CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ralph

MCP-owned Ralph loop around background evolve_step jobs

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/ralph/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 an unusually precise operational spec: exact tool signatures, defaults, response branches, and failure-recovery paths leave little ambiguity about what to do at each stage. Its weaknesses are mild — some cross-section repetition and unspecified argument sets for two secondary tools — and it is correctly scoped as a single-file orchestration skill.

DimensionReasoningScore

Conciseness

The body is spec-dense with no concept explanations and assumes Claude's competence ("The `ouroboros_ralph` tool owns the loop (do not reimplement it)", "Never quote verify commands or expected outputs"). Minor trimmable redundancy remains: observer ownership and cursor rules are restated across §3 and §4, and the observer-handoff paragraph crams several rules into run-on sentences. Matches anchor 4, not 5, due to that repetition.

4 / 5

Actionability

Gives exact tool signatures with parameters and defaults (`ouroboros_job_wait(job_id, cursor, timeout_seconds=120, stream="linked", wait_for="attention_or_ac_change")`), discovery commands (`"+ouroboros ralph job"`), naming formats (`ralph-<short-slug>-<uuid>`), and a copy-paste report template. Minor gaps keep it below anchor 5: `ouroboros_record_conductor_decision` and the full `ouroboros_session_signal` argument set are named but not specified.

4 / 5

Workflow Clarity

A clearly numbered §1–§5 sequence (prepare → start → handle response → monitor → terminate) with explicit validation checkpoints (deferred-schema guard before every call, fail-closed sentinel validation) and error-recovery feedback loops for observer failure, spawn failure, plugin delegation, and user interruption. Matches anchor 5: explicit validation, feedback loops, and per-outcase terminal handling.

5 / 5

Progressive Disclosure

No bundle files exist; the single file is well-organized under `## Usage`, `## Instructions` with `###` subsections, and a footer section, so navigation is easy. At ~78 dense lines, content like the relay rules and Conductor decision policy could plausibly live in one-level-deep reference files; matches anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

36%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 highly distinctive but opaque: it identifies the mechanism with unique jargon while failing to state what the skill concretely does or when to use it. A reader outside the Ouroboros ecosystem cannot determine the skill's purpose or triggers from this text alone.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when the user wants to run an autonomous evolution loop until QA passes, mentions Ralph, or asks to iterate a lineage').

Replace jargon-only phrasing with 2-3 concrete actions the skill performs, e.g., 'Starts, monitors, and reports on background evolve_step generation loops; relays progress; supports mid-run steering and cancellation.'

Include natural trigger terms users would actually say — 'evolution loop', 'iterate until passing', 'keep refining', 'lineage run' — alongside the proper nouns.

DimensionReasoningScore

Specificity

"MCP-owned Ralph loop around background evolve_step jobs" names the domain and mechanism but contains no concrete action verbs describing what the skill actually does (start, monitor, cancel, report). Matches anchor 2 (names the domain, actions minimal/generic); not 3 because no 1-2 concrete actions are listed.

2 / 5

Completeness

The single clause gives only a vague 'what' ("loop around background evolve_step jobs" presumes prior knowledge of the ecosystem) and completely omits any 'when to use' guidance — no "Use when..." clause or equivalent. Matches anchor 2 (vague what, no when); not 3 because the 'what' is not clear to an uninitiated reader.

2 / 5

Trigger Term Quality

The description is dominated by technical jargon and proper nouns ("MCP-owned", "Ralph loop", "evolve_step") with no natural phrases a user would say when needing this skill. Not 1 only because "Ralph" and "background jobs" are phrases target users do utter, but common natural variations are entirely missing.

2 / 5

Distinctiveness Conflict Risk

Unique ecosystem proper nouns ("Ralph", "evolve_step", "MCP-owned") carve out a clear niche with virtually no overlap risk against other skills. Matches anchor 5 (clear niche, minimal conflict risk).

5 / 5

Total

11

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

Q00/ouroboros

Path

skills/ralph/SKILL.md

Reviewed

Table of Contents

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.