plannotator-setup-goal

Turn an idea or objective into a goal package for /goal. Interviews the user, builds a reviewed fact sheet via Plannotator, then explores the codebase to produce an execution plan.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./apps/skills/extra/plannotator-setup-goal/SKILL.md

Quality

Content

81%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 is a highly actionable, well-sequenced multi-phase workflow with concrete commands, JSON schemas, and strong validation checkpoints. The main weakness is mild verbosity in a few normative passages and the absence of any external reference files for a skill of this size.

Suggestions

Tighten the fact-sheet prose in Phase 3 (e.g., collapse "A fact is literally anything... Again, a fact is literally anything...") to remove redundant explanation.

Consider extracting the grilling protocol and/or the JSON schema reference into a reference file (references/) and linking to it, which would lift progressive disclosure toward the one-level-deep ideal.

Trim the browser-session patience rules to a single concise directive per phase to reduce repeated normative text.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence, but a few padded normative passages ("A fact is literally anything that can be tested...", "Again, a fact is literally anything...") and verbose browser-patient rules could be trimmed, fitting the "mostly efficient but includes some unnecessary explanation" anchor.	3 / 5
Actionability	Provides fully executable, copy-paste-ready commands (mkdir -p, plannotator setup-goal ... --json, tee into result files, plannotator annotate --gate) plus complete JSON schemas for every artifact and exact file paths, covering the common cases concretely.	5 / 5
Workflow Clarity	Five phases are clearly sequenced with explicit validation checkpoints and feedback loops — wait-for-confirmation in Rearticulate, address skipped/uncertain answers before facts, gate the plan with --gate and re-gate until approved, and stop on dismissed sessions — matching the explicit-validation-with-error-recovery anchor.	5 / 5
Progressive Disclosure	Well-organized into clearly headed phases with no nested references and a self-contained single file (no bundle files exist in references/scripts/assets), but the larger multi-phase body keeps the grilling protocol, question-area lists, and JSON schemas inline where a skill of this size could split some detail out, fitting anchor 4 rather than the ideal one-level-deep split of anchor 5.	4 / 5
	Total	17 / 20 Passed

Description

66%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 specific and action-oriented with a clear niche, but it omits an explicit "Use when..." trigger clause, which caps completeness and leaves the activation condition implicit. Adding concrete trigger phrases would raise the completeness and trigger-term dimensions.

Suggestions

Append an explicit trigger clause such as "Use when the user wants to set up a new goal for /goal from an idea, objective, or rough plan."

Add natural synonyms users might say ("turn this into a goal", "scope out a feature", "plan a change") to broaden trigger-term coverage.

Tighten the "what" by leading with the artifact output ("Produces a goal package at goals/<slug>/") so the deliverable is named first.

Dimension	Reasoning	Score
Specificity	Names the domain and three concrete actions — "Interviews the user", "builds a reviewed fact sheet via Plannotator", "explores the codebase to produce an execution plan" — with only minor coverage gaps, matching the "lists several specific actions" anchor rather than the fully comprehensive anchor 5.	4 / 5
Completeness	Has a clear "what" (interview, fact sheet, codebase exploration, plan) but no explicit "Use when..." trigger clause, so per the missing-trigger guidance completeness is capped at 3 rather than reaching the both-what-and-when anchors.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ("idea or objective", "goal", "fact sheet", "execution plan", "codebase") with good coverage, but is missing common synonyms/variants that would push it to the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The Plannotator/"goal package for /goal" niche and specific artifact types make it mostly distinct with only minor overlap risk against general planning skills, fitting anchor 4 rather than the clearly-niche anchor 5.	4 / 5
	Total	15 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: backnotprop/plannotator
Path: apps/skills/extra/plannotator-setup-goal/SKILL.md
Commit: 79cb016

Reviewed: 1 day 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.