# NousResearch/hermes-agent · Inline skill mention syntax via $ prefix

## Open now

- 1 issue, 2 PRs open on GitHub.
- #64601: feat(cli): inline skill mentions with $ prefix (Codex-style) for natural skill chaining
- PR #64852: feat(skills): let users mention skills inline
- PR #64905: feat(cli): inline $skill-name mentions for mid-prompt skill invocation

These items all concern adding support for mentioning or invoking skills inline within prompts using a $ prefix syntax. The feature enables natural mid-prompt skill chaining without interrupting the user's input flow.

## TL;DR

- 3 member(s): 1 open issue(s), 0 closed issue(s), 2 open PR(s), 0 merged PR(s), 0 PR(s) closed without merging.
- No fix has been merged to main; one or more PRs were attempted (see below).
- **Recommended:** review the prior/competing PR(s) below. A fix was attempted but not merged; your case may extend or revive that work.

## Maintainer resolution verdict

- Internal-tracker verdict over this cluster's issue members: `unresolved`. This is distinct from the fix status above. Weigh it yourself.

## How this cluster was grouped

- Link evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
- Pairwise link density `0.67`: the share of member pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. `1.00` means every pair is linked.

## Open related issues

- #64601: feat(cli): inline skill mentions with $ prefix (Codex-style) for natural skill chaining

## Prior & competing PRs

- **#64852: feat(skills): let users mention skills inline**. open
  - maintainer direction: category `partial_fix`; implication `needs_llm`; refs `cd82f2c56dd7`, `#64601`, `#64852`, `#64905`, `#374151`
  - files: `agent/conversation_loop.py`, `agent/skill_commands.py`, `tests/agent/test_inline_skill_mentions.py`, `website/docs/user-guide/features/skills.md`
- **#64905: feat(cli): inline $skill-name mentions for mid-prompt skill invocation**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `agent/conversation_loop.py`, `agent/skill_commands.py`, `cli-config.yaml.example`, `hermes_cli/config.py`, `run_agent.py`, `tests/agent/test_skill_commands.py`, `tests/run_agent/test_run_agent.py`, `website/docs/user-guide/features/skills.md`

## Fix status

- No merged fix on record.
- Subsystem: `skills`