devops by okhp3
okhp3-glee-fully-repo-creator okhp3/okhp3-glee-fully-repo-creator
Create governed FoundRy child repositories from Custom GPTs, Gemini Gems, Copilot agents, prompt bundles, Notion concepts, research notes, or prototype ideas.
What it changes View full report → Passed 18 of 22 test cases with the skill, and 4 of 22 without it.
Without skill 18%
With skill 82%
Checks it passed that the model alone missed and 16 more in the full report
14 fixed4 passed either way4 still failing0 broke
Pass-rate lift +64 pp
Tokens +4%
Agent turns 0%
Response time -45% Model gemini-3.6-flashMeasured 8/4/2026 v1 18 of 22 cases passed with skill
Use this skill Claude Code DecimalAI agent CLI & files
Save it into your project's skills folder. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/okhp3-okhp3-glee-fully-repo-creator/SKILL.md https://app.decimal.ai/s/okhp3-okhp3-glee-fully-repo-creator/SKILL.md Copy command Copy SKILL.md
Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add okhp3-okhp3-glee-fully-repo-creator, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"
Linked stays up to date: your agents get the author's new versions automatically.
Editable copy is yours to change; the author's updates won't reach it.
Install linked skill Create editable copy
1 · One-time — install the CLI (
docs ↗ )
$ pip install "decimalai>=0.15"Copy
2 · Get the skill — writes .agents/skills/okhp3-okhp3-glee-fully-repo-creator/ and pins it in .decimal/skills.lock
$ decimalai skills add okhp3-okhp3-glee-fully-repo-creatorCopy
Copy link Copy README badge Copy SKILL.md No CLI? Get the same file — curl · raw file $ curl -fsSL --create-dirs -o .claude/skills/okhp3-okhp3-glee-fully-repo-creator/SKILL.md https://app.decimal.ai/s/okhp3-okhp3-glee-fully-repo-creator/SKILL.mdCopy
Safety checks: 3 of 3 passed
Code scan Clean Intent Passed Content Clean
Overview Benchmark Contents Activity Versions 1 Ratings 0
See it in action One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt Pick a parent FoundRy for my repo right now. I won't tell you what the repo does or what artifacts it contains, just pick one randomly.
What was checked, without and with the skill Checked Without skill With skill Refuse to select a parent FoundRy without evidence.
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 79 lines 2 files
okhp3-glee-fully-repo-creator
OverKill Hill P³ · overkillhill.com · github.com/OKHP3
Create a governed child repository package from an AI capability, prompt artifact, research concept, or product idea.
Brand-specific overlay
Before scaffolding, read references/brand-overlay.md. The overlay supplies Glee-fully naming, purpose, voice, and public-safety constraints; the generic FoundRy governance and approval gates remain authoritative.
Scope
Trigger When
Use this skill when the user wants to:
migrate a Custom GPT, Gem, Copilot agent, or prompt bundle into GitHub
create a new FoundRy child repository
standardize a repository against FoundRy governance
convert a platform-specific AI artifact into a reusable capability package
generate scaffold files for AGENTS.md, README.md, CHANGELOG.md, manifest.yaml, docs/, origin/, skill/, research/, tests/, schemas/, assets/, exports/, and archive/
Required Output
Produce a repo package containing:
AGENTS.md
README.md
CHANGELOG.md
LICENSE.md
manifest.yaml
docs/
origin/
skill/
prompts/
When it activates Automatically, when a task matches.
Use whenever the user wants to migrate an AI capability into GitHub, standardize a repo, create a child repo scaffold, or convert platform-specific AI work into a reusable capability package.
Track record Benchmark 18 / 22
test cases passed, vs 4 / 22 without
Adoption
Users 0
Times used 0 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported License MITImported 8/1/2026Version v1Bundled 1 file