opplan-converter

Convert engagement documents into machine-readable OPPLAN for the ralph loop — objective decomposition, acceptance criteria, MITRE mapping, priority ordering.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/soundwave/opplan-converter/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 content is a concise, well-sequenced overview that assumes Claude's competence and includes validation and approval checkpoints, but it leaves some step mechanics underspecified and includes one dangling reference path that undermines progressive disclosure.

Suggestions

Make Steps 1–2 more mechanically actionable (e.g., name the specific CONOPS fields to read and the decomposition heuristics) instead of deferring entirely to references.

Fix or remove the broken ../references/schema-quick-reference.md reference, or add the missing file under references/, so every signaled path resolves.

Inline the validation checklist referenced in Step 6 (or at least its key checks) so the validate→fix→retry feedback loop is visible without a follow-up read.

Dimension	Reasoning	Score
Conciseness	The body is lean — terse sections, a routing table, and compact bullets — and it assumes Claude already knows MITRE/CONOPS/RoE concepts, with only minor repetition of the one-context-window rule.	3 / 3
Actionability	It gives concrete guidance (OBJ-{NUMBER} IDs, the phase→sub-agent table, mandatory criteria examples, opsec enum values, and an add_objective→list_objectives tool sequence), but Steps 1–2 stay high-level and defer most mechanics to references, leaving some key details unspecified.	2 / 3
Workflow Clarity	A clear six-step sequence includes an explicit Validate step and an approval gate ('present for user approval before starting execution'), matching the anchor for a clear sequence with explicit validation checkpoints.	3 / 3
Progressive Disclosure	Overview content is appropriately split into one-level-deep, clearly signaled references (objective-templates.md, objective-rules.md, both real files), but the referenced ../references/schema-quick-reference.md does not exist in the bundle, breaking the navigation promise.	2 / 3
	Total	10 / 12 Passed

Description

67%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 distinctive, clearly conveying a well-scoped niche, but it relies on specialized jargon for triggers and omits an explicit 'Use when...' clause, leaving the when-to-use guidance implied rather than stated.

Suggestions

Add an explicit 'Use when...' trigger clause to the description (e.g., 'Use when converting engagement/CONOPS plans into runnable objectives or setting up the ralph loop') to raise completeness.

Soften the jargon-heavy triggers by including natural phrasings a user would actually say (e.g., 'convert plan to tasks', 'set up objectives') alongside OPPLAN/ralph-loop terms.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'objective decomposition, acceptance criteria, MITRE mapping, priority ordering' alongside the core conversion — matching the anchor for several specific concrete actions rather than just naming a domain.	3 / 3
Completeness	It clearly states what the skill does, but the description field lacks any 'Use when...' clause or equivalent explicit trigger; per the judging guideline a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Terms like 'OPPLAN', 'ralph loop', and 'MITRE mapping' are domain-specific jargon rather than natural phrasing a user would spontaneously say, so it has relevant keywords but misses common natural variations.	2 / 3
Distinctiveness Conflict Risk	The combination of 'machine-readable OPPLAN for the ralph loop' with MITRE mapping carves out a clear niche that is unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: PurpleAILAB/Decepticon
Path: packages/decepticon/decepticon/skills/standard/soundwave/opplan-converter/SKILL.md
Commit: e34afba

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.