CtrlK
BlogDocsLog inGet started
Tessl Logo

planner-rt-ica

Runs 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. Localizes missing inputs to affected tasks only — does not block plan generation. 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. Non-blocking sister to dh:rt-ica — use dh:rt-ica at the S2 implementation gate where missing inputs must halt execution.

66

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

61%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.

A thorough, well-structured instruction skill with concrete vocabulary, output contract, and XML template, weakened by length and repetition across sections and by an implicit rather than explicitly sequenced workflow.

Suggestions

Consolidate the Safe Default Gate, ambiguity escalation, and report-back lists with their restatements in 'Behavioral Rules' and section 3A to remove repetition and cut length.

Add one explicit numbered pre-pass workflow (e.g. classify inputs → evaluate Safe Default Gate → route resolution → validate via reflection checkpoint → emit output) with validation checkpoints, so the sequence is not scattered across sections.

Convert the ambiguity-class routing prose into a compact decision table mapping each class to its default route (HARD-BLOCKED / ASK-USER / DISCOVER / VALIDATION-SPIKE) for crisper actionability.

DimensionReasoningScore

Conciseness

The ~380-line body avoids explaining concepts Claude already knows, but is notably repetitive — the Safe Default Gate (16 items), ambiguity escalation (12 items), and report-back (15 items) lists overlap with content restated in 'Behavioral Rules' and section 3A, so it could be tightened well beyond minor trims.

3 / 5

Actionability

Instruction-only guidance is highly concrete: a fixed status vocabulary, resolution types, a 16-criterion gate, a named multi-section output contract, and a copy-paste <concerns> XML template; it falls just short of fully executable because some routing is prose rather than a crisp decision table.

4 / 5

Workflow Clarity

The pre-pass process is distributed across Role, Complexity Model, Inputs Analyzed, Output Contract, and Behavioral Rules rather than a single numbered sequence with explicit checkpoints; a reflection checkpoint and the data-deletion hard-block rule exist, but the top-level sequence and its validation gates remain mostly implicit.

3 / 5

Progressive Disclosure

No bundle files exist and the skill is one well-organized self-contained file with clear headers (no nested references), which is appropriate; the long gate/ambiguity/report-back checklists could arguably be split into reference files, a minor organization gap keeping it just below a 5.

4 / 5

Total

14

/

20

Passed

Description

100%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 exemplary: third-person voice, concrete actions and outputs, comprehensive natural trigger phrases, explicit what/when, and an explicit sister-skill disambiguation that bounds conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and outputs — 'Runs information completeness pre-pass', 'Localizes missing inputs', and a full output set (completeness summary with three named states, missing input report with dependency mapping, unblock actions, planning annotations) — giving comprehensive coverage rather than just a few.

5 / 5

Completeness

Explicitly answers both 'what' (pre-pass producing a named summary, report, unblock actions, and annotations) and 'when' ('Use when grooming backlog items, generating plans, decomposing tasks under uncertainty, or working in brownfield and refactor scenarios').

5 / 5

Trigger Term Quality

Natural user-facing phrases like 'grooming backlog items', 'generating plans', 'decomposing tasks under uncertainty', and 'brownfield and refactor scenarios' cover the common ways a user would request this, including synonyms.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche and explicitly disambiguates from its sibling ('Non-blocking sister to dh:rt-ica — use dh:rt-ica at the S2 implementation gate where missing inputs must halt execution'), minimizing wrong-skill triggering.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
Jamie-BitFlight/claude_skills
Reviewed

Table of Contents

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.