rt-ica

Reverse Thinking - Information Completeness Assessment. Mandatory pre-planning checkpoint that blocks planning until prerequisites are verified. Use when receiving specs, PRDs, tickets, RFCs, architecture designs, or any multi-step engineering task. Integrates with CoVe-style planning pipelines. Invoke BEFORE creating plans, delegating to agents, or defining acceptance criteria.

1.36x

Quality

79%

Does it follow best practices?

Impact

94%

1.36x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/rt-ica/SKILL.md

Quality

Discovery

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a solid description with excellent trigger term coverage and clear completeness (both what and when are addressed). The main weaknesses are moderate specificity (what exactly does 'blocking planning' and 'verifying prerequisites' entail?) and some potential overlap with other planning-related skills. The description effectively communicates its role as a mandatory checkpoint in engineering workflows.

Suggestions

Add 1-2 specific concrete actions the skill performs, e.g., 'Identifies missing requirements, flags ambiguous acceptance criteria, surfaces unstated assumptions'

Clarify what makes this distinct from general planning skills by specifying the unique output or verification method

Dimension	Reasoning	Score
Specificity	Names the domain ('pre-planning checkpoint', 'prerequisites verification') and mentions integration with 'CoVe-style planning pipelines', but the concrete actions are abstract ('blocks planning', 'verified') rather than listing specific verification steps or outputs.	2 / 3
Completeness	Clearly answers both what ('Mandatory pre-planning checkpoint that blocks planning until prerequisites are verified') and when ('Use when receiving specs, PRDs, tickets... Invoke BEFORE creating plans, delegating to agents, or defining acceptance criteria').	3 / 3
Trigger Term Quality	Excellent coverage of natural terms users would say: 'specs', 'PRDs', 'tickets', 'RFCs', 'architecture designs', 'multi-step engineering task', 'plans', 'agents', 'acceptance criteria'. These are terms engineers naturally use.	3 / 3
Distinctiveness Conflict Risk	While 'Reverse Thinking' and 'Information Completeness Assessment' provide some distinction, the description could overlap with general planning or requirements-gathering skills. The 'CoVe-style' reference helps but may not be universally understood.	2 / 3
	Total	10 / 12 Passed

Implementation

77%

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

This is a well-designed procedural skill with strong actionability and workflow clarity. The 5-step RT-ICA procedure is concrete and executable with clear decision gates. However, the skill is verbose for its purpose—the XML-style tags, extensive tables, and inline reference material inflate token cost. The content would benefit from splitting reference tables into separate files.

Suggestions

Move the condition_categories table, question_templates, and planning_deliverables sections to separate reference files (e.g., RT-ICA-CATEGORIES.md, RT-ICA-TEMPLATES.md) and link from the main skill

Remove XML-style tags (<core_rule>, <definitions>, etc.) as markdown headers already provide structure—this would reduce token overhead

Condense the definitions table; terms like 'Goal' and 'Condition' don't need formal definitions for Claude

Dimension	Reasoning	Score
Conciseness	The skill is comprehensive but includes some redundancy (e.g., definitions table for terms Claude knows, verbose XML-style tags throughout). The anti-patterns section and question templates add value but could be more condensed.	2 / 3
Actionability	Provides a clear 5-step procedure with explicit decision logic, concrete output format template, and a complete worked example showing exactly how to apply RT-ICA. The decision tree and status classifications are unambiguous.	3 / 3
Workflow Clarity	Excellent multi-step workflow with explicit checkpoints (Step 4 decision gate), clear BLOCKED/APPROVED branching logic, and integration points with CoVe-style planning. The procedure enforces validation before proceeding.	3 / 3
Progressive Disclosure	Content is well-structured with clear sections, but everything is inline in one large file. The condition categories table, question templates, and planning deliverables could be split into reference files. References to related skills are present but the main content is monolithic.	2 / 3
	Total	10 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: Jamie-BitFlight/claude_skills
Commit: 5667e97

Reviewed: 13 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.