Terminal
Terminal/Skill
Helps you write and test GoClaw agent skills, using evals to measure and improve them before publishing.
By Next Level Builder
Works with
npx skills add nextlevelbuilder/goclaw --skill skill-creatorCreate effective, eval-driven Claude skills using progressive disclosure and human-in-the-loop iteration.
| Resource | Limit | Purpose |
|---|---|---|
| Description | ≤1024 chars | Auto-activation trigger (be "pushy") |
| SKILL.md | <300 lines | Core instructions |
| Each reference | <300 lines | Detail loaded as-needed |
| Scripts | No limit | Executed without loading |
New skills MUST be created directly in ~/.goclaw/skills-store/<skill-name>/.
After writing SKILL.md and resources, use publish_skill to register in the system DB.
skill-name/
├── SKILL.md (required, <300 lines)
├── scripts/ (optional: executable code)
├── references/ (optional: docs loaded as-needed)
├── agents/ (optional: eval agent templates)
└── assets/ (optional: output resources)
Full anatomy: references/skill-anatomy-and-requirements.md
Follow the process in references/skill-creation-workflow.md:
/ck:docs-seeker, /ck:research for best practicesscripts/init_skill.py <name> --path <dir>publish_skill(path: "~/.goclaw/skills-store/<name>") to register in system databasescripts/package_skill.py <path> for external distributionEval infrastructure for quantitative skill validation:
evals/evals.json with prompts + assertionsscripts/aggregate_benchmark.pyeval-viewer/generate_review.py → interactive HTML reviewfeedback.jsonDetails: references/eval-infrastructure-guide.md
Agent templates: agents/grader.md, agents/comparator.md, agents/analyzer.md
JSON schemas: references/eval-schemas.md
Combat undertriggering with "pushy" descriptions:
# ❌ Undertriggers
description: Data processing skill
# ✅ Triggers reliably
description: Process CSV files and tabular data. Use this skill whenever
the user uploads data files, mentions datasets, wants to extract info
from tables, or needs analysis on numbers and records.
Automated optimization:
scripts/improve_description.py — one iteration from failed triggersscripts/run_loop.py — train/test split, 5-15 iterations, convergence detectioncompositeScore = accuracy × 0.80 + securityScore × 0.20
Scoring algorithms: references/skillmark-benchmark-criteria.md
Optimization patterns: references/benchmark-optimization-guide.md
| Script | Purpose |
|---|---|
scripts/init_skill.py | Initialize new skill from template |
scripts/package_skill.py | Validate + package skill as zip |
scripts/quick_validate.py | Quick frontmatter validation |
scripts/run_eval.py | Test skill triggering on queries |
scripts/aggregate_benchmark.py | Consolidate runs into summary stats |
scripts/improve_description.py | AI-powered description optimization |
scripts/run_loop.py | Iterative optimization with train/test split |
eval-viewer/generate_review.py | Generate interactive HTML eval viewer |
After creating and validating a skill, register it in the GoClaw database:
publish_skill(path: "~/.goclaw/skills-store/my-skill")
This tool:
~/.goclaw/skills-store/<slug>/<version>/ (Docker: /app/.goclaw/skills-store/)If dependencies are missing, try installing via exec (e.g. pip3 install <pkg>, npm install -g <pkg>).
If system binaries are missing and cannot be installed, inform the user.
Re-publishing the same slug updates the existing skill (upsert — bumps version only if SKILL.md content changes).
references/validation-checklist.mdreferences/metadata-quality-criteria.mdreferences/token-efficiency-criteria.mdreferences/script-quality-criteria.mdreferences/structure-organization-criteria.mdreferences/skill-design-patterns.mdreferences/distribution-guide.md