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

74%

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 ./templates/plate-playground-template/.agents/skills/autogoal/SKILL.md

Quality

Content

77%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 highly actionable with concrete commands, tool contracts, and explicit validation feedback loops for a durable-state workflow. Its weaknesses are length/repetition across sections and inlining of reference-grade material that could be split into bundle files for better progressive disclosure.

Suggestions

Consolidate the repeated template/pack-selection and 'fill the generated plan, don't replace it' guidance into a single authoritative section and cross-reference it elsewhere to cut redundancy.

Move the full goal-plan schema block and the template-quality bar into dedicated bundle files under assets/ (e.g., assets/templates/goal-plan-schema.md) and link to them from SKILL.md to improve progressive disclosure.

Add explicit 'See <path> for details' navigation cues beside the script command references so the bundle files function as clear drill-down targets.

Dimension	Reasoning	Score
Conciseness	The ~1258-line body is largely unique domain policy Claude would not already know, but it repeats the same guidance several times — template/pack selection and 'fill the generated plan, don't replace it' each appear across multiple sections — so it could be tightened.	3 / 5
Actionability	Provides copy-paste-ready bash commands with concrete flags, exact tool contracts (get_goal/create_goal/update_goal status values), a tool-objective shape template, and ready closeout/blocked report shapes covering the common cases.	5 / 5
Workflow Clarity	Multi-step flows (Start Workflow, Completion Gate Policy, Repair workflow, Resume Protocol) are explicitly sequenced with validation checkpoints and feedback loops such as check-complete.mjs as the final mechanical gate and 'verify unfinished plans still fail the checker'.	5 / 5
Progressive Disclosure	Section structure is clear and referenced bundle files (scripts/, assets/templates/) genuinely exist, but reference-grade content like the full goal-plan schema and template-quality bar is inlined in SKILL.md and script references are command invocations rather than well-signaled 'see X for details' navigation.	3 / 5
	Total	16 / 20 Passed

Description

71%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-rich, laying out the complete goal lifecycle with concrete mechanisms and a distinct niche. Its main weakness is the missing explicit 'Use when' trigger guidance, which caps completeness and limits trigger-term coverage.

Suggestions

Append an explicit 'Use when...' clause to the description naming natural triggers (e.g., 'Use when the user asks to set a durable goal, keep working until a verifiable end state, or repair a goal-backed workflow that missed expectations').

Add user-natural synonyms like 'keep going until', 'long-running', and 'autonomous work' alongside 'goal' to broaden trigger-term coverage.

Tighten the mechanism list slightly so the description reads as a concise handle rather than a comma-heavy inventory.

Dimension	Reasoning	Score
Specificity	Enumerates the full goal lifecycle as concrete actions — 'Create, verify, repair, and close' — plus concrete mechanisms (measurable outcomes, evidence gates, plan templates, blocker handling, completion audits), matching the comprehensive-coverage anchor.	5 / 5
Completeness	The description gives a clear and comprehensive 'what' but no 'when'/'Use when' clause, so per the missing-trigger-guidance cap it lands at the clear-what-without-when anchor.	3 / 5
Trigger Term Quality	Strong core keywords (goal, durable, verify, close, repair) but missing natural synonyms a user would say such as 'keep going until', 'long-running', or 'autonomous work', which the good-overall anchor treats as full coverage.	4 / 5
Distinctiveness Conflict Risk	The durable-goal lifecycle niche is clearly distinct from most skills, but 'goal' is a broad enough term to risk minor overlap with general planning or task-management skills.	4 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1259 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 2 missing, 2 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	13 / 16 Passed

Repository: udecode/plate
Path: templates/plate-playground-template/.agents/skills/autogoal/SKILL.md
Commit: 9ec2c8e

Reviewed: 3 days 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.