humanize-rlcr

Start RLCR (Ralph-Loop with Codex Review) on Codex using the native Stop hook.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/humanize-rlcr/SKILL.md

Quality

Content

77%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.

The body is a well-sequenced, actionable flow definition with explicit validation and hook-driven feedback loops. Its main weakness is organization of reference-like inline content (the options table and enforcement list) that has no accompanying bundle file to offload it.

Suggestions

Move the options table into a bundled reference file (e.g. references/options.md) and link to it from SKILL.md to improve progressive disclosure.

Tighten the "What This Enforces" bullet list to the few items Claude actually needs to act on, or push the full list into a reference.

Confirm the referenced scripts (setup-rlcr-loop.sh, cancel-rlcr-loop.sh) exist in the bundle, since the scripts/ directory was not present.

Dimension	Reasoning	Score
Conciseness	It is mostly efficient and operational with no padding of concepts Claude already knows, but the 15-item "What This Enforces" list and the large options table could be tightened — it sits at the mostly-efficient-but-could-trim level rather than fully lean.	2 / 3
Actionability	Commands are concrete and copy-paste ready ("{{HUMANIZE_RUNTIME_ROOT}}/scripts/setup-rlcr-loop.sh" $ARGUMENTS, the cancel script), with explicit file paths and a runnable usage section.	3 / 3
Workflow Clarity	The sequence is explicit (Setup → numbered Work Round steps 1-7) with a validation checkpoint ("If setup exits non-zero, stop and report the error") and a clear feedback loop ("If the hook blocks exit, follow the returned instructions exactly and continue the next round").	3 / 3
Progressive Disclosure	Sections are clearly labeled and references to setup/cancel scripts are one-level deep, but no bundle files exist and the sizable options table and enforcement list are inline content that could be split into a reference — matching the "could be better organized" anchor.	2 / 3
	Total	10 / 12 Passed

Description

57%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.

The description is specific and distinct but incomplete: it tells Claude what to start without any explicit guidance on when to use it. Adding a "Use when..." clause would lift completeness and trigger coverage.

Suggestions

Add an explicit trigger clause, e.g. "Use when starting or resuming an RLCR Codex review loop."

Expand the action list beyond a single "Start" verb to cover what the loop actually does (implement rounds, commit, run Codex review).

Include common user phrasings like "Codex review loop" alongside "RLCR" to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	It names a concrete action — "Start RLCR (Ralph-Loop with Codex Review) on Codex using the native Stop hook" — but lists only a single starting action rather than the multiple concrete actions the score-3 anchor requires.	2 / 3
Completeness	It states what the skill does (start RLCR on Codex) but provides no "Use when..." trigger guidance, so the "when" is missing — which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	"RLCR", "Codex", and "Stop hook" are the terms a user of this tool would say, but "Ralph-Loop" and "native Stop hook" lean technical and common variations (e.g. "Codex review loop") are missing.	2 / 3
Distinctiveness Conflict Risk	"RLCR" and "Codex Review" form a clear, named niche unlikely to trigger for unrelated skills, matching the distinct-triggers anchor.	3 / 3
	Total	9 / 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: PolyArch/humanize
Path: skills/humanize-rlcr/SKILL.md
Commit: 0ec921a

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.