CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-goal

Draft a `/goal` line that gives long-running Codex or Claude Code work an objective, validation evidence, and a stop condition. Use when the user explicitly asks for `/goal`, an agent goal, or a completion condition.

73

Quality

92%

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

92%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 tight, highly actionable instruction skill: a concrete template, an ordered procedure, hard rules with a worked example, and a pre-handoff checklist. Its only inefficiency is the Platform Note's slight redundancy with the Rules section.

Suggestions

Merge the Platform Note into the Rules section (e.g., as a one-line rule: 'the goal must not rely on hidden state — run checks and surface evidence in the transcript') to remove the redundancy with Rule 2.

Consider replacing the four-question plaintext block with the same content folded into the shape template's slot labels, cutting a few lines while keeping the procedure.

DimensionReasoningScore

Conciseness

The body is efficient and assumes competence — the shape template, four-question sequence, and rules all earn their tokens. The "Platform Note" section partially restates Rule 2 (transcript-judgeable vs. no hidden state) and could be trimmed or merged, which keeps it just below the lean anchor.

4 / 5

Actionability

The skill provides a copy-paste-ready `/goal` line template with labeled slots, an ordered four-question procedure, and a concrete contrast example ("`bun test packages/auth` exits 0" beats "tests pass"). For an instruction-only skill the guidance is fully executable.

5 / 5

Workflow Clarity

The sequence is clear and ordered (answer the four questions in order, compress into one line, apply rules), and the "Check" section serves as an explicit pre-handoff validation checklist. No destructive or batch operations, so no feedback loop is required.

5 / 5

Progressive Disclosure

This is a ~58-line single-purpose skill with no need for external references, and no bundle files exist. Sections are well-organized with no inlined bulk content and no nested references, so simple-skill full credit applies.

5 / 5

Total

19

/

20

Passed

Description

87%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.

A strong description: concrete, third-person, and well-scoped, with an explicit trigger clause tied to specific phrases a user would naturally say. Its only gap is modest keyword breadth (no synonyms like "definition of done"), leaving trigger coverage just short of comprehensive.

DimensionReasoningScore

Specificity

"Draft a `/goal` line that gives long-running Codex or Claude Code work an objective, validation evidence, and a stop condition" names the domain and several concrete deliverables (objective, evidence, stop condition), but stops short of the fuller action coverage (starting context, checkpoints) the skill body actually provides.

4 / 5

Completeness

It explicitly answers both what ("Draft a `/goal` line that gives... an objective, validation evidence, and a stop condition") and when ("Use when the user explicitly asks for `/goal`, an agent goal, or a completion condition") with concrete trigger phrases.

5 / 5

Trigger Term Quality

"Use when the user explicitly asks for `/goal`, an agent goal, or a completion condition" includes good natural keywords users would say, but misses common synonyms such as "definition of done" or "success criteria".

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche (the slash-goal artifact for long-running agent work) with distinct triggers, and the explicit-ask trigger wording minimizes the chance of firing for ordinary prompt drafting.

5 / 5

Total

18

/

20

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.

Validation — 16 / 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.