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

97%

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.

A tight, highly executable skill body: copy-paste commands, a clearly sequenced pipeline with validation feedback loops, explicit safety bounds and halt conditions, and a verified single-script bundle. The only blemish is a brief historical aside about a retired predecessor loop that could be cut or condensed.

Suggestions

Trim the 'UX note' paragraph: keep the actionable half (inspect/resume via ~/.prp/<key>/state/prp-loop.state.json instead of watching live) and drop the description of the retired Ralph loop's Stop-hook mechanics, or move the comparison to a short 'old patterns' note.

Consider one line showing how to inspect loop progress (e.g., tailing the run.log or reading the state file's stage field) so operators can check on a detached run without resuming it.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — commands, defaults, and halt conditions with zero concept explanation — but the "UX note" paragraph about the retired Ralph loop mixes historical comparison ("was single-session and interactive (a Stop-hook fed the prompt back...)" ) with useful guidance and could be trimmed to just the actionable half. Not 5 because of this minor over-explanation; not 3 because nothing else is padded.	4 / 5
Actionability	Fully executable copy-paste commands for both start and resume ("uv run .agents/skills/prp-loop/scripts/prp_loop.py \"$ARGUMENTS\" --cli codex" and the --resume variant), plus the --until example, all defaults (--max-cycles, --max-implement-iterations, --validate), and the state-file path for inspection.	5 / 5
Workflow Clarity	The five stages are sequenced (plan → implement → pr → review → cycle) with an explicit feedback loop ("if the verdict needs fixes, the complete report, plan, and live PR feed into a fresh prp-implement correction pass → push → re-review, up to --max-cycles"), explicit validation detection (VALIDATION: GREEN sentinel or --validate), and enumerated halt conditions.	5 / 5
Progressive Disclosure	A short, single-purpose skill (~50-line body) with well-organized sections (Run it, What it does, Safety, Notes) and a single one-level-deep bundle reference (scripts/prp_loop.py, verified to exist and to implement --until/--validate/the GREEN sentinel and state file described). No inlined content that belongs in separate files; nothing needs external references.	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.

An exemplary description: concrete third-person capability statement, explicit and quoted trigger conditions, and active disambiguation from the sibling prp-issue skill. Every clause is load-bearing with no fluff or over-claiming.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — "Runs the detached, resumable PRP pipeline in fresh headless CLI sessions, cycling plan, implementation, PR, review, and corrections with persisted state and safety bounds" — covering the full pipeline comprehensively with no vague filler.	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, matching the anchor-5 example structure.	5 / 5
Trigger Term Quality	Quoted natural phrases a user would actually say ("run the full PRP loop", "run this detached", "continue across context windows", "resume a saved loop") plus the skill-name invocation ($prp-loop) give comprehensive coverage including synonyms for this niche. Not the 4 anchor because the quoted phrases cover the common variations users would use, not just a few keywords.	5 / 5
Distinctiveness Conflict Risk	Clear niche with distinct triggers; the "Use only when" restriction plus explicit disambiguation ("Use prp-issue for ordinary end-to-end delivery") minimizes conflict risk with sibling delivery skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Wirasm/prp
Path: .agents/skills/prp-loop/SKILL.md
Commit: 4352925

Reviewed: 7 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.