AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Curate Skills

skill-justingastby-hermes-mind-skill-curate-skills · by JustinGastby

>-

No reviews yet
0 installs
7 views
0.0% view→install

Install

$ agentstack add skill-justingastby-hermes-mind-skill-curate-skills

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-justingastby-hermes-mind-skill-curate-skills)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
18d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Curate Skills? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Curate Skills

A much lighter version of Hermes Agent's Curator: it keeps .cursor/skills/ from accumulating stale or near-duplicate entries, but — unlike Hermes's fully-automatic background Curator — it never touches a file without the user confirming first. A wrong or premature archive/merge is worse than a slightly untidy skills folder.

Two things this does, and neither one deletes anything

  1. Archive long-unused skills — move the skill's directory into

.cursor/skills/.archive/. Recoverable, never destructive.

  1. Merge near-duplicate skills into one broader skill, then archive the

originals (not delete) so nothing is lost if the merge was wrong.

When to run this

  • The stop hook's curator sweep (nudge-skill-distillation.js) nudged you

with a list of skills that haven't been read in ~30 days.

  • The user explicitly asks to clean up, compress, or prune skills.
  • While drafting a new skill in distill-skill, you notice 2+ existing

skills already cover very similar ground.

Workflow

  1. Survey the current skills. List .cursor/skills/*/SKILL.md (skip

.archive/). For each, read the frontmatter name + description, and check .cursor/hooks/.state/skill-usage.json for use_count / last_used_at if present.

  1. Never touch these:
  • distill-skill, curate-skills — this project's own bundled skills.
  • Any skill whose SKILL.md frontmatter contains pinned: true.
  • Bundled/hub-installed skills the user didn't create locally, if that's

distinguishable (e.g. skills that shipped with another tool/plugin).

  1. Draft a short proposal, not a file edit. Two independent lists:
  • Archive candidates: name + how long unused (from the nudge message

or skill-usage.json).

  • Merge candidates: which 2+ skills overlap, a proposed merged name +

one-sentence description, and which old skills would be absorbed.

  1. Ask the user to confirm each list separately (a skill might be a

merge candidate but not stale, or vice versa) — e.g. "这些技能好久没用了, 要不要归档?" / "这几个技能内容挺重叠的,要不要合并成一个?" Do not modify any file before the user agrees.

  1. On confirmed archive: mkdir -p .cursor/skills/.archive then move the

skill's whole directory there (keep references/, templates/, scripts/ subfiles together — archive the full package, don't cherry-pick files).

  1. On confirmed merge:
  • Create .cursor/skills//SKILL.md with the combined

procedure — write it fresh, don't just concatenate the old bodies. Fold overlapping steps together; keep pitfalls from all sources.

  • Move any references//templates//scripts/ subfiles the merged

skill still needs into the new skill's directory.

  • Archive (not delete) each absorbed skill's original directory into

.cursor/skills/.archive/ so the merge is reversible.

  1. On no or no response, drop it — don't archive/merge and don't ask

again this session.

Recovering an archived skill

Just move it back: mv .cursor/skills/.archive/ .cursor/skills/. Nothing about archiving is ever a one-way trip.

Pinning a skill so it's never flagged as stale

Add pinned: true anywhere in the skill's YAML frontmatter:

---
name: some-skill
description: ...
pinned: true
---

The curator sweep skips pinned skills entirely, and this skill should too — never propose archiving or merging a pinned skill even if the user asks you to review "everything."

Verifying a merge didn't lose anything

Before archiving the absorbed originals, diff the new skill's body against each original to confirm every concrete step/command/pitfall made it into the merged version — a merge that silently drops a hard-won pitfall is worse than not merging at all.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.