auto

Automatically converge from goal to A-grade Seed and execute it

Quality

67%

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/auto/SKILL.md

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 highly actionable and clearly workflowed with explicit validation and error-recovery loops, but it is a dense single-file monolith that would benefit from offloading reference material (status-code taxonomies, monitoring protocol) into bundle files for better progressive disclosure and token efficiency.

Suggestions

Split the stop_reason_code taxonomy and interview-closure-mode tables into a references/ file and link to it, reducing the inline token load while keeping the dispatch rules up front.

Extract the detailed background-monitoring observer protocol (Codex/Claude Code child-session delegation, relay filtering rules) into a separate reference and keep only the decision summary inline.

Tighten the repeated status-token enumerations (detached/blocked/failed, queued/running) into compact statements to avoid restating the same enum across multiple sections.

Dimension	Reasoning	Score
Conciseness	The body is operational rather than concept-explaining and largely respects Claude's intelligence, but ~280 lines of repeated status-token enums, stop_reason taxonomy tables, and edge-case polling protocol could be tightened, fitting the 'mostly efficient but includes some unnecessary explanation or could be tightened' anchor.	2 / 3
Actionability	It gives concrete MCP tool names with exact argument signatures (ouroboros_start_auto, ouroboros_job_wait with job_id/cursor/timeout_seconds), a copy-paste CLI-flag→MCP-arg translation table, and explicit call examples, matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	The Background monitoring UX section is a numbered 9-step sequence with explicit validation checkpoints and feedback loops (handle non-terminal status, terminal result fetching, observer-failure fallback, attention_required escalation), matching the 'clear sequence with explicit validation steps; feedback loops for error recovery' anchor.	3 / 3
Progressive Disclosure	It is well-sectioned but a single monolithic ~280-line file with no bundle files (references/scripts/assets absent) and no offloaded reference docs, so taxonomy tables and the monitoring protocol that could be separate stay inline, matching the 'content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 specific to its Ouroboros Auto niche and unlikely to conflict with other skills, but it is purely what-oriented with no 'Use when' trigger guidance and only partial action enumeration, so it lands mid-rubric on completeness and trigger coverage.

Suggestions

Append a 'Use when...' clause with natural user triggers (e.g. 'Use when the user wants to turn a single goal into a finished, A-grade product end-to-end via the Auto pipeline').

List the concrete pipeline phases (e.g. interview, Seed generation, review/repair, run) instead of compressing them to 'converge' and 'execute' so the action set reads as comprehensive.

Add a few common user phrasings ('prototype an app', 'build a product from a description', 'run an auto session') to broaden natural trigger-term coverage.

Dimension	Reasoning	Score
Specificity	It names the Auto-pipeline domain and two concrete actions ('converge from goal to A-grade Seed' and 'execute it') but does not list a comprehensive set of specific actions, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	It states what the skill does (converge to an A-grade Seed and execute) but provides no 'Use when...' clause or explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Terms like 'goal', 'A-grade Seed', 'converge', and 'execute' are relevant to the niche but it omits common user-facing variations (e.g. 'prototype', 'build a feature', 'end-to-end app'), fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The highly specific 'A-grade Seed' / 'converge from goal' framing carves a clear Ouroboros Auto niche unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers; unlikely to conflict' anchor.	3 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Q00/ouroboros
Path: .claude-plugin/skills/auto/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.