Files

Defame1297 95ba57d0d5 fix(kyberforge): address self-audit findings and update lessons

- Reorder skill-audit description to lead with 'Use when...' trigger (P3)
- Add concrete example to 'control calibration' body discipline check (P4)
- Add bats test files to README file tables for both skills
- Fix REPO_ROOT and SCRIPT paths in bats files after tests/ subdirectory removed
- Add three lessons: plugin cache isolation, spec-grounded rubrics, test file placement

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-06-22 20:16:24 +00:00

marketplace-architect

fix(kyberforge): co-locate evals/tests with skills and fix manifest inconsistencies

2026-06-20 18:56:52 +00:00

plugin-create

fix(kyberforge): co-locate evals/tests with skills and fix manifest inconsistencies

2026-06-20 18:56:52 +00:00

promptfoo

feat(skills): add promptfoo skill for LLM evaluation and red-teaming

2026-06-21 11:11:59 +00:00

skill-audit

fix(kyberforge): address self-audit findings and update lessons

2026-06-22 20:16:24 +00:00

skill-write

fix(kyberforge): address self-audit findings and update lessons

2026-06-22 20:16:24 +00:00

write-agent

feat(skills): add write-agent factory skill for cross-tool agent authoring

2026-06-21 12:01:34 +00:00

write-eval

fix(kyberforge): co-locate evals/tests with skills and fix manifest inconsistencies

2026-06-20 18:56:52 +00:00

README.md

feat: add kyberforge plugin and rename plugin-create skill

2026-06-20 17:46:02 +00:00

README.md

skills/

Skills for this plugin. Each skill lives in its own subdirectory:

skills/
  <skill-name>/
    SKILL.md      # required — frontmatter + skill body
    META.md       # required — provenance and audit fields
    references/   # optional — on-demand reference docs
    scripts/      # optional — executable helper scripts
    assets/       # optional — templates, data files, lookup tables

Shared — both Claude Code and GitHub Copilot CLI read skills/<name>/SKILL.md.

To add a skill, run /write-skill in a Claude Code session. Do not write SKILL.md by hand without following the authoring standard — trigger descriptions and self-checks are required.