Terminator v0.2.1

Quality hardening — closes the residual findings from the pre-launch review.

Added

• Validator test suite (tests/test_validate_repo.py): eight unittest cases run the validator against synthetic repository fixtures and prove it catches missing files, invalid or unclosed frontmatter, version mismatches, invalid JSON, non-English residue, and banned positioning phrases — and that a valid tree passes.
• Continuous integration runs the test suite before repository validation on every push and pull request.

Improved

• The validator lists its own script and test suite among the required repository files.
• The release snapshot now includes the enriched README (protocol table, representative run report, design principles, FAQ).
• The contributing guide documents the test command.

Install: copy skills/terminator/ into the skills folder used by your agent environment, then invoke with Use Terminator to <objective>.

Terminator v0.2.0

Orchestration protocol refinement — this release upgrades the skill instructions themselves, based on a design review of how agents behave across small, large, and very different repositories.

Added

• Proportionality and scope rules: the protocol scales with the objective; small goals compress scanning, discovery, and planning into one pass, while verification and the final report are never skipped. Out-of-scope discoveries become recommendations, not actions.
• Plan-presentation rule: large, ambiguous, or high-impact objectives receive the orchestration plan before execution; small unambiguous objectives execute directly.
• Tool selection rules: confirm availability before planning around a tool, prefer dedicated over generic tools, keep discovery read-only, parallelize independent steps where supported, verify with deterministic checks.
• Report STATUS vocabulary: Complete, Partial, Blocked, or Ready — reports are now comparable across runs and environments.

Improved

• Verification is evidence-bound: success is never reported without at least one concrete check; unverifiable results are stated under LIMITS.
• Compact Tool Registry field names aligned with the tool discovery guide.
• Specification updated to match the refined protocol.

Install: copy skills/terminator/ into the skills folder used by your agent environment, then invoke with Use Terminator to <objective>.

Terminator v0.1.3

Public release polish: the repository is now easier to understand at a glance, validates itself, and completes the English-only, vendor-neutral presentation.

Improved

• README rewritten for a ten-second overview: badges, quickstart, installation verification, safety rules, output format, and an example index.
• SKILL.md frontmatter extended with license and versioned metadata, following the Agent Skills specification.
• Skill manifest description and version aligned with the instruction file.

Added

• scripts/validate_repo.py: locally runnable validation covering required files, SKILL.md frontmatter rules, JSON validity, version consistency, an English-only documentation scan, and positioning checks.
• Continuous integration now runs the shared validation script on every push and pull request.

Fixed

• Removed the last non-English lines from the skill package README and historical release notes.
• Renamed the readiness example to examples/readiness-check.md.
• Replaced the hardcoded CI version pin with cross-file version consistency checks.

Install: copy skills/terminator/ into the skills folder used by your agent environment, then invoke with Use Terminator to <objective>.

Terminator v0.1.2

Package format fix.

This release updates the installable package so compatible agent environments can discover it correctly.

Updated:

• Added required YAML metadata to the main instruction file.
• Added repository validation for required metadata.
• Updated README and specification with the installable package structure.
• Kept the repository fully English.

Invocation:
Use Terminator to ...

Terminator

Terminator v0.1.1

Compatibility wording update.

This release clarifies Terminator as an environment-adaptive orchestration skill for compatible AI agent environments.

Updated:

• Removed terminal-only positioning from public documentation.
• Made public-facing repository content fully English.
• Updated the skill manifest version to 0.1.1.
• Preserved the same orchestration protocol and installation structure.

Core protocol:
Goal → Context Scan → Tool Discovery → Tool Registry → Plan → Orchestration → Execution → Verification → Report

Invocation:
Use Terminator to ...

Terminator

Terminator v0.1.0

Initial public release of Terminator.

Terminator is a terminal-first, environment-adaptive orchestration skill for AI agents. It turns user-defined goals into executable multi-tool workflows by discovering the tools available in the current environment, building a Tool Registry, planning the workflow, coordinating execution, handling blockers, and verifying the result.

Included:

• Portable Terminator skill structure
• Main skill instructions in skills/terminator/SKILL.md
• Skill manifest in skills/terminator/skill.json
• Public README
• Usage documentation
• Tool discovery guide
• Workflow examples
• Linux/macOS installer
• Windows PowerShell installer
• Repository validation workflow
• MIT License

Invocation:
Use Terminator to ...

Usa Terminator per ...

Terminator

Core protocol:
Goal → Context Scan → Tool Discovery → Tool Registry → Plan → Orchestration → Execution → Verification → Report