v0.3.5 — defi/evm_tx_handler, Black CI, docs & CI alignment

Added

• defi/evm_tx_handler (#142): Structured EVM agent wallet skill on Ethereum and Base — resolve, Uni V2 quote/preview/execute (approve + swap), transfer, balances, wallet_info, YAML registries, optional CoinGecko USD preview, max_trade_usd fail-closed cap, balance pre-flight checks, and mocked Web3 tests. Examples: examples/gemini_evm_tx_handler.py, examples/claude_evm_tx_handler.py.

Changed

• CI: GitHub Actions installs from pyproject.toml only (pip install -e ".[dev,all]"); runs black --check, flake8, then pytest tests/ (#151, #153). Co-located skills/**/test_skill.py remains a local pre-PR step.
• Documentation: COMPARISON.md and README updated for Agent Skills (SKILL.md) and fairer MCP framing (#123); TESTING.md and CONTRIBUTING.md aligned with CI and Black gate (#151, #153); defi skill category added to CONTRIBUTING.

Fixed

• dev_tools/issue_resolver: Replaced wide emoji regex in commit-message validation with explicit Unicode ranges (CodeQL py/overly-large-range, #146).

Upgrade

pip install -U skillware
pip install -U "skillware[cli]"   # optional Rich CLI

For defi/evm_tx_handler, install skill deps from the manifest (e.g. pip install web3) — see the skill README.

Contributors

• @Hendobox — defi/evm_tx_handler (#142)
• @ReifStanfield — COMPARISON / Agent Skills documentation (#123, #141)
• @rosspeili — CI alignment (#151), Black CI (#153), issue_resolver CodeQL fix (#146)

Full changelog

• #142, #123, #141, #151, #153, #146

Compare: v0.3.3...v0.3.5

v0.3.3 — Issue resolver workflow, version policy, vision docs, wallet screening

Skillware v0.3.3

Added

• dev_tools/issue_resolver — GitHub issue workflow with sequential stage checklists, conditional verify/commit gates, and commit-message validation (#143).
• Examples — gemini_issue_resolver.py, claude_issue_resolver.py, and ollama_issue_resolver.py for dev_tools/issue_resolver; closes the runnable-examples gap (#118).
• Version policy — skillware/version_policy.py with supported-version thresholds; CLI prints one dim stderr advisory for installs below 0.2.6 (#132).
• Tests — tests/test_version_policy.py for advisory thresholds, opt-out, and CLI hook (#132).
• Documentation — docs/vision.md with project story, roadmap, and agent discoverability (#133).

Changed

• finance/wallet_screening — Unified TRM/scam transaction risk index for analysis (#140).
• SECURITY.md — Supported-version table aligned with >= 0.3.1 security support and unsupported < 0.2.6 band (#132).
• CLI — Version advisory runs once at main() startup, not on menu re-loops (#132).
• Dependencies — Added packaging for semver comparisons (#132).
• Documentation — README Mission links to vision.md; comparison table and docs cross-links updated (#133).

Upgrade

Core package (skills, loader, issue_resolver):

pip install -U skillware

CLI users (version advisory on skillware list / menu):

pip install -U "skillware[cli]"

---

Contributors

Thanks to everyone who shipped between v0.3.2 and v0.3.3:

• @rosspeili — dev_tools/issue_resolver v0.2 workflow and commit gate (#143); runnable Gemini/Claude/Ollama examples (#118); version support policy and CLI advisory (#132); vision docs and README refresh (#133)
• @Hendobox — finance/wallet_screening TRM/scam tx risk index (#140)

---

Full changelog

• #118 — Runnable agent-loop examples for dev_tools/issue_resolver
• #132 — Version support policy and CLI advisory for unsupported installs
• #133 — Vision doc and README / docs refresh
• #140 — wallet_screening unified TRM/scam tx risk index
• #143 — Universal issue resolver workflow stages and commit gate

Compare: v0.3.2...v0.3.3

v0.3.2 — CHANGELOG, wallet screening, CLI polish, contributor docs

Skillware v0.3.2

Added

• Root CHANGELOG.md — Keep a Changelog format with retrospective history from v0.2.0; linked from README nav and docs (#108).
• finance/wallet_screening — FTM publicKey matching and ETH sanctions index for faster local screening (#128).

