skill-router
/skill-router
Wybiera skill dla zamiaru i podaje gotowe polecenie do wklejenia, porównując zamiar z frazami użycia, słowami kluczowymi i wykluczeniami.
- Autor
- aminmzadev ↗
- Repozytorium
- keyless-agent-skills ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 02.11.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 2
- Skrypty
- 1
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 02.11.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
- 1 skrypt w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.
Skrypty: scripts/route.py
Co robi i kiedy
Wybiera skill dla zamiaru i podaje gotowe polecenie do wklejenia, porównując zamiar z frazami użycia, słowami kluczowymi i wykluczeniami.
Wyzwalacze z opisu
Oryginalny opis (EN)
Pick the right skill for an intent and print a pasteable command. Reads MANIFEST.json (or every SKILL.md frontmatter when there is no manifest) and scores the intent against use_when phrases, curated keywords and not_for exclusions. Use when an agent has several skills installed and must choose one entry point before doing anything, or when you want to know which script handles "make me a logo" versus "read this page".
Jak działa
- What it actually does
- Special case: meta questions
- Composition hint
- Output contract
- Failure modes
- Notes for the agent
Podgląd SKILL.md
---
name: skill-router
description: Pick the right skill for an intent and print a pasteable command. Reads MANIFEST.json (or every SKILL.md frontmatter when there is no manifest) and scores the intent against use_when phrases, curated keywords and not_for exclusions. Use when an agent has several skills installed and must choose one entry point before doing anything, or when you want to know which script handles "make me a logo" versus "read this page".
version: 1.2.0
license: MIT
---
# skill-router
One command that answers "which of these seven things do I run?".
```bash
route.py "make me a logo for a coffee shop"
# anon-image (1.88)
# python3 anon-image/scripts/imgen.py gen "make me a logo for a coffee shop" -o out.jpg
route.py "which skill handles PDFs" --top 3
route.py "I need a voiceover for my video" --explain
route.py --list
route.py "read this page" --json
```
## What it actually does
1. **Find the pack.** `--skills-dir`, else `$AGENT_SKILLS_DIR`, else walk up from the
script until it sees `MANIFEST.json` (or a directory of `SKILL.md` files).
2. **Load the catalogue.** `MANIFEST.json` if present — it carries `use_when`,
`not_for`, `keywords`, `entry` and `commands`. No manifest? It parses the YAML
frontmatter of every `SKILL.md` and guesses the entry point from `scripts/`.
That fallback is what makes this work for *other* people's skill packs too.
3. **Score the intent.**
```
score = 3.0 × best match against any use_when phrase
+ 3.0 × curated keyword hit rate (two hits = full credit)
+ 1.5 × keyword overlap with description
+ 1.5 × keyword overlap with the skill name
− 4.0 × match against not_for (a veto, not a nudge)
```
`not_for` is the field that stops an agent trying to generate music with a TTS
endpoint, so it is weighted heavier than any positive signal.
4. **Refuse to guess.** Below `1.00` it prints "no confident match" and the closest
three, exit code `1`. A wrong confident answer costs an agent more than an honest
shrug — it will spend four tool calls doing the wrong thing.
5. **Print a command, not advice.** The output is pasteable and already contains the
intent where the skill takes free text.
## Special case: meta questions
"which skill / what tool / list skills / what should I use" is a question about the
pack, not a task. Bag-of-words scoring will never rank the router first for those, so
there is an explicit detector that does. It is deliberately narrow — "route this: I
need a podcast intro" still routes to `anon-audio`, because `route` alone is not a
meta signal.
## Composition hint
When the runner-up is within ~1.2 points **and** the winner declares it in
`composes_with`, the router says so:
```
anon-audio (2.62)
python3 anon-audio/scripts/tts.py say "I need a voiceover for my video" -o out.mp3
```
Becomes, when `ffmpeg-pipeline` wins by a hair:
```
note: close call with anon-audio and it composes — ffmpeg-pipeline can call it for you
```
That one line is usually the correct answer: the task genuinely needs two skills.
## Output contract
| Mode | Shape |
|---|---|
| default | `skill (score)` + indented command (+ alternatives when `--top > 1`) |
| `--json` | `{intent, root, match:{skill,entry,command,score}, alternatives[], all[]}` |
| `--explain` | the per-field score breakdown for the winner |
| `--list` | the whole routing table: name, entry, first `use_when` phrase |
Exit codes: `0` matched · `1` nothing above threshold · `2` no skills found.
## Failure modes
| Symptom | Meaning | Action |
|---|---|---|
| `no confident match` | intent too vague, or genuinely not covered | rephrase with the object you want ("logo", "voiceover", "PDF"); the three closest are printed |
| everything scores `0.00` | no skill owns those words | check `--list`; the pack has no such capability and it is telling you so |
| wrong skill wins | that skill's `keywords` are too broad | edit `keywords` in `MANIFEST.json` — the router is data-driven on purpose, fixing routing should not mean editing Python |
| `no skills found` | pack layout not recognised | `--skills-dir /path/to/pack` or export `AGENT_SKILLS_DIR` |
| `only one skill found under …` | you installed the router on its own — there is nothing to route between | point it at a pack: `--skills-dir ~/agent-skills` or `export AGENT_SKILLS_DIR=~/agent-skills` |
## Notes for the agent
- Run the router **once**, before a multi-step task, not before every call. It costs
nothing but it is a decision, not a reflex.
- `--json` if you are parsing; the human output is for humans and its exact spacing
is not a contract.
- If the router says no confident match and you still think a skill applies, run it
anyway with `--provider`-style explicit arguments — the router is a hint, and the
scripts are the source of truth.
Pliki w paczce (2)
- SKILL.md 5 KB
- scripts/route.py 12 KB
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · aminmzadev/keyless-agent-skills | 100 | MIT |
| FrancoStino/opencode-skills-collection | 100 | MIT |
| dreamlab-ai/agentbox | 100 | AGPL-3.0 |
| hanmariyang/giting-skills | 100 | MIT |
| wrongstack/wrongstack | 100 | MIT |
| sickn33/agentic-awesome-skills | 100 | MIT |
| dotslashsimran/simcraft | 100 | MIT |
| borghei/Claude-Skills | 100 | MIT |
| byrmeng/skill-router | 100 | MIT |
Migawka bazy z 13.11.2026 · wersja paczki 568268d1026a (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 98agent-library-skill-create
Tworzy jednym poleceniem skill do biblioteki agentów: SKILL.md, manifest i intencję, domyślnie widoczny dla wszystkich agentów. - 100vault-router
Kieruje prośbę do jednego pasującego skilla z kolekcji vault, po analizie zadania i oczekiwanego efektu. - 100add-skill
Tworzy nowy skill dla użytkowników w katalogu skills/, który uczy agentów AI korzystać z poleceń CLI cx, w tym dokumentuje polecenie jako skill z SKILL.md. - 100using-foundationskills
Działa tylko na polecenie /using-foundationskills: kieruje zamiar do właściwego skilla FoundationSkills i wymienia dostępne skille. - 100guide
Pełni rolę mapy hub skilli repozytorium: opisuje scenariusze użycia, granice i powiązania zainstalowanych skilli jako router o zerowym koszcie kontekstu. - 100skill-frontmatter
Pisze nagłówek YAML pliku SKILL.md z nazwą, opisem i słowami aktywującymi, tak by skill uruchamiał się niezawodnie.