run

Execute a Seed specification through the workflow engine

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude-plugin/skills/run/SKILL.md

Quality

Content

62%

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, well-sequenced operational workflow with strong validation checkpoints, but it is verbose and monolithic with no progressive disclosure to reference files. Conciseness, actionability, and progressive disclosure are the limiting dimensions.

Suggestions

Move the extended protocol detail (Synapse intent refinement, Active Conductor attention handling, RFC breadcrumb footer) into reference files under references/ and link to them one level deep from the main steps to improve progressive disclosure and conciseness.

Tighten or deduplicate the repeated deferred-schema guard instructions into a single stated rule that is referenced once, reducing verbosity without losing the safety guidance.

Define or eliminate the undefined relay helper functions (task_progress_relay, subtask_progress_relay, terminal_relay, etc.) so the monitoring loop is concrete and copy-paste-ready rather than referencing pseudocode helpers.

Dimension	Reasoning	Score
Conciseness	The ~510-line body is mostly domain-specific protocol Claude does not already know, but it carries notable repetition (the deferred-schema guard is restated several times) and verbose inline relay contracts that could be tightened, matching the level-2 "mostly efficient but could be tightened" anchor rather than the lean level-3 anchor.	2 / 3
Actionability	It names concrete MCP tools with explicit argument blocks and a structured polling loop, but relies on undefined helper functions (e.g., task_progress_relay, terminal_relay) and environment-conditional discovery, so it is not fully copy-paste-ready and lands at level 2 rather than the fully-executable level-3 anchor.	2 / 3
Workflow Clarity	Execution is laid out as a clearly numbered sequence (steps 1-10) with explicit validation checkpoints (deferred-schema reload before every call, terminal-status handling, post-execution QA) and recovery/feedback loops (fallback relay, stale-target rediscovery, attention verify-decide-log-act), matching the level-3 anchor and exceeding the level-2 "validation gaps" case.	3 / 3
Progressive Disclosure	No bundle files exist and everything lives inline in a large monolithic SKILL.md with no one-level-deep reference files or overview-to-detail navigation; it is internally sectioned (above level 1) but content that could be split (Synapse, Conductor, RFC footer) is inline, matching the level-2 anchor.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 concrete and niche-specific but terse: it states one action with no "Use when..." trigger guidance and only narrow keyword coverage. Trigger terms and completeness are the weakest areas.

Suggestions

Expand the description to list the concrete capabilities beyond execution (e.g., validate, start background jobs, monitor progress, run post-execution QA) to reach the multi-action level-3 anchor for specificity.

Add an explicit "Use when..." clause naming natural user triggers (e.g., "Use when the user says 'ouroboros run' or asks to execute a seed specification") to lift completeness and trigger-term quality to level 3.

Include common user phrasings ("run a seed", "execute a spec", "start an Ouroboros workflow") to broaden trigger-term coverage and reduce conflict with other skills.

Dimension	Reasoning	Score
Specificity	Names a concrete action and domain ("Execute a Seed specification through the workflow engine") but lists only a single action rather than multiple specific capabilities, so it matches the level-2 anchor rather than the level-3 multi-action example.	2 / 3
Completeness	It answers "what" (execute a Seed spec via the workflow engine) but provides no explicit "Use when..." trigger guidance in the description, so per the rubric guideline it is capped at level 2 ("Has what, but when is missing or only implied").	2 / 3
Trigger Term Quality	It contains the natural phrase "execute seed" but leans on product-internal jargon ("Seed specification", "workflow engine") and lacks broad coverage of common user phrasings, matching the level-2 anchor "some relevant keywords but missing common variations."	2 / 3
Distinctiveness Conflict Risk	The description targets a clear niche (Seed/Ouroboros) so it is not generic, but it lacks distinct trigger phrasing, keeping it at level 2 rather than the level-3 anchor that requires explicit distinct triggers.	2 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (528 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Q00/ouroboros
Path: .claude-plugin/skills/run/SKILL.md
Commit: f09fa36

Reviewed: about 3 hours 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.