skill-creator
/skill-creator
Tworzy, pisze i waliduje skill Agenta, zamienia powtarzalny przepływ w SKILL.md albo naprawia skill, który się nie ładuje.
- Autor
- stippi ↗
- Repozytorium
- code-assistant ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 27.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 1
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 27.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Tworzy, pisze i waliduje skill Agenta, zamienia powtarzalny przepływ w SKILL.md albo naprawia skill, który się nie ładuje.
Oryginalny opis (EN)
Scaffold, author, and validate an Agent Skill. Use when the user wants to create a new skill, turn a repeatable workflow into a reusable SKILL.md, or fix a skill that fails to load.
Jak działa
- 1. Choose a scope
- 2. Write SKILL.md
- 3. Add resources (optional)
- 4. Validate
- Template
- Quality checklist
Podgląd SKILL.md
--- name: skill-creator description: Scaffold, author, and validate an Agent Skill. Use when the user wants to create a new skill, turn a repeatable workflow into a reusable SKILL.md, or fix a skill that fails to load. --- # Skill Creator A *skill* is a reusable, task-specific playbook stored as a `SKILL.md` file in a directory named after the skill. Skills are advertised in the system prompt by name + description (progressive disclosure); their full instructions are loaded on demand with the `read_skill` tool. Use this skill whenever the user asks to create, author, or improve a skill. ## 1. Choose a scope A skill lives in one of three scopes. Pick based on how widely it should apply: - **project** — `<project_root>/.agents/skills/<name>/` — specific to one repo. Load with `read_skill(project="<project-name>", name="<name>")`; read its resources with `read_files(project="<project-name>", ...)`. - **user** — `~/.agents/skills/<name>/` — your personal skills, available in every project (and shared with other agent harnesses). Addressed by the scope token `:config:`; load with `read_skill(project=":config:", ...)`. - **system** — token `:system:` — bundled skills (like this one). Usually read-only. On a name collision, project wins over user wins over system. ## 2. Write `SKILL.md` The file MUST start with a YAML frontmatter block delimited by `---` lines, followed by a free-form Markdown body: ``` --- name: my-skill description: One-paragraph routing description the model uses to decide when to load this skill. --- # My Skill ...instructions... ``` Frontmatter rules (enforced by the loader): - `name` is required, must be **lowercase letters, digits, and hyphens** only, at most 64 characters, and must **equal the directory name**. - `description` is required, at most 1024 characters. Write it as a routing signal: say *when* to use the skill, not just what it does. - `disable-model-invocation` (optional, default `false`): when `true`, the skill is hidden from the model-facing catalog and the `list_skills` tool so the model never auto-invokes it. It stays loadable via `read_skill` (e.g. when a user explicitly activates it) and visible in the settings UI. Use this for skills that should only run on explicit user request. - Other keys (license, allowed-tools, metadata, etc.) are allowed and ignored for now. ## 3. Add resources (optional) Bundle supporting files under the skill directory and reference them from the body with paths relative to the skill directory: - `scripts/` — runnable helpers. Prefer running them with `execute_command` rather than reading them into context. - `references/` — longer docs to read on demand with `read_files`. - `assets/` — templates or output skeletons. Keep `SKILL.md` itself short: it should orchestrate, pointing at the right resource for each sub-task instead of inlining everything. ## 4. Validate - The directory name equals `name`. - Frontmatter parses and `name`/`description` satisfy the rules above. - Referenced resource paths exist and are relative to the skill directory. - Load it once with `read_skill` to confirm the body renders as expected. ## Template ``` --- name: <kebab-case-name> description: Use this skill when <trigger>. It <what it does>. --- # <Human Title> ## When to use <one or two sentences> ## Workflow 1. <step> 2. <step> ## Resources - `references/<doc>.md` — <what it contains> - `scripts/<tool>` — <what it does> (run with execute_command) ``` ## Quality checklist - Single responsibility: one skill, one job. - The description is a strong routing signal (the model only sees this until it loads the skill). - Progressive disclosure: short body, details in `references/`. - Deterministic work lives in `scripts/`, not in prose.
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · stippi/code-assistant | 100 | MIT |
| opencue/cuecards | 100 | MIT |
| zzusp/night-bot | 100 | MIT |
| gonzalezpazmonica/savia | 100 | MIT |
| iuliandita/skills | 100 | MIT |
| langfuse/langfuse | 100 | MIT |
| seaworld008/commonly-used-high-value-skills | 100 | MIT |
| dfinity/icskills | 100 | Apache-2.0 |
| LumenJSN/Aris | 100 | Apache-2.0 |
Migawka bazy z 13.11.2026 · wersja paczki d8c0304ee116 (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
- 95workflow-skill-creator
Zamienia ukończony przepływ pracy użytkownika w wielokrotnego użytku skill agenta. - 100workflow-skill-creator
Zamienia ukończony przepływ pracy użytkownika w wielokrotnego użytku skill dla agenta. - 90Add skill
Tworzy nowy wielorazowy skill w bibliotece albo propozycję z projektu i zamienia powtarzalny workflow w instrukcje. - 100create-skill
Zamienia powtarzalny prompt AI lub przepływ pracy w ustrukturyzowany, udostępnialny skill dla repozytorium affiliate-skills na GitHubie, z plikiem SKILL.md. - 98skill-crafting
Tworzy, naprawia i waliduje skille dla agentów AI, także z gotowej sesji, i sprawdza budżet znaków w opisach. - 100create-skill
Tworzy, edytuje, projektuje, sprawdza i refaktoryzuje skille, komendy ukośne i subagenty Claude Code, także wyodrębniając powtarzalny workflow z bieżącej sesji.