Skill catalog pages (bundled/optional) were drowning out real user-guide and reference docs in search results. There are ~3100 of them and they match on almost every generic term. - Add `ignoreFiles` regexes to docusaurus-search-local for `user-guide/skills/bundled/` and `user-guide/skills/optional/`. The two human-written catalog indexes (`reference/skills-catalog`, `reference/optional-skills-catalog`) remain indexed. - Add a new feature page `user-guide/features/curator.md` covering the curator subsystem merged in #16049 and refined in #17307 (per-run reports): how it runs, config, CLI (`hermes curator status/run/pin/ restore/...`), `.usage.json` telemetry, archival semantics, and recovery. Slotted into the Core features sidebar next to Skills. Search index size dropped from 5822 docs to 2704 in the main section; `user-guide/features/curator` is indexed.
7.1 KiB
| sidebar_position | title | description |
|---|---|---|
| 3 | Curator | Background maintenance for agent-created skills — usage tracking, staleness, archival, and LLM-driven review |
Curator
The curator is a background maintenance pass for agent-created skills. It tracks how often each skill is viewed, used, and patched, moves long-unused skills through active → stale → archived states, and periodically spawns a short auxiliary-model review that proposes consolidations or patches drift.
It exists so that skills created via the self-improvement loop don't pile up forever. Every time the agent solves a novel problem and saves a skill, that skill lands in ~/.hermes/skills/. Without maintenance, you end up with dozens of narrow near-duplicates that pollute the catalog and waste tokens.
The curator never touches bundled skills (shipped with the repo) or hub-installed skills (from agentskills.io). It only reviews skills the agent itself authored. It also never auto-deletes — the worst outcome is archival into ~/.hermes/skills/.archive/, which is recoverable.
Tracks issue #7816.
How it runs
The curator is triggered by an inactivity check, not a cron daemon. On CLI session start, and on a recurring tick inside the gateway's cron-ticker thread, Hermes checks whether:
- Enough time has passed since the last curator run (
interval_hours, default 7 days), and - The agent has been idle long enough (
min_idle_hours, default 2 hours).
If both are true, it spawns a background fork of AIAgent — the same pattern used by the memory/skill self-improvement nudges. The fork runs in its own prompt cache and never touches the active conversation.
A run has two phases:
- Automatic transitions (deterministic, no LLM). Skills unused for
stale_after_days(30) becomestale; skills unused forarchive_after_days(90) are moved to~/.hermes/skills/.archive/. - LLM review (single aux-model pass,
max_iterations=8). The forked agent surveys the agent-created skills, can read any of them withskill_view, and decides per-skill whether to keep, patch (viaskill_manage), consolidate overlapping ones, or archive via the terminal tool.
Pinned skills bypass all auto-transitions and the LLM is instructed not to touch them.
Configuration
All settings live in config.yaml under curator: (not .env — this isn't a secret). Defaults:
curator:
enabled: true
interval_hours: 168 # 7 days
min_idle_hours: 2
stale_after_days: 30
archive_after_days: 90
auxiliary:
provider: null # null = use main auxiliary client resolution
model: null
To disable entirely, set curator.enabled: false.
To use a cheaper aux model for the LLM review pass instead of your main model, set curator.auxiliary.provider and curator.auxiliary.model to something specific (e.g. openrouter + google/gemini-3-flash-preview).
CLI
hermes curator status # last run, counts, pinned list, LRU top 5
hermes curator run # trigger a review now (background by default)
hermes curator run --sync # same, but block until the LLM pass finishes
hermes curator pause # stop runs until resumed
hermes curator resume
hermes curator pin <skill> # never auto-transition this skill
hermes curator unpin <skill>
hermes curator restore <skill> # move an archived skill back to active
hermes curator status also lists the five least-recently-used skills — a quick way to see what's likely to become stale next.
The same subcommands are available as the /curator slash command inside a running session (CLI or gateway platforms).
What "agent-created" means
A skill is considered agent-created if its name is not in:
~/.hermes/skills/.bundled_manifest(skills copied from the repo on install), and~/.hermes/skills/.hub/lock.json(skills installed viahermes skills install).
Everything else in ~/.hermes/skills/ is fair game for the curator. This includes:
- Skills the agent saved via
skill_manage(action="create")during a conversation. - Skills you created manually with a hand-written
SKILL.md. - Skills added via external skill directories you've pointed Hermes at.
If you want to protect a specific skill from ever being touched — for example a hand-authored skill you rely on — use hermes curator pin <name>. The pin is a hard guarantee enforced at the shared mutation helper; no code path that would archive, consolidate, or state-transition a skill can bypass it.
Usage telemetry
The curator maintains a sidecar at ~/.hermes/skills/.usage.json with one entry per skill:
{
"my-skill": {
"use_count": 12,
"view_count": 34,
"last_used_at": "2026-04-24T18:12:03Z",
"last_viewed_at": "2026-04-23T09:44:17Z",
"patch_count": 3,
"last_patched_at": "2026-04-20T22:01:55Z",
"created_at": "2026-03-01T14:20:00Z",
"state": "active",
"pinned": false,
"archived_at": null
}
}
Counters increment when:
view_count: the agent callsskill_viewon the skill.use_count: the skill is loaded into a conversation's prompt.patch_count:skill_manage patch/edit/write_file/remove_fileruns on the skill.
Bundled and hub-installed skills are explicitly excluded from telemetry writes.
Per-run reports
Every curator run writes a timestamped directory under ~/.hermes/logs/curator/:
~/.hermes/logs/curator/
└── 20260429-111512/
├── run.json # machine-readable: full fidelity, stats, LLM output
└── REPORT.md # human-readable summary
REPORT.md is a quick way to see what a given run did — which skills transitioned, what the LLM reviewer said, which skills it patched. Good for auditing without having to grep agent.log.
Restoring an archived skill
If the curator archived something you still want:
hermes curator restore <skill-name>
This moves the skill back from ~/.hermes/skills/.archive/ to the active tree and resets its state to active. The restore refuses if a bundled or hub-installed skill has since been installed under the same name (would shadow upstream).
Disabling per environment
The curator is on by default. To turn it off:
- For one profile only: edit
~/.hermes/config.yaml(or the active profile's config) and setcurator.enabled: false. - For just one run:
hermes curator pause— the pause persists across sessions; useresumeto re-enable.
The curator also refuses to run if min_idle_hours hasn't elapsed, so on an active dev machine it naturally only runs during quiet stretches.
See also
- Skills System — how skills work in general and the self-improvement loop that creates them
- Memory — a parallel background review that maintains long-term memory
- Bundled Skills Catalog
- Issue #7816 — original proposal and design discussion