CtrlK
BlogDocsLog inGet started
Tessl Logo

continue

Use after an execution slice to reassess whether the current tactic still serves the user's north star, then keep course, pivot, replan, or stop. Designed for long-running loops where the agent should keep moving unless a real blocker or completed lane exists.

66

Quality

81%

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

77%

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

The content is highly actionable with a clear sequenced workflow and explicit checkpoints, but it is a long monolithic document with internal redundancy that leaves room for tightening and possible extraction into reference files.

Suggestions

Collapse the overlapping guidance among Core Questions, Escalation Rules, and Verdicts into a single decision spine to cut length and reduce conciseness drag.

Extract the verdict definitions, Output format, and state-file field lists into a reference file referenced one level deep from SKILL.md to lift progressive_disclosure toward 3.

Lead with a compact one-screen procedure (Read First → verdict → execute) so the core loop is unambiguous before the detailed rules follow.

DimensionReasoningScore

Conciseness

The body is mostly lean and directive with no padding of basics Claude already knows, but Core Questions, Escalation Rules, and Verdicts overlap in spirit and add length that could be tightened, so it does not reach the every-token-earns-its-place level 3.

2 / 3

Actionability

As an instruction-only skill it provides concrete executable guidance: an exact Output format with named fields, a full example block, enumerated state-file fields, and hard rules such as 'never use status: blocked when the checkpoint names a runnable next move'.

3 / 3

Workflow Clarity

A clear sequence runs Read First → evaluate → verdict → same-turn state update → execute next move, with explicit validation checkpoints (Completion Guard, patch-limit escalation) and feedback loops for error recovery, matching the level-3 anchor rather than the checkpoint-missing level 2.

3 / 3

Progressive Disclosure

The skill is a single self-contained file with no bundle references and is organized into many short sections, but at ~390 lines it is monolithic and exceeds the simple-skill (<50 line) threshold that would justify a 3; it falls between the well-organized level 2 and the multi-file level 3.

2 / 3

Total

10

/

12

Passed

Description

85%

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 cleanly answers both what and when with a concrete verdict taxonomy and a distinct niche, though its trigger language is somewhat jargon-flavored for the intended audience.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'keep course, pivot, replan, or stop' and 'reassess whether the current tactic still serves the user's north star' — matching the multiple-specific-actions anchor rather than the partial domain-only level 2.

3 / 3

Completeness

Explicitly states both what ('reassess... then keep course, pivot, replan, or stop') and when ('Use after an execution slice... Designed for long-running loops where the agent should keep moving unless a real blocker or completed lane exists'), matching the level-3 anchor and not the level-2 what-only case.

3 / 3

Trigger Term Quality

Includes relevant natural-ish terms ('long-running loops', 'real blocker', 'completed lane') but leans on domain jargon ('execution slice', 'north star') rather than the broad everyday phrasing that defines the level-3 anchor, so it sits below 3 and above the jargon-only 1.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear niche as a progress governor with named verdicts, making it unlikely to trigger for unrelated file- or code-handling skills; not generic enough to fall to level 2.

3 / 3

Total

11

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
udecode/plate
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.