autogoal

Create, verify, repair, and close durable Codex goals with measurable outcomes, evidence gates, plan templates, blocker handling, completion audits, and goal-backed workflow repair.

Quality

72%

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 ./.agents/skills/autogoal/SKILL.md

Quality

Content

77%

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

The body is highly actionable and clearly sequenced with strong validation checkpoints, but it is verbose with notable repetition and keeps most policy content inline rather than splitting it into reference files.

Suggestions

Consolidate the repeated rules (completion, template-fill, generated-plan handling) into one canonical section and cross-reference it instead of restating across Completion Rules, Goal Plan, and Template Composition.

Move the long inline policy blocks (Evidence Type Contract, Goal Anatomy, Repair Mode scope matrix, required goal-plan sections) into a reference file under assets/ and keep SKILL.md as a lean overview with one-level-deep links.

Tighten verbose prose throughout by assuming Claude's competence and keeping only the rules, commands, and templates that earn their tokens.

Dimension	Reasoning	Score
Conciseness	The content is skill-specific rather than teaching known concepts, but the ~1200-line body repeats the same rules in several places (e.g., "do not mark complete because", "fill the generated plan", template-fill guidance each restated 3+ times) and could be tightened substantially.	2 / 3
Actionability	Provides copy-paste-ready bash commands (create-goal-scratchpad.mjs, init-templates.mjs, check-complete.mjs), concrete objective/threshold examples ("p95 < 120 ms", "score >= 0.92"), and exact report/checklist templates.	3 / 3
Workflow Clarity	The 15-step Start Workflow, hybrid Completion Gate Policy with check-complete.mjs as a mechanical validation gate, and 7-step Repair workflow with a "Prove the repair" checkpoint give explicit sequencing with validation and feedback loops.	3 / 3
Progressive Disclosure	Real bundle files (scripts/ and assets/templates/ including packs/) are referenced one level deep via path-coded blocks, but SKILL.md itself is a monolithic ~1200-line rulebook with large policy sections inline rather than an overview pointing to detailed materials.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 occupies a clear niche, but it omits explicit "Use when..." trigger guidance and relies on skill jargon over natural user phrasings, capping both completeness and trigger-term quality at 2.

Suggestions

Append a "Use when..." clause naming natural user triggers (e.g., "Use when the user asks to keep working until a verifiable end state, or says continue / keep going / rerun the benchmark until it works").

Soften jargon by pairing technical terms with plain phrasings users actually say ("durable goals" -> "keep working until done", "evidence gates" -> "proof that it's done").

Add the goal-setup and repair triggers that appear in the body's "Use When" section so the description alone signals when to invoke the skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Create, verify, repair, and close") plus specific mechanisms ("measurable outcomes, evidence gates, plan templates, blocker handling, completion audits"), matching the multi-action anchor.	3 / 3
Completeness	Clearly answers "what" with concrete capabilities but has no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Contains some natural terms ("goals", "verify", "repair") but leans on skill-specific jargon ("evidence gates", "completion audits", "goal-backed workflow repair") and omits the plain user phrasings the body itself lists ("keep going until it works", "continue").	2 / 3
Distinctiveness Conflict Risk	The durable-goal lifecycle niche (measurable outcomes, evidence gates, plan templates, blocker/completion rules) is distinct and unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1207 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/autogoal/SKILL.md
Commit: 45116fd

Reviewed: about 14 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.