CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ralph-prompt-single-task

Generate Ralph-compatible prompts for single implementation tasks. Creates prompts with clear completion criteria, automatic verification, and TDD approach. Use when creating prompts for bug fixes, single features, refactoring tasks, or any focused implementation that can be completed in one session.

Quality

84%

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

The canonical home for this skill is ralph-prompt-single-task in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

Highly actionable and clearly sequenced content with strong validation and feedback loops. Its main weaknesses are verbosity from three near-duplicate worked examples and the absence of any progressive disclosure of example material into separate files.

Suggestions

Move the three worked example prompts into a references/EXAMPLES.md file and keep only one inline example, adding clearly signaled one-level-deep references (e.g., "**Bug fix example**: See EXAMPLES.md").

Trim the second and third examples (or replace them with short input/output sketches) to remove the near-duplicate repetition of the full prompt template and reduce token cost.

Condense the good/bad completion-criteria table and DO/DON'T lists, which restate guidance already embedded in the template and validation checklist.

DimensionReasoningScore

Conciseness

The body is mostly efficient and actionable, but the full ~50-line prompt template is essentially repeated three times across the worked examples, and sections like the good/bad criteria table explain things Claude can largely infer. Cutting one or two examples would tighten it considerably.

3 / 5

Actionability

Fully executable guidance throughout: a copy-paste-ready prompt template, specific verification commands (npm test, grep -r, curl), and three complete worked examples covering the common task types (bug fix, feature, refactor).

5 / 5

Workflow Clarity

The 4-step generation workflow is clearly sequenced, includes an explicit validation checklist, a TDD feedback loop (write test, run, fix, repeat), and "If Stuck" recovery guidance, matching the strongest anchor.

5 / 5

Progressive Disclosure

Section structure and navigation are good, but all ~360 lines live in a single SKILL.md with no references/ directory; the three full example prompts (~150 lines) are exactly the kind of content that belongs in a separate references file, which keeps it below anchor 4.

3 / 5

Total

16

/

20

Passed

Description

83%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.

A strong description with third-person voice, explicit when-to-use triggers, and concrete capability statements. It is slightly held back by unmentioned body capabilities (promise tags, If Stuck guidance) and some overlap risk with sibling Ralph prompt skills.

DimensionReasoningScore

Specificity

Lists several concrete actions ("Creates prompts with clear completion criteria, automatic verification, and TDD approach") but omits other capabilities present in the body, such as promise tags, verification commands, and "If Stuck" guidance, so coverage has minor gaps rather than being comprehensive.

4 / 5

Completeness

Explicitly answers both what ("Generate Ralph-compatible prompts... Creates prompts with clear completion criteria, automatic verification, and TDD approach") and when ("Use when creating prompts for bug fixes, single features, refactoring tasks, or any focused implementation that can be completed in one session") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural trigger phrases like "bug fixes", "single features", "refactoring tasks" match what users would actually say; a few natural variants (e.g., "write a prompt for a task", "one-off change") are missing.

4 / 5

Distinctiveness Conflict Risk

The "single implementation tasks" and "completed in one session" scoping gives it a clear niche distinct from the sibling multi-task/project/research skills, but the general prompt-creation domain creates minor overlap risk with those closely related skills.

4 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

fernandezbaptiste/Skrillz

Path

.claude/skills/ralph-prompt-single-task/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.