added the skill

[7007259Ankur]

Summary

Type of change

• New skill
• Update to an existing skill
• Tests
• Repository tooling or CI
• Documentation
• Other:

Skills touched

How this was tested

uv run skills-ref validate ./skills/<name>
uv run --with pytest python -m pytest tests/<name> -q

Related issues and references

---

Checklist

Drawn from the Pull Request Checklist in CONTRIBUTING.md. Items that do not apply to this PR can be left unchecked with a short note.

Skill format

• The skill directory name and the name frontmatter match exactly.
• The skill directory contains only SKILL.md, references/, scripts/, and assets/ — no tests/ directory and no test_*.py files.
• SKILL.md has valid YAML frontmatter and a Markdown body.
• Only the six spec-defined top-level fields are present; everything else lives under metadata.
• metadata is a block mapping, not single-line JSON, and scalar values are quoted where needed.
• Any metadata.openclaw or metadata.hermes block is a nested mapping, not a JSON string.
• metadata.version exists, is quoted, and is bumped if an existing skill changed.
• The description says both what the skill does and when an agent should use it.

Validation and tests

• uv run skills-ref validate ./skills/<name> passes.
• Tests live in tests/<skill-name>/, and any new scripts/ skill has a [skills.<name>] entry in tests/skill-requirements.toml.
• Relevant test suites pass, or the failures are explained below.
• Security scanner results are clean or explained in this PR.

Content and safety

• Examples and scripts were tested, or are clearly marked as illustrative.
• No secrets, credentials, private data, or unsafe instructions are included.
• Credentials the skill needs are named in compatibility and declared in metadata.openclaw.envVars.
• Relevant official documentation is linked where useful.

Notes for reviewers

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: b0fe677b16

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Remove the out-of-scope runtime-safety skill

This applies to every local coding-agent harness and only narrows its trigger by saying “scientific workflows”; it is not a skill for a particular scientific package, database, platform, or research workflow. Adding it makes general runtime infrastructure selectable alongside all specialist skills, which the repository explicitly declines because it competes across tasks.

AGENTS.md reference: AGENTS.md:L17-L19

Useful? React with 👍 / 👎.

[chatgpt-codex-connector]

Declare the required pipx and network environment

The frontmatter provides no compatibility requirements even though the prescribed first step requires both pipx and access to install a package from a package index. In offline or pipx-less environments, agents have no discovery-time indication that this skill cannot run and will select it only to fail at its first command; declare those system and network requirements.

AGENTS.md reference: AGENTS.md:L186-L186

Useful? React with 👍 / 👎.

[7007259Ankur]

I have investigated the issue. Both feedback comments apply to the hol-guard-agent-runtime-safety
skill, as it was the only one that used pipx install in its prescribed first step and functioned
as an out-of-scope general runtime infrastructure rather than a specialist scientific tool (as
explicitly noted as out-of-scope in AGENTS.md).

I have resolved both requests by completely removing the hol-guard-agent-runtime-safety skill
directory (skills/hol-guard-agent-runtime-safety). Since the skill itself has been removed from
the repository, the missing compatibility requirements for pipx and network access no longer need
to be addressed.