Agent skill
hermes-skill-source-classification
Diagnose Hermes `hermes skills list` source labels (`builtin` vs `local`) and avoid false sync decisions.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/hermes-skill-source-classification
SKILL.md
Hermes skill source classification
Use this when hermes skills list shows source=builtin for skills that also exist in local skill directories.
Key finding
Hermes source labeling is name-manifest based:
- if a skill name appears in
~/.hermes/skills/.bundled_manifest, the CLI may label it asbuiltin - this can happen even when a local copy exists at
~/.hermes/skills/<category>/<name>/
So builtin does not always mean “no local copy”.
Verification workflow
- Check label:
hermes skills list --source all | grep -E '<skill-name>'
- Check bundled manifest hit:
grep -nE '^<skill-name>:' ~/.hermes/skills/.bundled_manifest
- Check both physical paths:
test -f ~/.hermes/hermes-agent/skills/<category>/<skill-name>/SKILL.md && echo bundled_exists
test -f ~/.hermes/skills/<category>/<skill-name>/SKILL.md && echo local_exists
Sync decision rule
For repo/local sync scripts, do not use only --source local as truth.
Use a combined rule:
- source label
- local path existence
- repo path existence
Pitfall
A skill may be misclassified as repo-only if your script trusts source label alone. This can trigger unnecessary sync prompts.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?