prp-loop

Runs the detached, resumable PRP pipeline in fresh headless CLI sessions, cycling plan, implementation, PR, review, and corrections with persisted state and safety bounds. Use only when the user explicitly asks to "run the full PRP loop", "run this detached", "continue across context windows", use headless autonomous execution, resume a saved loop, or invokes /prp-loop. Use prp-issue for ordinary end-to-end delivery.

Quality

96%

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

Quality

Content

92%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 action-first with executable commands, a clearly sequenced multi-stage workflow, explicit validation/halt checkpoints, and a well-organized single-script bundle. Only minor conciseness slack comes from the legacy Ralph-loop comparison.

Suggestions

Consider condensing or removing the 'UX note' about the retired Ralph loop; it is historical context rather than operational guidance and adds tokens Claude does not need to act.

Dimension	Reasoning	Score
Conciseness	The body is lean — executable commands up front, terse stage list, compact Safety/Notes — but the 'UX note' paragraph comparing the retired Ralph loop is contextual lore that could be trimmed without losing operational clarity.	4 / 5
Actionability	Copy-paste-ready commands cover the common cases (new loop with args, --resume, --until implement, --validate) and each flag's effect is stated concretely, e.g. '`--until implement` runs plan → implement and stops once validations are green...'.	5 / 5
Workflow Clarity	The plan → implement → pr → review → cycle sequence is explicit, with validation checkpoints (VALIDATION: GREEN sentinel, authoritative --validate, halt conditions on no-progress/failed push/dirty review) and a bounded review→fix feedback loop for this batch/autonomous operation.	5 / 5
Progressive Disclosure	A single bundled script (scripts/prp_loop.py, verified present) is referenced one level deep and appropriately signaled, and the body is organized into clear sections (Run it, Stop after a stage, What it does, Safety, Notes) well within the simple-skill threshold.	5 / 5
	Total	19 / 20 Passed

Description

100%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 third-person, concise, and fully covers what the skill does, when to trigger it, and how it differs from prp-issue. It uses natural trigger phrases and concrete pipeline stages with no padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete pipeline actions — 'cycling plan, implementation, PR, review, and corrections' — each qualified with specifics like 'fresh headless CLI sessions', 'persisted state', and 'safety bounds', giving comprehensive coverage rather than a single generic verb.	5 / 5
Completeness	Explicitly answers both: what ('Runs the detached, resumable PRP pipeline...cycling plan, implementation, PR, review, and corrections') and when ('Use only when the user explicitly asks to...'), with concrete trigger phrases rather than weak implication.	5 / 5
Trigger Term Quality	Embeds the natural phrases a user would actually say — "run the full PRP loop", "run this detached", "continue across context windows", "resume a saved loop", "/prp-loop", "headless autonomous execution" — covering synonyms and the slash-command invocation.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (detached/resumable autonomous cyclic pipeline) and actively disambiguates from the sibling skill via 'Use prp-issue for ordinary end-to-end delivery', minimizing wrong-skill triggering.	5 / 5
	Total	20 / 20 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: Wirasm/prp
Path: .claude/skills/prp-loop/SKILL.md
Commit: 9724799

Reviewed: ~12 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.