CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-goal

Create a slash-command `/goal` for long-running Codex or Claude Code work when the user explicitly asks for a `/goal`, agent goal, or completion condition. Outputs one goal line with the objective, starting context, validation evidence, and stop condition.

80

Quality

100%

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

100%

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

A compact, well-structured instruction skill that gives a concrete template, an ordered generation process, and a verification checklist. It stays lean, assumes competence, and needs no external bundle.

DimensionReasoningScore

Conciseness

Lean and efficient: a template, four guiding questions, terse field definitions, and short rules — no explanations of concepts Claude already knows, every section earning its place.

3 / 3

Actionability

Provides a copy-paste-ready `/goal` template with labeled placeholders, concrete field meanings, and a specific example check ('`bun test packages/auth` exits 0'); the guidance is directly executable for an instruction-only skill.

3 / 3

Workflow Clarity

Single-task skill with an unambiguous sequence ('Answer these in order, then compress them into one line') and an explicit 'Check' verification checklist before handing back the goal.

3 / 3

Progressive Disclosure

A small, single-purpose skill with no need for external references; content is organized into clearly signaled sections (Shape, Rules, Platform Note, Check) and no bundle files are required.

3 / 3

Total

12

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A focused, third-person description that states concrete outputs and explicit use-when triggers for a well-bounded artifact. It answers both what and when without padding or over-claiming.

DimensionReasoningScore

Specificity

Lists multiple concrete actions: 'Outputs one goal line with the objective, starting context, validation evidence, and stop condition,' naming the four distinct deliverables of the artifact.

3 / 3

Completeness

Explicitly answers what ('Create a slash-command `/goal`... Outputs one goal line...') and when ('when the user explicitly asks for a `/goal`, agent goal, or completion condition').

3 / 3

Trigger Term Quality

Gives natural trigger phrasings users would say — 'the user explicitly asks for a `/goal`, agent goal, or completion condition' — covering several common variations.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche — the slash-goal artifact for long-running Codex/Claude Code work — with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
EpicenterHQ/epicenter
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.