ralph

Queue processing with fresh context per phase. Processes N tasks from the queue, spawning isolated subagents to prevent context contamination. Supports serial, parallel, batch filter, and dry run modes. Triggers on "/ralph", "/ralph N", "process queue", "run pipeline tasks".

Quality

88%

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

77%

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

The body is a thorough, actionable orchestration spec with strong workflow sequencing and validation gates. Its weaknesses are repetition that hurts token efficiency and a monolithic structure with no progressive disclosure into reference files.

Suggestions

Collapse the repeated "spawn a subagent, never run inline" mandate into a single canonical statement in the MANDATORY CONSTRAINT section and reference it from elsewhere instead of restating it in Steps 4c, 6b, Critical Constraints, and Quality Gate 1.

Extract the phase-specific prompt templates (extract/create/enrich/reflect/reweave/verify) and the parallel-mode architecture into separate reference files under references/, linked one level deep from the main body, to improve progressive disclosure.

Trim redundant framing sentences like "This is not a suggestion. This is not an optimization you can skip" that add length without adding information.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and actionable, but the subagent-spawning mandate is repeated many times ("This is not a suggestion...", "REPEAT: You MUST call the Task tool here", the MANDATORY CONSTRAINT section, Critical Constraints) — padding that could be tightened without losing clarity.	2 / 3
Actionability	Provides concrete executable guidance: exact Task tool invocation patterns, queue YAML schemas, and phase-specific prompt templates with specific file paths like ops/queue.yaml — copy-paste ready rather than pseudocode.	3 / 3
Workflow Clarity	Multi-step process is clearly sequenced (Steps 0–7, 6a–6e) with explicit validation checkpoints — the Phase B completion gate, the subagent-count-equals-task-count verification, Quality Gates, and Error Recovery feedback loops.	3 / 3
Progressive Disclosure	A ~600-line monolithic file with no bundle reference files; well-sectioned but content that could be split (phase prompt templates, parallel architecture) is inline, matching the "some structure but content that should be separate is inline" anchor rather than the one-level-deep reference ideal.	2 / 3
	Total	10 / 12 Passed

Description

100%

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

The description is concise, concrete, and third-person, listing specific capabilities and modes alongside an explicit trigger clause. It cleanly satisfies all four dimensions with no vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Processes N tasks from the queue", "spawning isolated subagents", "Supports serial, parallel, batch filter, and dry run modes" — matching the anchor that lists several specific concrete actions.	3 / 3
Completeness	Clearly answers both what (processes N tasks, spawns subagents, four modes) and when (explicit "Triggers on..." clause), matching the anchor requiring both with explicit triggers.	3 / 3
Trigger Term Quality	Explicit "Triggers on "/ralph", "/ralph N", "process queue", "run pipeline tasks"" provides natural terms a user would actually say, with good coverage.	3 / 3
Distinctiveness Conflict Risk	"Queue processing with fresh context per phase" with the "/ralph" trigger is a clear niche with distinct triggers unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (603 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: agenticnotetaking/arscontexta
Path: skill-sources/ralph/SKILL.md
Commit: 2acfd5c

Reviewed: 3 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.