CtrlK
BlogDocsLog inGet started
Tessl Logo

he-heartbeat

Create bounded Harness Engineering follow-up checkpoints, resume packets, stop conditions, and automation-safe handoff notes. Use when work must continue later without losing state or silently becoming autonomous execution.

53

Quality

60%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./Plugins/harness-engineering/skills/he-heartbeat/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

35%

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

This skill provides a reasonable structural framework for heartbeat/checkpoint automation but suffers significantly from lack of actionability—there are no concrete schemas, structured output examples, or executable commands. The workflow is sequenced but vague, relying on abstract descriptions rather than specific, reproducible steps. The content would benefit greatly from a concrete heartbeat payload example and explicit validation criteria.

Suggestions

Add a concrete example of a complete heartbeat output payload (JSON schema with schema_version, next_invocation, stop condition, subagent_policy, etc.) so Claude knows exactly what to produce.

Replace the natural language examples with structured input/output pairs showing the actual heartbeat prompt and structured response for at least one scenario.

Add explicit validation checkpoints within the Procedure steps (e.g., 'After step 3, verify no duplicate heartbeat exists by checking [specific field/condition]') rather than deferring validation to a separate abstract section.

Consolidate the overlapping Gotchas, Anti-Patterns, and Constraints sections into a single 'Guardrails' section to reduce redundancy and improve token efficiency.

DimensionReasoningScore

Conciseness

The content is moderately efficient but includes some vague or abstract phrasing that doesn't add actionable value (e.g., 'apply the context-disposition policy', 'classify the strongest side effect'). Some sections like Philosophy and Execution Boundaries could be tightened. However, it avoids explaining basic concepts Claude already knows.

2 / 3

Actionability

The skill is almost entirely abstract guidance with no concrete code, commands, schemas, or executable examples. The 'Outputs' section mentions a schema but never defines it. The 'Examples' section provides natural language descriptions of use cases rather than actual input/output pairs or structured heartbeat payloads. There is nothing copy-paste ready.

1 / 3

Workflow Clarity

The Procedure section provides a numbered sequence of steps, and there are validation and failure mode sections that mention fail-fast behavior. However, the steps are vague ('encode cadence, destination, stop criteria'), lack explicit validation checkpoints between steps, and the feedback loop for error recovery is underspecified ('stop and return the blocker with the smallest recovery step').

2 / 3

Progressive Disclosure

The References section provides clearly signaled one-level-deep links to supporting files, and the Stage Arc Boundary references an external contract. However, no bundle files were provided to verify these references exist, and the main content itself could benefit from better separation—the anti-patterns, gotchas, and constraints sections overlap significantly and could be consolidated or restructured.

2 / 3

Total

7

/

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.

This is a well-structured description that clearly defines both what the skill produces and when it should be used. Its main strength is the explicit 'Use when' clause and the specificity of its deliverables. The primary weakness is that trigger terms lean toward specialized jargon rather than natural user language, which could reduce discoverability when users phrase requests more casually.

Suggestions

Add more natural trigger terms users might say, such as 'pick up later', 'save progress', 'pause and resume', 'context handoff', or 'don't lose my place'.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'bounded follow-up checkpoints', 'resume packets', 'stop conditions', and 'automation-safe handoff notes'. These are distinct, named deliverables rather than vague abstractions.

3 / 3

Completeness

Clearly answers both what ('Create bounded follow-up checkpoints, resume packets, stop conditions, and automation-safe handoff notes') and when ('Use when work must continue later without losing state or silently becoming autonomous execution'). The 'Use when' clause is explicit.

3 / 3

Trigger Term Quality

Includes some relevant terms like 'handoff notes', 'resume', 'continue later', and 'losing state', but the language is fairly specialized ('Harness Engineering', 'automation-safe', 'resume packets'). Users might more naturally say things like 'pick up where I left off', 'save progress', 'pause work', or 'context handoff' which are missing.

2 / 3

Distinctiveness Conflict Risk

The description carves out a very specific niche around work continuation state management with safety constraints against autonomous execution. The 'Harness Engineering' qualifier and focus on 'stop conditions' and 'automation-safe' handoff make it highly distinctive and unlikely to conflict with other skills.

3 / 3

Total

11

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

Total

10

/

11

Passed

Repository
jscraik/Agent-Skills
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.