planner-rt-ica

Same reverse-thinking method as dh:rt-ica (see dh:rt-ica or dh-glossary for the definition), but localizes any MISSING input to the affected task only, as a non-blocking information-completeness pre-pass before task decomposition and plan generation. Use when grooming backlog items, generating plans, decomposing tasks under uncertainty, or working in brownfield and refactor scenarios. Produces completeness summary (APPROVED-FOR-PLANNING, APPROVED-WITH-GAPS, or BLOCKED-FOR-PLANNING), missing input report with dependency mapping, required unblock actions, and planning annotations for downstream tasks. Use dh:rt-ica instead at the S2 implementation gate where missing inputs must halt execution.

Quality

55%

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 ./plugins/development-harness/skills/planner-rt-ica/SKILL.md

Quality

Content

38%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 content is well-reasoned and internally consistent as a planning methodology, but it is far too long and monolithic for a SKILL.md: large enumerated catalogs that belong in bundled reference files are inlined, the guidance is classification-heavy rather than executable, and there is no progressive disclosure structure.

Suggestions

Move the Safe Default Gate criteria, the 12 ambiguity escalation classes, and the 15 report-back categories into bundled reference files (e.g. references/safe-default-gate.md, references/ambiguity-rules.md, references/report-back.md) and reference them one level deep from SKILL.md.

Add a concise numbered workflow up front (pre-pass -> classify each input -> apply Safe Default Gate -> batch ASK-USER -> emit output contract) with explicit validation/reclassification feedback loops so the sequence is unambiguous.

Trim explanatory prose that restates what each status label means once the labels are defined, and replace descriptive paragraphs with a worked example showing a sample plan's completeness analysis.

Dimension	Reasoning	Score
Conciseness	The ~370-line body extensively explains and enumerates concepts (16 Safe Default Gate criteria, 12 ambiguity classes, 15 report-back categories) that are highly padded; much could be condensed or moved to bundled reference files without loss.	2 / 5
Actionability	Provides concrete vocabulary, an output contract, and a literal <concerns> block format, but the guidance is mostly classification and prose rules rather than executable steps or worked examples an agent can directly follow.	3 / 5
Workflow Clarity	Status vocabulary, escalation routing, and an output contract give a recognizable sequence with reflection checkpoints, but there is no explicit validate-then-fix feedback loop and the ordering of pre-pass -> classify -> emit is implicit rather than stepwise numbered.	3 / 5
Progressive Disclosure	No bundle files exist and the entire framework (gate criteria, ambiguity catalog, report-back catalog, output template) is inlined into SKILL.md; large reference-style content that clearly belongs in separate files is buried inline with no navigation.	2 / 5
	Total	10 / 20 Passed

Description

72%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 highly specific and clearly answers both what the skill does and when to use it, with strong distinctiveness guidance against its sister skill. Its weakness is trigger-term quality: it leans on internal vocabulary (rt-ica, dh-glossary) rather than natural user language, slightly limiting discoverability.

Suggestions

Lead the description with a plain-language trigger phrase (e.g. 'Use when planning or decomposing work and some inputs are unknown') before referencing the rt-ica framework, so users who don't know the internal terminology can still discover it.

Reduce reliance on internal jargon like 'dh:rt-ica' and 'dh-glossary' in the opening sentence, or move those cross-references to a later sentence.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and deliverables: 'localizes any MISSING input to the affected task only', 'non-blocking information-completeness pre-pass', and specific outputs (completeness summary, missing input report, dependency mapping, unblock actions, planning annotations).	5 / 5
Completeness	Clearly states what the skill does and gives an explicit 'Use when' clause with multiple concrete scenarios; the 'when' could be sharper by leading with the user-facing trigger rather than the cross-reference to a sister skill.	4 / 5
Trigger Term Quality	Includes some natural phrases users would say ('grooming backlog items', 'generating plans', 'decomposing tasks', 'brownfield and refactor scenarios'), but leans heavily on internal jargon (rt-ica, dh:rt-ica, dh-glossary) that a user would not naturally utter.	3 / 5
Distinctiveness Conflict Risk	Mostly distinct thanks to explicit differentiation from the blocking sister skill dh:rt-ica ('Use dh:rt-ica instead at the S2 implementation gate'), though minor overlap risk exists between the two RT-ICA variants.	4 / 5
	Total	16 / 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: Jamie-BitFlight/claude_skills
Path: plugins/development-harness/skills/planner-rt-ica/SKILL.md
Commit: 4e1e73b

Reviewed: ~13 hours 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.