hermes-agent/skills
Teknium fdefd98aa3 docs(skills): make descriptions self-contained, not cross-dependent
Previous pass assumed both skills would always be loaded together, so
each description pointed at the other ('use concept-diagrams instead').
That breaks when only one skill is active — the agent reads 'use the
other skill' and there is no other skill.

Now each skill's description and scope section is fully self-contained:

- States what it's best suited for
- Lists subjects where a more specialized skill (if available) would be
  a better fit, naming them only as 'consider X if available'
- Explicitly offers itself as a general SVG diagram fallback when no
  more specialized skill exists

An agent loading either skill alone gets unambiguous guidance; an
agent with both loaded still gets useful routing via the 'consider X
if available' hints and the related_skills metadata.
2026-04-16 20:39:55 -07:00
..
apple feat: secure skill env setup on load (core #688) 2026-03-13 03:14:04 -07:00
autonomous-ai-agents docs: fix stale hermes login references in hermes-agent skill (#10603) 2026-04-15 17:43:54 -07:00
creative docs(skills): make descriptions self-contained, not cross-dependent 2026-04-16 20:39:55 -07:00
data-science feat: restore ACP server implementation from PR #949 (#1254) 2026-03-14 00:09:05 -07:00
devops/webhook-subscriptions feat(webhook): hermes webhook CLI + skill for event-driven subscriptions (#3578) 2026-03-28 14:33:35 -07:00
diagramming refactor: reorganize skills into sub-categories 2026-03-09 03:35:53 -07:00
dogfood refactor: remove browser_close tool — auto-cleanup handles it (#5792) 2026-04-07 03:28:44 -07:00
domain refactor: reorganize skills into sub-categories 2026-03-09 03:35:53 -07:00
email feat: secure skill env setup on load (core #688) 2026-03-13 03:14:04 -07:00
feeds refactor: reorganize skills into sub-categories 2026-03-09 03:35:53 -07:00
gaming feat: add pokemon-player skill with battle-tested gameplay tips 2026-03-09 20:29:38 -07:00
gifs refactor: reorganize skills into sub-categories 2026-03-09 03:35:53 -07:00
github fix: five HERMES_HOME profile-isolation leaks (#10570) 2026-04-15 17:09:41 -07:00
index-cache Release set of skills 2026-02-25 05:21:17 -08:00
inference-sh feat(gateway): skill-aware slash commands, paginated /commands, Telegram 100-cap (#3934) 2026-03-30 10:57:30 -07:00
leisure/find-nearby fix(skills): use is None check for coordinates in find-nearby to avoid dropping valid 0.0 values 2026-04-15 03:45:09 -07:00
mcp feat: secure skill env setup on load (core #688) 2026-03-13 03:14:04 -07:00
media docs: improve youtube-content skill structure and workflow 2026-04-03 22:18:00 -07:00
mlops refactor: codebase-wide lint cleanup — unused imports, dead code, and inefficient patterns (#5821) 2026-04-07 10:25:31 -07:00
note-taking refactor: update Obsidian vault path handling 2026-02-25 20:24:51 -08:00
productivity fix(google-workspace): normalize authorized user token writes 2026-04-16 04:22:16 -07:00
red-teaming/godmode fix: five HERMES_HOME profile-isolation leaks (#10570) 2026-04-15 17:09:41 -07:00
research fix: stop hermes update from nagging about llm-wiki's wiki.path (#11222) 2026-04-16 13:34:16 -07:00
smart-home feat: secure skill env setup on load (core #688) 2026-03-13 03:14:04 -07:00
social-media feat(skills): add X/Twitter xitter skill via upstream x-cli (#1285) 2026-03-14 04:00:27 -07:00
software-development refactor(skills): consolidate code verification skills into one (#4854) 2026-04-03 14:13:27 -07:00