Changed

• CLI visual redesign — Pastel skillware list table, short_description column, interactive splash and menu (#129).
• CLI polish — Splash footer links, menu re-loop, stub labels for #81 / #83, width-aware table (#130, #131).
• Contributor docs — Code of Conduct contribution process, CHANGELOG maintenance in CONTRIBUTING and agent workflow, PR template checkbox (#124).
• Documentation — Changelog links in README docs table and docs/introduction.md; optional short_description in skill template (#130).

Upgrade

pip install -U "skillware[cli]"

---

Contributors

Thanks to everyone who shipped between v0.3.1 and v0.3.2:

• @Avonaxe — retrospective CHANGELOG.md and README link (#108)
• @Hendobox — finance/wallet_screening sanctions index (#128)
• @rizzoMartin — CLI visual redesign (#129) and interactive polish (#130, #131)
• @rosspeili — contributor docs and CHANGELOG workflow (#124)

---

Full changelog

• #108 — Add retrospective CHANGELOG.md and link in README
• #124 — Align Code of Conduct, CONTRIBUTING, and agent workflow for CHANGELOG maintenance
• #128 — wallet_screening FTM publicKey matching and ETH sanctions index
• #129 — CLI visual redesign (pastel theme, short descriptions, interactive menu)
• #130 — CLI visual polish and UX
• #131 — CLI polish follow-up (cli.md, tests, template ripple)

Compare: v0.3.1...v0.3.2

v0.3.1 — Novelty Extractor skill, google-genai migration, examples index

Skillware v0.3.1

Added

• data_engineering/novelty_extractor skill (#116, fixes #24), local semantic novelty filtering via fastembed (BAAI/bge-small-en-v1.5); multi-turn distillation via baseline_chunks; catalog page, tests, and runnable examples (novelty_extractor_demo.py, gemini_novelty_extractor.py, ollama_novelty_extractor.py).
• examples/README.md, canonical index of runnable provider scripts (#107).

Changed

• Gemini SDK migration, moved from deprecated google-generativeai to google-genai (#97); usage docs and snippets updated (#92).
• Documentation, README navigation and skill catalog discoverability (#98); runnable examples cross-linked on skill catalog pages (#121); agent_loops.md matrix synced with the examples index (#122).

Notes

• novelty_extractor requires pip install fastembed numpy (manifest deps; not bundled in base install).
• First run downloads the embedding model (~50 MB) to local cache.
• Tag v0.3.1 when ready, version bump is on main at 60021d9.

Contributors

Thanks to everyone who shipped between v0.2.9 and v0.3.1:

• @rizzoMartin — data_engineering/novelty_extractor (#116)
• @CleanDev-Fix — examples index (#107)
• @narutamaaurum — skill catalog runnable examples (#121)
• @choucaleb602-commits — examples index follow-up (#122)
• @kunal-9090 — Gemini docs snippets (#92)
• @rosspeili — google-genai migration (#97), README navigation (#98)

v0.2.9 — CLI & Dependency Cleanup

What's new

🖥️ skillware list — CLI for skill discovery

The framework now ships a skillware command-line tool. After install, run:

pip install "skillware[cli]"
skillware list

This prints a rich table of every locally installed skill — ID, version, category, issuer, description, and requirements — using the same path resolution order as SkillLoader.load_skill(). Skills are discovered across SKILLWARE_SKILL_PATH, the skills/ directory under your working directory, and bundled package skills.

Filtering:

skillware list --category compliance
skillware list --issuer rosspeili
skillware list --skills-root /path/to/my/skills

The CLI entrypoint is intentionally extensible — follow-on commands (paths, doctor, test) are tracked in #81, #83, and #86.

See the CLI Reference for full documentation.

---

📦 Leaner core install — SDK dependencies are now optional extras

pip install skillware no longer forces anthropic, google-generativeai, pymupdf, or openai on every user. These are skill-specific SDKs, not framework dependencies. Install only what your skills actually need:

Extra	Installs
skillware[cli]	rich>=13.0
skillware[gemini]	google-generativeai
skillware[claude]	anthropic
skillware[openai]	openai
skillware[office]	pymupdf
skillware[all]	all of the above
skillware[dev]	pytest, flake8, black

The core install now only requires requests, pyyaml, python-dotenv, and beautifulsoup4.

requirements.txt has been updated to reflect this — it now serves as a dev-convenience pointer to pip install -e ".[dev,all]" rather than a duplicate flat dependency list. All dependency management lives in pyproject.toml.

