70763091af
- domains, subdomains, tags : frontmatter distribution counts
- enable-domain / disable-domain : bulk by 'domain:' (eg. cybersecurity)
- enable-subdomain / disable-subdomain : bulk by 'subdomain:' (eg. malware-analysis)
- enable-tag / disable-tag [--all] : multi-tag union (default) or intersection
- INDEX.json now exposes domain, subdomain, tags[]
- INDEX.md columns expanded; top-domains/subdomains/tags summaries
- PyYAML-first frontmatter parser (regex fallback) — parses 1027/1032 descriptions
and 758 skills' tags correctly (previous regex parser missed almost everything)
- enable/disable now incrementally update INDEX.json status so bulk ops stay
consistent without a full reindex
- jq --args bug fix in tag commands ('--' was leaking into ARGS.positional)
94 lines
4.3 KiB
Markdown
94 lines
4.3 KiB
Markdown
# opc-skills
|
|
|
|
Small shell utility for toggling opencode skills between a curated "active" set and a full "parked" catalog. Keeps `~/.config/opencode/skills/` small and intentional while preserving the full skill library offline.
|
|
|
|
This is deliberately a quick, standalone tool — it is **not** a general AI persona manager. For agent / skill / persona management across multiple AI platforms (Claude Code, opencode, Gemini, Paperclip, ...), see the `personas` repo.
|
|
|
|
## Install
|
|
|
|
```bash
|
|
ln -s ~/Documents/opc-skills/bin/opc-skills ~/.local/bin/opc-skills
|
|
```
|
|
|
|
Ensure `~/.local/bin` is on your `PATH`.
|
|
|
|
## Layout it expects
|
|
|
|
```
|
|
~/Documents/opencode-skills-parked/ # full catalog — untracked data dir
|
|
<skill-name>/SKILL.md
|
|
INDEX.json
|
|
INDEX.md
|
|
~/.config/opencode/skills/ # only currently-enabled skills
|
|
<skill-name>/SKILL.md
|
|
```
|
|
|
|
Override via env:
|
|
- `OPC_PARKED` — parked catalog root (default `~/Documents/opencode-skills-parked`)
|
|
- `OPC_ACTIVE` — active skills root (default `~/.config/opencode/skills`)
|
|
|
|
## Commands
|
|
|
|
### Inspection
|
|
|
|
```
|
|
opc-skills status # counts of active vs parked
|
|
opc-skills list {active|parked|all} # skill folder names
|
|
opc-skills categories # verb-prefix counts (performing, detecting, ...)
|
|
opc-skills domains # frontmatter `domain:` distribution
|
|
opc-skills subdomains # frontmatter `subdomain:` distribution
|
|
opc-skills tags # frontmatter `tags:` distribution
|
|
```
|
|
|
|
### Single-skill operations
|
|
|
|
```
|
|
opc-skills enable <folder> # copy parked → active
|
|
opc-skills disable <folder> # remove from active (parked preserved)
|
|
opc-skills disable-all [-y|--yes] # disable every active skill
|
|
```
|
|
|
|
### Bulk by axis
|
|
|
|
```
|
|
opc-skills enable-category <prefix> # fzf multi-pick within a verb-prefix
|
|
opc-skills disable-category <prefix>
|
|
opc-skills enable-domain <domain> # bulk by frontmatter domain (eg. cybersecurity)
|
|
opc-skills disable-domain <domain>
|
|
opc-skills enable-subdomain <subdomain> # bulk by subdomain (eg. malware-analysis)
|
|
opc-skills disable-subdomain <subdomain>
|
|
opc-skills enable-tag [--all] <tag>... # bulk by tags (default: any; --all: intersection)
|
|
opc-skills disable-tag [--all] <tag>...
|
|
```
|
|
|
|
### Interactive / search
|
|
|
|
```
|
|
opc-skills pick # fzf: category → multi-select → enable
|
|
opc-skills disable-pick # fzf: ACTIVE category → multi-select → disable
|
|
opc-skills search [query] # fzf fuzzy over name+description
|
|
opc-skills disable-search [query] # fzf over ACTIVE only
|
|
opc-skills reindex # rebuild INDEX.json / INDEX.md
|
|
```
|
|
|
|
`fzf` is required for the interactive commands; `jq` for the bulk-by-axis commands; `python3` (with optional `PyYAML`) for `reindex`.
|
|
|
|
### INDEX schema
|
|
|
|
`reindex` parses each `SKILL.md` frontmatter and emits records with: `folder`, `name`, `description`, `domain`, `subdomain`, `tags[]`, `status`. `enable` / `disable` perform an incremental status update on `INDEX.json` so `enable-domain` / `disable-tag` etc. stay accurate without a full reindex.
|
|
|
|
## Shared reference files
|
|
|
|
Some skills reference sibling files via `../<name>.md` (e.g. the 20 Feynman research skills use `../_platform-mapping.md` for cross-platform tool mapping). `opc-skills enable` auto-syncs any such files from PARKED → ACTIVE so the relative references keep resolving.
|
|
|
|
Currently synced:
|
|
- `_platform-mapping.md` — Feynman-skills cross-platform subagent/scheduling/persistence mapping
|
|
|
|
If you add new shared-reference files at the PARKED root, extend `sync_shared_refs()` in `bin/opc-skills`.
|
|
|
|
## Known interaction
|
|
|
|
The `personas` repo's `build.py --install opencode` currently wipes and repopulates `~/.config/opencode/skills/` as part of installation, which destroys the active set curated here. Use `opc-skills` *after* any personas install, or skip the skills half of `build.py` installs.
|
|
|
|
`build.py --install opencode` and `build.py --install claude-skills` both emit `_platform-mapping.md` at the skills-root alongside the 20 Feynman skills (`deep-research`, `literature-review`, `paper-code-audit`, `peer-review`, `paper-writing`, `replication`, `source-comparison`, `summarize`, `alpha-research`, `eli5`, `autoresearch`, `docker`, `modal-compute`, `runpod-compute`, `session-log`, `session-search`, `jobs`, `watch`, `preview`, `contributing`).
|