Tessl • The management layer for AI agent skills

SkillPublic

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

76%

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 strong, fully actionable five-phase workflow with concrete commands, complete JSON schemas, and genuine validation feedback loops at every risky boundary. Its weaknesses are localized verbosity (a repetitive fact-definition paragraph and a thrice-stated patience rule) and the absence of any reference-file split for long protocol/schema content.

Suggestions

Rewrite the fact-sheet definition paragraph into 1-2 tight sentences — the current 'A fact may... A fact may... Again, a fact is...' repetition adds tokens without adding guidance.

State the browser-session patience rule once (Phase 1) and reference it from Phases 2 and 3 instead of restating it.

Move the adapted grilling protocol blockquote and the interview/facts JSON schemas into a references/ file, keeping SKILL.md as a lean phase overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but the fact definition paragraph is repetitive ('A fact may describe... A fact may determine... Again, a fact is literally anything...') and the browser-session patience rule is restated three times across phases. Fits the mostly-efficient-but-could-be-tightened anchor; not 2 because padding is localized, not pervasive.	3 / 5
Actionability	Fully executable throughout: copy-paste bash commands with tee patterns, complete inline JSON schemas for interview and facts bundles, exact CLI invocations ('plannotator setup-goal interview goals/<slug>/interview.json --json'), and enumerated answerMode values. Matches the fully-executable anchor.	5 / 5
Workflow Clarity	Five clearly sequenced phases with explicit validation checkpoints: rearticulation confirmed by the user before continuing, a pre-facts answer-review ruleset (uncertainty, skipped-with-note, skipped-without-note), dismissed-session handling, and a re-gate feedback loop ('If denied, revise from feedback and re-gate until approved'). Matches the explicit-validation-with-feedback-loops anchor.	5 / 5
Progressive Disclosure	Well-organized into a clear phase structure with no nested references and everything one level deep, but no bundle files exist and all content (grilling protocol, JSON formats) is inlined in a ~178-line file that could partially live in reference files. Fits the good-structure-minor-gaps anchor; not 5 because some inlineable content (the adapted grilling protocol, JSON schema examples) belongs in separate files.	4 / 5
	Total	17 / 20 Passed

Description

58%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 communicates a clear, multi-action pipeline anchored to a specific tool (Plannotator) and output (/goal), making it reasonably distinctive. Its main weakness is the complete absence of a 'when to use' trigger clause and natural synonym coverage, which caps completeness and trigger quality at 3.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when the user wants to turn an idea, feature request, or objective into an actionable goal package') to raise completeness above 3.

Include natural trigger synonyms users would actually say — 'set up a goal', 'plan this feature', 'create a spec' — alongside the existing 'idea' and 'objective' terms.

Mention the end state more concretely (a launchable /goal command) so the description's final trigger phrase matches what the user will do with the output.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Interviews the user, builds a reviewed fact sheet via Plannotator, then explores the codebase to produce an execution plan' — matching the several-specific-actions anchor. Not 5 because coverage has gaps (e.g., grilling, plan gating, goal output are unmentioned); not 3 because it goes beyond 1-2 actions.	4 / 5
Completeness	The 'what' is clearly stated (turn an idea into a goal package via interview, fact sheet, and codebase exploration), but the 'when' is entirely missing — no 'Use when...' clause or equivalent trigger guidance, capping this dimension at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Contains relevant keywords ('idea', 'objective', 'goal', 'execution plan', 'codebase') but misses natural variations and synonyms users would say ('set up a goal', 'plan this feature', 'spec it out'), and lacks any explicit 'Use when' phrasing. Fits the some-keywords-but-missing-variations anchor.	3 / 5
Distinctiveness Conflict Risk	Names the specific toolchain ('Plannotator', 'goal package for /goal') giving it a clear niche with mostly distinct triggers. Not 5 because generic planning phrases ('explores the codebase to produce an execution plan') carry minor overlap risk with general planning/scaffolding skills.	4 / 5
	Total	14 / 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
Revision: bbcaa97

Reviewed: 22 days ago

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.

plannotator-setup-goal

Table of Contents

Is this your skill?