v0.2.0 - Naming Unification

harness-ai-kit v0.2.0 — Naming Unification

The project name is now consistently harness-ai-kit across package, command, manifest, lockfile, config directory and env var. This release also adds 11 curated skills (34 total).

⚠️ BREAKING — naming unified to harness-ai-kit

Was	Now
Python package ai_kit	harness_ai_kit
Primary command ai-kit	harness-ai-kit (short ai-kit alias still works)
Manifest ai-kit.yml	harness-ai-kit.yml
Lockfile ai-kit.lock	harness-ai-kit.lock
Config dir ~/.ai-kit/	~/.harness-ai-kit/
Env var AI_KIT_PRODUCT	HARNESS_AI_KIT_PRODUCT

Migration for early adopters (from 0.1.0):

1. Rename ai-kit.yml → harness-ai-kit.yml and ai-kit.lock → harness-ai-kit.lock in your project.
2. Move ~/.ai-kit/ → ~/.harness-ai-kit/.
3. Re-run harness-ai-kit sync (skill inject markers refresh automatically).

Added

• 11 additional curated skills (34 total):
  • AI engineering methodology: spec-driven dev, agent engineering, eval-driven agent, ai-kit miner, tech-debt ops
  • Patent & document authoring (6)
  • Testing / quality: web deep acceptance, web E2E, tech-fit eval
• Skill catalog (CATALOG.md) and usage scenarios (docs/usage-scenarios.md) covering the skill+SDD and loop+runtime models
• PyPI trusted-publishing workflow (.github/workflows/publish.yml)

Install

pip install harness-ai-kit
harness-ai-kit --version   # 0.2.0

Full details in the CHANGELOG.

v0.1.0 — Initial Release

ai-kit v0.1.0

First public release of the AI asset package manager.

Features

• Unified asset schema (skills / CLIs / MCPs / plugins / hooks / subagents / loops)
• Dependency resolution with resolvelib + lockfile (ai-kit.lock) + SHA-256 checksums
• Multi-runtime support: Codex, Claude Code, Cursor, Kiro (project + global scope)
• GitHub direct install 鈥?no private registry required
• Staging + atomic rollback on install failure
• Offline cache mode
• Sensitive-reference CI scan (0 internal hostnames/credentials)

Curated Skill Library (23 skills)

• 9 knowledge bases (MySQL, PostgreSQL, Redis, MongoDB, Kafka, RabbitMQ, Oracle, NL2SQL, Git)
• 7 diagnostic chains (MySQL deadlock/slow/replication, container OOM, K8s CrashLoopBackOff/node-pressure, network port)
• 6 general engineering skills (registry mirror, goal execution, markitdown, doc convert/export, task miner)
• 1 infra flagship sample (Monit watchdog / service self-healing)

Infrastructure

• Bilingual README (English + Chinese)
• GitHub Actions CI (syntax check + import + CLI smoke + skill validation + sensitive scan + secret scan)
• Issue templates (bug / feature / skill proposal) + PR template
• CONTRIBUTING.md (with DCO) + CODE_OF_CONDUCT.md
• docs/ (quickstart + concepts + skill-authoring + asset-map)
• Apache-2.0 license

Install: \pip install harness-ai-kit
CLI: ^Gi-kit --version\ 鈫?0.1.0

---

⚠️ BREAKING — naming unified to harness-ai-kit (on main, after this tag)

Since this v0.1.0 tag was cut, main has fully unified the project naming to harness-ai-kit. If you are tracking main (or installing from source), note:

Was	Now
Python package ai_kit	harness_ai_kit
Primary command ai-kit	harness-ai-kit (the short ai-kit alias still works)
Manifest ai-kit.yml	harness-ai-kit.yml
Lockfile ai-kit.lock	harness-ai-kit.lock
Config dir ~/.ai-kit/	~/.harness-ai-kit/
Env var AI_KIT_PRODUCT	HARNESS_AI_KIT_PRODUCT

Migration for early adopters:

1. Rename ai-kit.yml → harness-ai-kit.yml and ai-kit.lock → harness-ai-kit.lock in your project.
2. Move ~/.ai-kit/ → ~/.harness-ai-kit/.
3. Re-run harness-ai-kit sync (inject markers refresh automatically).

Full details in CHANGELOG → Unreleased.