prp-loop

Run the autonomous cyclic PRP pipeline end to end (plan → implement → pr → review, looping review→fix until the PR is clean). Use when the user wants to "ship feature X end to end", "run the full PRP loop", "auto-implement and open a PR for a feature", or invokes /prp-loop.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, actionable orchestrator doc with executable commands, a clearly sequenced multi-step workflow with validation and feedback loops, and a clean one-level reference to its script. The only weakness is mild verbosity from the historical Ralph-loop comparison.

Suggestions

Remove or condense the 'UX note' about the retired Ralph loop's single-session/interactive behavior — it is historical context that does not help operate the current headless skill and adds token overhead.

Tighten the 'Notes' section so it states only the operational fact (no Stop-hook; green is detected via each stage's VALIDATION: GREEN sentinel or --validate) without restating loop ownership already covered under 'What it does'.

If the Ralph comparison must be retained, move it to a brief 'Migration from Ralph' sub-line rather than a full explanatory paragraph to preserve the lean, command-first tone.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and command-driven, but the 'UX note' paragraph recounting the retired Ralph loop's history is unnecessary for operating the skill and could be trimmed; it is not score-3 'every token earns its place'.	2 / 3
Actionability	Provides copy-paste-ready executable commands ('uv run .claude/skills/prp-loop/scripts/prp_loop.py "$ARGUMENTS"', '--resume', '--until implement') with concrete flags and stated defaults (--max-cycles 3, --max-implement-iterations 10).	3 / 3
Workflow Clarity	The 'What it does' section sequences plan→implement→pr→review→cycle with explicit validation checkpoints (implement loops until validations pass, review writes a {clean, blocking} verdict) and a review→fix feedback loop, plus enumerated halt conditions — appropriate for autonomous batch operations.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview with clearly signaled one-level-deep references to the real bundle file scripts/prp_loop.py (verified present), and the implementation logic is appropriately split into that script rather than inlined.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 that concisely states what the skill does, names concrete pipeline stages, and provides explicit, natural-language triggers in third person. It clearly answers both what and when with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions via the explicit stage sequence 'plan → implement → pr → review, looping review→fix until the PR is clean', matching the multi-action anchor rather than the single-domain score-2 example.	3 / 3
Completeness	Explicitly answers both 'what' (run the cyclic PRP pipeline end to end with the stage sequence) and 'when' via an explicit 'Use when' clause, so it is not capped at 2 for a missing trigger.	3 / 3
Trigger Term Quality	Includes natural phrases users would actually say — 'ship feature X end to end', 'run the full PRP loop', 'auto-implement and open a PR for a feature', and the '/prp-loop' invocation — giving good coverage rather than just one keyword.	3 / 3
Distinctiveness Conflict Risk	A clear niche (the PRP cyclic pipeline orchestrator) with distinct, specific triggers, unlikely to fire for unrelated skills; voice is third person so no specificity penalty applies.	3 / 3
	Total	12 / 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: Wirasm/prp
Path: .claude/skills/prp-loop/SKILL.md
Commit: 1142738

Reviewed: 11 days 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.