ouroboros-run

Execute a Seed specification through the workflow engine

Quality

54%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/run/SKILL.md

Quality

Content

67%Weight 40%Scale 1-5

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 concrete tool calls and a well-sequenced workflow including validation, but it is a verbose single-file monolith that inlines material which would benefit from being split into one-level-deep reference files.

Suggestions

Move the host-specific observer spawning (Codex spawn_agent / OMP Task / Claude Code Task) and the Synapse/Conductor protocols into separate reference files linked from SKILL.md to improve progressive disclosure.

De-duplicate the deferred-schema-reload guidance into one canonical statement referenced where needed, reducing repetition.

Tighten the relay-loop pseudocode and relay-style examples; keep the structured-field contract but trim redundant prose.

Dimension	Reasoning	Score
Conciseness	The body is dense operational specification rather than concept explanation, but it repeats the deferred-schema-reload injunction several times and inlines lengthy host-specific observer/relay/Synapse/Conductor prose that could be tightened, fitting 'mostly efficient but includes some unnecessary explanation or could be tightened'.	3 / 5
Actionability	It supplies exact MCP tool names (ouroboros_start_execute_seed, ouroboros_job_wait, ouroboros_job_result) with full argument blocks and a copy-paste relay loop, covering the common execution and monitoring cases fully.	5 / 5
Workflow Clarity	A clear numbered 1-10 sequence includes explicit validation checkpoints (deferred-schema guard, Conductor verify-decide-log-act, validate-before-mutation) and feedback loops, but the heavy branching across host runtimes and observer/fallback paths leaves minor validation/sequencing gaps.	4 / 5
Progressive Disclosure	No references/scripts/assets bundle exists and everything lives in one ~560-line SKILL.md; large host-specific and protocol sections that clearly belong in separate reference files are inlined, matching 'content that clearly belongs in separate files is inlined' despite the presence of section headers.	2 / 5
	Total	14 / 20 Passed

Description

41%Weight 40%Scale 1-5

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 a clear but minimal one-liner: it states what the skill does but omits any trigger/when guidance and relies on domain jargon, limiting trigger-term quality and completeness.

Suggestions

Add an explicit 'Use when ...' clause naming concrete trigger phrases (e.g. 'Use when the user asks to run or execute a seed, start an Ouroboros workflow, or says "ouroboros run"').

List 1-2 more concrete actions beyond 'execute' (e.g. validate, monitor, relay progress) to raise specificity.

Include natural synonyms and the file extension (e.g. 'seed', '.yaml', 'workflow run') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Seed specification", "workflow engine") but offers only a single generic action ("Execute"), matching the anchor 'Names the domain but actions are minimal or generic' rather than the 1-2 concrete actions required for a 3.	2 / 5
Completeness	It clearly states the 'what' ("Execute a Seed specification through the workflow engine") but provides no 'when'/Use-when guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	"Execute a Seed specification through the workflow engine" leans on technical jargon ("Seed specification", "workflow engine") with only one natural term ("execute"); common variations and synonyms users would actually say are missing, fitting the 'one or two generic keywords' anchor.	2 / 5
Distinctiveness Conflict Risk	"Seed specification" plus "workflow engine" carves a fairly specific Ouroboros niche with only minor overlap risk against closely related execution skills, though without the plugin name it is not maximally distinct.	4 / 5
	Total	11 / 20 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 (562 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: skills/run/SKILL.md
Commit: 80333ae

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.