docs(hermes): fix skill activation instructions

[Lukyyyyy]

Summary

Fix the Hermes installation documentation to accurately describe how the i-have-adhd skill is activated.

The current documentation instructs users to type /i-have-adhd and states that the skill is exposed as a slash command. However, Hermes does not expose installed skills as per-skill slash commands.

This change:

• removes the incorrect /i-have-adhd activation instruction
• documents explicit natural-language activation of the skill
• notes that Hermes may load the skill automatically when the conversation matches its description
• updates the Chinese installation guide to keep it synchronized with the English documentation

Before this change, Hermes users could follow the documented /i-have-adhd instruction and find that it does not work. After this change, the documentation reflects the actual skill activation behavior.

Fixes #118.

Authorship and provenance — select exactly one

• Human-authored — substantive implementation and text were produced by a human.
• Autonomous agent-authored — an agent planned and produced most of the substantive change.
• Hybrid — a human and one or more agents both made substantive contributions.

Agent/tool and model/version: ChatGPT, GPT-5.6 Sol

Agent contribution: Helped analyze issue #118, identify the affected documentation, propose the documentation changes, and review the PR structure and wording.

Human verification: I reviewed issue #118, manually reviewed the English and Chinese Hermes installation documentation, reviewed the complete diff, and ran git diff --check.

Known limitations or uncertain results: None known.

Labels

Target label: Target:Docs

Author label: Author:Hybrid

Workflow labels: bug

Safety and side effects

• The change does not access or expose secrets, private files, or unrelated user/repository data.
• Scripts, hooks, workflows, and evals are bounded and do not create surprising or irreversible side effects.
• No destructive, privileged, production, externally visible, or persistent action occurs without explicit user intent and appropriate safeguards.
• Network access, third-party code, permissions, and provider costs are minimized and documented.
• Prompt text, examples, and fixtures contain no hidden instructions that weaken safety or expand agent authority.

Side effects, permissions, network access, and cost:

None. This is a documentation-only change and introduces no runtime behavior, permissions, network access, or additional cost.

Compatibility

• This is not a breaking change.
• This is a breaking change; it was discussed, and migration/deprecation documentation is included below.
• Canonical and mirrored skill files are synchronized when applicable.
• Relevant platform manifests and installation documentation were reviewed.

Migration or rollback notes:

No migration is required. This change only corrects the documented Hermes activation instructions. It can be rolled back by reverting the documentation changes.

Verification

• git diff --check — passed with no whitespace errors
• Manual review of INSTALL.md — Hermes activation instructions correctly describe natural-language activation
• Manual review of .github/install/INSTALL.zh-CN.md — Chinese Hermes instructions are synchronized with the English documentation

Behavior evals: Not applicable. This PR only changes installation documentation and does not modify skill behavior.

Final accountability

• I reviewed the complete diff, removed unrelated generated changes, and take responsibility for the submitted content.
• All failed, skipped, or unrun checks are disclosed above.