⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
tracemantle
Validates and scores SKILL.md files against the agentskills.io specification; use when linting skills for cross-agent compatibility, description quality, or capability graph structure.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
// README
About the project
TraceMantle is a Python CLI and library for checking agent skill bundles before they are committed or released. It provides:
- Skill validation: checks
SKILL.mdfrontmatter, file references, size limits and compatibility advice against the Agent Skills specification. - Bundle tracking: hashes skill files and packaged resources so helper changes are detected too.
- Evidence checks: imports evaluator results and compares bundles against trusted policies. Missing, stale or incompatible evidence blocks the gate.
TraceMantle analyzes files; it does not execute skills or evaluators. Static checks and imported model judgments do not prove that a skill works in a live agent.
Getting started
Requires Python 3.10 or later. Install in a virtual environment:
python -m venv .venv
source .venv/bin/activate
python -m pip install tracemantle==1.6.1
tracemantle --version
Version 1.6.1 corrects dependency discovery across Markdown headings and rejects numeric overflow in evidence imports. See the changelog and implementation ledger for behavior and verification.
On Windows PowerShell, activate with .venv\Scripts\Activate.ps1. Replacing SkillCheck? Follow the migration guide before installing.
Usage
Validate a skill, scan a directory, or inspect a bundle:
tracemantle path/to/SKILL.md
tracemantle path/to/skills/ --strict --format json
tracemantle path/to/SKILL.md --analyze-graph
tracemantle manifest path/to/skill --format json
Validation exits 0 when it passes and nonzero on errors; --strict also fails on warnings. Text, JSON and GitHub annotation output are supported.
For release evidence, use import-evidence and compare with a trusted base revision and approved evidence. The evidence workflow covers setup, supported imports and runnable examples.
Configure defaults in tracemantle.toml or [tool.tracemantle] in pyproject.toml. Explicit CLI flags take precedence. Token counting uses an offline estimate by default; optional tiktoken counting must be selected explicitly.
See the CLI and configuration reference, compatibility profiles and input limits for details.
Integrations
Use the composite GitHub Action pinned to a release:
- uses: moonrunnerkc/[email protected]
with:
path: skills/
Action inputs control validation and reporting. Versions before 1.6.0 contain the older SkillCheck implementation. A pre-commit hook, Python API and installed skill are also included.
Contributing
1407 tests cover validation, CLI integrations, bundle identity and evidence checks. CI runs Python 3.10 through 3.13 on Linux, macOS and Windows, plus optional-tokenizer and clean package-install checks.
See CONTRIBUTING.md for development setup and verification. Submit fixes through pull requests; use issues for bugs and proposals. Changes are recorded in the changelog.
License and contact
MIT. Maintained by moonrunnerkc, Aftermath Technologies Ltd.
// HOW IT'S BUILT
KEY FILES