output that contains a judgment includes a
rule_refsfield.
Why split into 6 instead of 1 monolithic skill
- Each skill stays small (< 500 lines of prompt) — better LLM accuracy per task
- Independent iteration — can update
claw-customer-radarwithout touching others - Independent eval — each skill has its own gold-standard test set
- Customer-perceived "AI team" — boss sees Project Manager, People Observer, Customer Radar, Boss Distiller, Report Writer working together
See ../AGENTS.md for orchestration order under each entry point (A/B/C/D/E).