CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ralph

Self-referential loop until task completion with configurable verification reviewer

Quality

62%

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

70%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 delivers exceptionally actionable, well-sequenced guidance with real validation gates and feedback loops — model execution clarity. Its weaknesses are repetition (the verify-gate contract is explained five times) and the absence of any progressive disclosure: everything, including deep policy specs and basic execution hygiene, lives in one large file.

Suggestions

State the omc ralph verify contract (flags, exit codes, timeout handling, baseline semantics) once — in <Precondition_Feedback_Gate> — and have Steps 1f, 4b, and 7.6 reference it instead of restating it, cutting substantial tokens.

Move the PRD_Criterion_Amendments ledger spec, the stale-state reconciliation JSON example, and the parallel-session caveats into one-level-deep reference files under references/ and link them clearly, keeping SKILL.md as the loop overview.

Drop or trim the <Advanced> background/foreground execution rules and other reminders of basics Claude already knows; keep only the skill-specific policy.

DimensionReasoningScore

Conciseness

The ~370-line body restates the verify-gate semantics in five places (<Precondition_Feedback_Gate>, Step 1f, Step 4b, Step 7.6, Final Checklist), repeats the "polite-stop anti-pattern / do not stop after approval" warning in both Step 7 and Escalation_And_Stop_Conditions, and includes an <Advanced> section explaining background-vs-foreground execution basics ("Package installation... run in background", "Quick status checks... foreground") that Claude already knows. Not 3 because these are several distinct padded/redundant sections rather than minor tightening opportunities; not 1 because most of the policy content is genuine non-obvious domain knowledge rather than generic concept explanation.

2 / 5

Actionability

Guidance is fully executable: exact commands with flags ("omc ralph verify --write-baseline --session <sessionId>", "omc ralph closeout --deslop completed"), concrete state paths (.omc/state/sessions/{sessionId}/prd.json, feedback-baseline.json), a JSON reconciliation schema, programmatic API signatures (amendCriterion/supersedeCriterion), and complete worked examples for Task() delegation and criterion amendment. Exit-code semantics (0 = pass, 1 = new failures) make the gates machine-checkable.

5 / 5

Workflow Clarity

Ten explicitly sequenced steps with lettered sub-steps, mandatory validation gates at story verification (Step 4), post-deslop regression (Step 7.6), and closeout, plus explicit feedback loops: exit-1 failures are fixed and re-verified, reviewer rejection (Step 9) loops back to fixing and re-marking, and a Final Checklist enforces terminal state. Not 4 because validation checkpoints are not merely present but explicit and exit-code driven throughout.

5 / 5

Progressive Disclosure

Sections are clearly labeled (XML-style tags, numbered steps), but this is a single monolithic ~370-line file: detailed policy blocks (the criterion-amendment ledger spec, stale-state reconciliation JSON, parallel-session caveats, background-execution rules) are inlined where reference files would fit, and mentions of docs/shared/agent-tiers.md, docs/company-context-interface.md, and docs/REFERENCE.md are buried mid-paragraph rather than clearly signaled navigation — and no references/ bundle exists. Not 2 because the internal structure is strong and navigation within the file is possible; not 4 because several substantial blocks clearly belong in one-level-deep reference files.

3 / 5

Total

15

/

20

Passed

Description

37%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 conveys a clear what (a persistence loop with reviewer verification) but is thin on concrete capabilities, carries no natural user trigger phrases, and omits any use-when guidance. The body's own Use_When list shows exactly which trigger terms were left on the table.

Suggestions

Add a "Use when..." clause with the natural trigger phrases already documented in the body: "Use when the user says 'ralph', 'don't stop', 'keep going until done', or when a task must be completed and verified, not just attempted."

Enumerate 2-3 concrete capabilities instead of abstractions, e.g. "Builds and refines a PRD of user stories with testable acceptance criteria, iterates story-by-story with automatic retry, and gates completion on fresh reviewer verification against each criterion."

Differentiate from sibling skills in the description itself (e.g. mention PRD-driven stories or the verification gate) so it does not collide with autopilot/goal-loop skills.

DimensionReasoningScore

Specificity

"Self-referential loop until task completion" names the domain but the only action stated is an abstract "loop until... completion"; "configurable verification reviewer" is a feature modifier, not a concrete action like "creates a prd.json", "runs feedback commands", or "verifies stories against acceptance criteria". It does not reach the 3 anchor because it never enumerates 1-2 concrete actions, and it is above 1 because the domain is named with a discernible mechanism.

2 / 5

Completeness

A clear "what" is present (loops on a task until completion with a configurable reviewer), but the "when" is entirely absent — no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guideline. Not 4 because the when is not merely implicit-weak, it is missing outright; not 2 because the what is concrete, not vague.

3 / 5

Trigger Term Quality

The description contains only generic technical terms ("self-referential loop", "task completion", "verification reviewer") and none of the natural phrases a user would say — the body itself lists "ralph", "don't stop", "must complete", "finish this", "keep going until done" as triggers, yet none appear in the description. Score 2 rather than 3 because even the domain-level keywords users would utter (persistence, retry, PRD) are missing.

2 / 5

Distinctiveness Conflict Risk

"Self-referential loop until task completion" carves a niche (persistence/loop skills) but "task completion" and "verification" are broad enough to overlap with general completion, review, or goal-tracking skills. Not 4 because without distinctive trigger words (e.g. "ralph", PRD-driven) it remains confusable with sibling loop/goal skills in the same plugin (autopilot, ultragoal).

3 / 5

Total

10

/

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

Yeachan-Heo/oh-my-claudecode

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.