---

Contributors

• @rizzoMartin — CLI implementation (skillware list, skillware/cli.py, tests/test_cli.py, docs) — first open-source contribution 🎉

---

Full changelog

• #84 — Add skillware list CLI command for skill discovery
• #87 — Move SDK deps to optional extras, slim requirements.txt, bump to v0.2.9

v0.2.8 — Issue Resolver skill and dev_tools category

New Skills

dev_tools/issue_resolver

A universal GitHub issue analysis and resolution skill. Give it any public GitHub issue URL and it validates and normalises the input, resolves the GitHub token, and returns a structured status: ready payload containing all pre-computed GitHub API and raw content URLs the calling agent needs to begin work.

The calling agent follows a five-stage workflow defined in instructions.md: fetch the issue (body, labels, comments, linked PRs), read the repository context (README, CONTRIBUTING, directory tree), analyse affected files and ripple effects, produce a ranked resolution plan, and implement only after explicit user approval. The skill makes no network calls itself and has no runtime dependencies beyond PyYAML.

• Supports any public GitHub repository
• Optional github_token parameter (overrides GITHUB_TOKEN env var) for authenticated API access
• Optional extra_instructions parameter for project-specific context injection
• Compatible with all five provider adapters (Gemini, Claude, OpenAI, DeepSeek, Ollama)
• Introduces the new dev_tools skill category

Closes #56.

---

Documentation

Skill catalog revamp (#82)

Full overhaul of docs/skills/ — all skill catalog pages now include a breadcrumb trail, per-provider Usage Examples (Gemini, Claude, OpenAI, DeepSeek, Ollama), environment variable tables linking to the API keys guide, data schema blocks, and a limitations section. Emojis removed from all catalog pages and the skills README index. Closes #52.

---

Bug Fixes

• Fixed pyproject.toml author name (ARPA Hellenic Logic Systems corrected to ARPA Hellenic Logical Systems).

---

What's Changed

Commit	Description
5ae3a82	chore: bump package version to 0.2.8
8b829e6	Add dev_tools/issue_resolver skill
cca7334	docs: skill docs revamp — remove emojis, add breadcrumbs, fix index, add missing sections (#82)

Full changelog: v0.2.7...v0.2.8

v0.2.7 — Pip skill paths and full wheel bundles

Bug fixes

• Skill loader paths after pip install (#13)
  SkillLoader.load_skill("category/skill_name") no longer resolves only under site-packages/skills/. The loader now searches, in order:

  1. An existing path on disk (absolute or relative skill directory)
  2. Roots in SKILLWARE_SKILL_PATH (multiple paths separated by your OS path separator)
  3. A skills/ folder in the current working directory (and up to six parent directories)
  4. Bundled registry skills shipped with the package

  If nothing matches, the error lists the paths that were tried.

Packaging

• Full skill bundles on PyPI — Wheels now include manifest.yaml, instructions.md, card.json, and skill data files, not only .py modules.
• MANIFEST.in grafts the skills/ tree; [tool.setuptools.package-data] uses skills = ["**/*"] so new registry skills do not require per-skill pyproject.toml edits.
• Registry layout — Empty __init__.py files under skills/ category packages (and skill folders where needed) so setuptools packages the complete tree.

Documentation

• Usage guide: Finding skills on disk
• Contributor notes for PyPI packaging (CONTRIBUTING.md, skill template README)

Upgrade notes

• Clone / editable install: Behavior is unchanged for normal development from the repo root.
• Pip consumers: Place project skills in ./skills/<category>/<name>/, or set SKILLWARE_SKILL_PATH to your skills root. Registry IDs like compliance/tos_evaluator still work and now load complete manifests from the installed package.
• New registry skills: Add empty __init__.py in new category and skill directories (enforced in tests); do not add entries to pyproject.toml per skill.

Verification

pip install skillware==0.2.7
pytest tests/   # for contributors cloning the repo

v0.2.6 — Multi-Provider Integration Release

This release expands model adapters, documents how to run every skill across providers, and strengthens contributor and registry metadata.

