edge-pipeline-orchestrator

Orchestrate the full edge research pipeline from candidate detection through strategy design, review, revision, and export. Use when coordinating multi-stage edge research workflows end-to-end.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear sequenced workflow, an explicit feedback loop, a quality gate before export, and well-organized one-level-deep references. The main weakness is token efficiency from redundant CLI examples and partial overlap between the manual and automated workflow sections.

Suggestions

Condense the five CLI blocks into one full example plus a compact table of mode-specific flag combinations (--from-ohlcv, --resume-from, --review-only, --dry-run) to reduce vertical repetition.

Trim the "Claude Code LLM-Augmented Workflow" section so it only documents what differs from the automated CLI (manual hint generation and the --llm-ideas-file / --promote-hints handoff) rather than re-staging the full pipeline.

Consider moving the detailed optional-flags reference into references/pipeline_flow.md and keeping only the most common flags inline.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of concept over-explanation, but five near-identical CLI blocks share most flags and the manual "Claude Code LLM-Augmented Workflow" partly duplicates the automated CLI flow, so it could be tightened.	2 / 3
Actionability	Provides copy-paste-ready CLI invocations with real flags and paths, a complete YAML hint schema example, and a concrete output directory tree — fully executable guidance.	3 / 3
Workflow Clarity	An 8-step sequenced workflow includes an explicit review-revision feedback loop (REVISE triggers apply_revisions and re-review, max iterations, downgrade to research_probe) and an export eligibility gate (PASS + export_ready_v1) acting as a validation checkpoint.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview and the Resources section points one level deep to two real, clearly-signaled files (pipeline_flow.md for architecture, revision_loop_rules.md for loop rules), with content appropriately split.	3 / 3
	Total	11 / 12 Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly answers both what the skill does and when to use it within a distinct niche. The only weakness is trigger-term naturalness, which relies on domain jargon rather than phrasings a user would commonly say.

Suggestions

Add more natural trigger phrasings a user might actually say (e.g., "edge research", "strategy pipeline", "backtest and export strategies") alongside the existing jargon to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete pipeline actions — "candidate detection through strategy design, review, revision, and export" — matching the anchor for several specific concrete actions rather than a single domain mention.	3 / 3
Completeness	Explicitly states what it does (orchestrate detection→design→review→revision→export) and when to use it via a clear "Use when coordinating multi-stage edge research workflows end-to-end" clause.	3 / 3
Trigger Term Quality	Terms like "edge research pipeline" and "multi-stage edge research workflows" are relevant to the niche but lean on specialized jargon and lack common user-facing variations, fitting the "some relevant keywords but missing common variations" anchor.	2 / 3
Distinctiveness Conflict Risk	The "edge research pipeline" niche with end-to-end orchestration triggers is highly specific and unlikely to fire for unrelated skills, matching the clear-niche anchor.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tradermonty/claude-trading-skills
Path: skills/edge-pipeline-orchestrator/SKILL.md
Commit: 62a1635

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.