ralplan

Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution

1.08x

Quality

65%

Does it follow best practices?

Impact

92%

1.08x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/ralplan/SKILL.md

Quality

Content

70%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 delivers a clearly sequenced, validation-rich consensus workflow with concrete commands and gate examples, but is undermined by significant internal repetition and a monolithic structure with a dangling external reference. Consolidating the repeated sequencing constraints and moving the Pre-Execution Gate detail to a reference file would improve both conciseness and progressive disclosure.

Suggestions

Consolidate the Architect/Critic sequencing constraints (currently restated in steps 3, 4, the blockquote, and the final Important note) into one constraint block to cut redundant tokens.

Remove the empty "## Behavior" heading (it is immediately followed by "## Planning/Execution Boundary") and move the Pre-Execution Gate signal table, examples, and troubleshooting into a reference file such as references/gate.md.

Either add the missing docs/company-context-interface.md to the bundle or drop/inline the reference so the skill is self-contained.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational (gate tables, example prompts, workflow steps) rather than explanatory, but the Architect/Critic sequencing constraints are restated four times (steps 3, 4, the blockquote, and the closing note), flag semantics are repeated between the Flags section and the workflow, and the empty "## Behavior" heading adds noise. It could be consolidated into a single constraint block.	3 / 5
Actionability	Provides copy-paste invocations ("/oh-my-claudecode:ralplan --interactive ...", Skill("oh-my-claudecode:team")), concrete AskUserQuestion option lists, and good/bad prompt examples covering common cases; the minor gap is the deferral to "the Plan skill's full documentation" for core consensus-mode details needed to execute this skill standalone.	4 / 5
Workflow Clarity	The consensus loop is explicitly numbered 0-8 with hard sequencing rules, a bounded feedback loop (max 5 iterations, non-APPROVE verdicts trigger revise/re-review), an explicit approval gate, and a "pending approval" checkpoint before any mutation — clear sequence with explicit validation steps and error-recovery loops.	5 / 5
Progressive Disclosure	Well-sectioned single file with one clearly signaled one-level reference, but no bundle files exist (no references/, scripts/, assets/), the referenced docs/company-context-interface.md is missing from the bundle, and the ~60-line Pre-Execution Gate detail (signal table, examples, troubleshooting) is inline content that belongs in a reference file.	3 / 5
	Total	15 / 20 Passed

Description

61%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 compact, domain-specific, and uses third person with concrete trigger keywords, but it lacks an explicit "Use when..." clause and only hints at the full capability set. Adding a trigger clause and naming the Planner/Architect/Critic consensus loop would raise completeness and specificity.

Suggestions

Append a "Use when" clause, e.g. "Use when the user issues a vague ralph/autopilot/team execution request or asks for consensus planning before implementation."

Name the concrete actions (runs Planner/Architect/Critic loop to consensus, produces a pending-approval plan, supports --interactive/--deliberate flags) instead of only "auto-gates".

Include the other execution keyword "ultrapilot" and synonyms like "underspecified" so natural trigger variations match.

Dimension	Reasoning	Score
Specificity	"Consensus planning entrypoint" plus "auto-gates vague ralph/autopilot/team requests" names the domain and 1-2 concrete actions, but does not enumerate the planning workflow or flags, so coverage is not comprehensive.	3 / 5
Completeness	Has a clear "what" (consensus planning entrypoint that auto-gates requests) but no "Use when..." clause; the "when" is only weakly implied by "vague ... requests", which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Includes the natural execution-mode keywords users would actually type (ralph, autopilot, team, planning), but misses common variations such as ultraplit/ultrapilot (only in the body) and phrases like "underspecified request".	4 / 5
Distinctiveness Conflict Risk	Anchored to specific sibling skill names (ralph/autopilot/team), making it mostly distinct with only minor overlap risk against the generic plan skill.	4 / 5
	Total	14 / 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: Yeachan-Heo/oh-my-claudecode
Path: skills/ralplan/SKILL.md
Commit: dc7ba1d

Reviewed: 3 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.