---

Framework

• OpenAI adapter (SkillLoader.to_openai_tool()) for Chat Completions tool calling (#68)
• DeepSeek adapter (SkillLoader.to_deepseek_tool()) as a separate public API (#70)
• Shared function-name sanitization for OpenAI-compatible providers

---

Documentation

Provider integration

• OpenAI usage guide and examples/openai_tos_evaluator.py (#69)
• DeepSeek usage guide and examples/deepseek_tos_evaluator.py (#70)
• Usage guides index, agent loops, and skill usage template (#71)
• Usage Examples on all seven skill catalog pages (Gemini, Claude, OpenAI, DeepSeek, Ollama) (#71)
• API keys for skills — generic setup guide (#67)
• README links to usage index and agent loops; Ollama guide updated for current local models (#71)

Contributing & workflow

• CONTRIBUTING.md restructured; contribution types and skill standards (#64)
• Agent Contribution Workflow — agent-directed guide (#64, #65)
• Usage Examples requirement aligned in CONTRIBUTING and agent workflow (#71)

Registry & catalog

• Issuer attribution on all skills (manifest.yaml, card.json, docs/skills/*.md, catalog) (#63)
• Enterprise disclaimer on ARPA catalog skill pages (#59, #62)

---

Tests

• tests/test_skill_issuer.py — registry issuer validation (#63)

---

Upgrade

pip install -U skillware==0.2.6

v0.2.5 - TOS Evaluator

Release Notes - v0.2.5

Added

• New skill: compliance/tos_evaluator
  • Local-first website policy evaluation before automated access.
  • Checks robots.txt permissions for the target URL/path and user-agent.
  • Discovers candidate legal pages (Terms, Legal, Acceptable Use, API-related links).
  • Extracts and evaluates policy clauses relevant to automated behaviors (scraping, crawling, indexing, monitoring, downloading, API use).
  • Returns structured verdicts: SAFE, UNSAFE, CAUTION, INSUFFICIENT_EVIDENCE.
  • Includes evidence payloads and recommended next-step guidance.
  • Optional low-cost LLM fallback for ambiguous clauses (Gemini model shown as example; interface remains provider/model configurable).

Skill Package Contents

• Added skills/compliance/tos_evaluator/:
  • manifest.yaml
  • skill.py
  • instructions.md
  • card.json
  • __init__.py
  • test_skill.py

Tests

• Added focused central tests:
  • tests/skills/compliance/test_tos_evaluator.py
• Added local skill test:
  • skills/compliance/tos_evaluator/test_skill.py

Documentation

• Added skill documentation:
  • docs/skills/tos_evaluator.md
• Updated skill catalog:
  • docs/skills/README.md (Compliance section now includes compliance/tos_evaluator)

Examples

• Added integration examples:
  • examples/gemini_tos_evaluator.py
  • examples/claude_tos_evaluator.py
  • examples/ollama_tos_evaluator.py

Dependencies

• Added HTML parsing dependency for deterministic policy extraction:
  • beautifulsoup4 (project dependency)
• Skill manifest requirement uses import-resolvable package name:
  • bs4

Packaging

• Bumped package version:
  • pyproject.toml: 0.2.4 -> 0.2.5

v0.2.4 - MiCA Compliance Module and PII Masking Implementation

This release introduces major compliance capabilities and framework optimizations focused on high-performance agentic workflows.

Key Changes:

1. MiCA Compliance Module: Added the compliance/mica_module skill, featuring in-memory caching for ultra-low latency RAG (~1.7ms) and a weighted surgical router to prevent context window asphyxiation.
2. PII Masking: Integrated the compliance/pii_masker skill for high-precision, local privacy guardrails using micro-f1-masking.
3. Pure Cognitive Framework: Realigned all MiCA examples (Gemini, Claude, Ollama) to follow a prompt-based cognitive pattern that avoids opaque native tool-calling obstacles.
4. Documentation: Comprehensive documentation updates for the new Compliance category and a refined core README.
5. Quality Engineering: Resolved all PEP 8 and Flake8 violations across the registry and verified execution with 100% unit test success.
6. Versioning: Framework version bumped to 0.2.4.

This release ensures that Skillware agents can operate in highly regulated environments with deterministic precision and local privacy.