Files
holocron/plugins/kyberforge/skills/skill-write/README.md
Defame1297 672fd25890 feat(kyberforge): replace write-skill with spec-compliant skill-write and add skill-audit
Rewrote the skill authoring factory skill from scratch against the agentskills.io
specification. Renamed write-skill → skill-write (name now matches directory per spec).

skill-write:
- Full scaffold via new-skill.sh (annotated templates for SKILL.md, README.md,
  scripts/, references/, assets/)
- validate.sh checks all spec constraints deterministically (name format/length,
  description length, placeholder detection, line count, script rules)
- SKILL.md body includes description rules, body discipline, patterns, and scripts
  guidance with "why" rationale throughout
- Templates usable standalone by agents and humans

skill-audit:
- Structural validation (via validate.sh) + seven qualitative dimensions
- Produces PASS/FAIL/SUGGESTION punch list with per-FAIL fix proposals
- Report-only: does not apply fixes

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-22 18:50:00 +00:00

64 lines
1.9 KiB
Markdown

# skill-write
Author a new skill conforming to the [agentskills.io](https://agentskills.io) specification.
## What it does
1. Scaffolds a full skill directory from annotated templates
2. Guides filling in `SKILL.md` and supporting files
3. Validates the result against the spec
## Before you start
This skill produces its best output when you arrive with rich context:
- Run `/grill-me` to resolve design decisions (scope, triggers, patterns)
- Collect domain research, examples, and reference docs
- Know the skill name (kebab-case) and destination path
## Usage
Invoke via your agent tool with `/skill-write`, or follow the steps in `SKILL.md` manually.
**Agent invocation:**
```
/skill-write
```
**Manual (human) workflow:**
```bash
# 1. Create the scaffold
bash scripts/new-skill.sh <skill-name> <destination-dir>
# 2. Fill in the templates at <destination-dir>/<skill-name>/
# 3. Validate
bash scripts/validate.sh <destination-dir>/<skill-name>
```
## Files
| File | Purpose |
|------|---------|
| `SKILL.md` | Skill instructions for agents |
| `scripts/new-skill.sh` | Copies annotated templates to the destination |
| `scripts/validate.sh` | Validates a skill directory against the spec |
| `assets/templates/SKILL.md` | Annotated SKILL.md template |
| `assets/templates/README.md` | Annotated README template for the new skill |
| `assets/templates/scripts/README.md` | Placeholder for bundled scripts |
| `assets/templates/references/README.md` | Placeholder for reference docs |
| `assets/templates/assets/README.md` | Placeholder for static assets |
## Placement
Skills can be installed in two locations:
| Type | Path |
|------|------|
| Direct (available immediately) | `~/.agents/skills/<name>/` |
| Plugin (installed via marketplace) | `plugins/<plugin>/skills/<name>/` |
## Spec reference
[agentskills.io specification](https://agentskills.io/specification.md)