agent toolingby skillscatalog
Detects installed harnesses and prompts for selection
skillscatalog/skill-installer
Install Agent Skills to your AI coding agent. Supports Claude Code, Goose, OpenCode, Cursor, and other harnesses.
What it changes
Passed 17 of 20 test cases with the skill, and 4 of 20 without it.
Without skill18%
With skill86%
Checks it passed that the model alone missed
- Specifies Python 3.9 as the minimum required version.
- Identifies .opencode/skill/{name}/ as the relative path.
- Runs python3 install_skill.py --list without filter flags.
and 12 more in the full report
15 fixed4 passed either way3 still failing0 broke
- Pass-rate lift
- +68 pp
- Tokens
- -23%
- Agent turns
- 0%
- Response time
- -61%
Model gemini-3.6-flashMeasured 8/6/2026v119 of 22 cases passed with skill · 20 comparable
See it in action
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptWhat relative directory path does OpenCode use for storing local project skills?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Identifies .opencode/skill/{name}/ as the relative path. | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md99 lines2 filesincludes scripts
Instructions
Use this skill to install Agent Skills from local directories or the catalog to your preferred harness.
Supported Harnesses
How to Use
Install from local directory:
python3 install_skill.py /path/to/my-skill --harness claude-code
python3 install_skill.py ./my-skill --harness goose
Install from catalog:
python3 install_skill.py anthropic/document-skills --harness claude-code
python3 install_skill.py anthropic/document-skills --harness goose
Auto-detect harness:
python3 install_skill.py /path/to/my-skill
# Detects installed harnesses and prompts for selection
List installed skills:
python3 install_skill.py --list
Track record
Benchmark
17 / 20
test cases passed, vs 4 / 20 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
ImportedLicense MITImported 8/2/2026Version v1Bundled 1 file · scripts