eas-oss/agent-skills
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

F4492: promote loop-engineering skill from DRAFT to listed

Browse source 
Content-only: removes status:draft from the well-known discovery index,
SKILL.md frontmatter, and the README table row. No Stripe object created,
no price set (hosted-tier pricing stays an explicit owner decision per the
SKILL.md Upgrade section). Verified before this change: templates valid
JSON, no secrets/internal hostnames in the skill content, all three repo
files render 200 on git.eliteaiempire.com.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012Yni81JScNftKTeRvP6DLa
This commit is contained in:
F2850 Lumen 2026-09-04 18:30:23 +00:00
parent 68de616361
commit 61240a6f18
3 changed files with 11 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
.well-known/agent-skills/index.json
View file

@ -16,8 +16,7 @@
},
{
"name": "loop-engineering",
"description": "Turn a one-off agent prompt into a self-supervising loop that runs unattended, safely. Five stages (manifest, unit, watchdog, attribution, re-grade) plus a human-approval gate on any outward-facing or irreversible step. DRAFT.",
"status": "draft",
"description": "Turn a one-off agent prompt into a self-supervising loop that runs unattended, safely. Five stages (manifest, unit, watchdog, attribution, re-grade) plus a human-approval gate on any outward-facing or irreversible step.",
"files": [
"SKILL.md",
"templates/research-loop.json",
@ -26,4 +25,4 @@
]
}
]
}
}

2
README.md
View file

@ -15,7 +15,7 @@ npx skills add eliteaiempire/agent-skills --skill bug-class-detectors
|---|---|---|
| **bug-class-detectors** | Find bug CLASSES not instances — 37 root-cause detectors + CI auto-fix PRs (Snyk/Sonar alt). | https://bugclass.eliteaiempire.com |
| **backtest-integrity** | Lopez-de-Prado overfit battery (purged-CPCV, PBO, deflated-Sharpe, uniqueness, triple-barrier) — trust a backtest only if it survives. | https://th-validator.eliteaiempire.com |
| **loop-engineering** *(DRAFT)* | Manifest -> unit -> watchdog -> attribution -> re-grade: package a one-off agent prompt into a safely self-supervising loop, with a human-approval gate on any outward-facing/irreversible step. Includes 3 Orchestrator flow templates. | https://ourtools.eliteaiempire.com |
| **loop-engineering** | Manifest -> unit -> watchdog -> attribution -> re-grade: package a one-off agent prompt into a safely self-supervising loop, with a human-approval gate on any outward-facing/irreversible step. Includes 3 Orchestrator flow templates. | https://ourtools.eliteaiempire.com |
Each skill is the open, portable logic; the hosted engines add CI integration, dashboards,
auto-fix PRs, and (for backtest-integrity) 16-venue prediction-market settlement + L2 depth.

14
skills/loop-engineering/SKILL.md
View file

@ -4,15 +4,16 @@ description: "Turn a one-off agent prompt into a self-supervising loop that runs
license: MIT
homepage: https://ourtools.eliteaiempire.com
tested_with: claude-code v2.x
status: draft
status: listed
---
# Loop Engineering
**DRAFT — not for sale yet.** This is the packaged, sanitised version of a pattern we run in
production at real scale (thousands of concurrent scheduled agent units on our own fleet). No
internal hostnames, IP addresses, credentials, or private tooling paths are included below — only
the shape of the pattern, which is generic and reusable on any agent stack.
**Listed** (no hosted-tier price set yet — this skill is free to use). This is the packaged,
sanitised version of a pattern we run in production at real scale (thousands of concurrent
scheduled agent units on our own fleet). No internal hostnames, IP addresses, credentials, or
private tooling paths are included below — only the shape of the pattern, which is generic and
reusable on any agent stack.
## The problem this solves
"Set up a recurring agent task" usually means a cron job that calls an LLM and hopes for the
@ -122,4 +123,5 @@ fails safely and tells you so, instead of failing silently.
## Upgrade
The hosted version of this pattern — pre-built manifest/watchdog/attribution tooling wired to your
own infra, plus the approval-gate integration — is on the **Our Tools** roadmap; this skill is the
portable, sanitised logic. No hosted product exists yet for this skill (draft).
portable, sanitised logic, listed and free to use today. Hosted-tier pricing is not yet set
(owner decision).