CtrlK
BlogDocsLog inGet started
Tessl Logo

autonomous-agent-harness

Transform Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing. Replaces standalone agent frameworks (Hermes, AutoGPT) by leveraging Claude Code's native crons, dispatch, MCP tools, and memory. Use when the user wants continuous autonomous operation, scheduled tasks, or a self-directing agent loop.

61

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/autonomous-agent-harness/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 actionable and well-structured with concrete examples, but it is over-long for a single SKILL.md, mildly padded, and—critically for an automation skill—lacks explicit validation/feedback loops in its workflows. Splitting detail into reference files and adding verification checkpoints would lift the weaker dimensions.

Suggestions

Add explicit validate-then-retry checkpoints to the example workflows (e.g., after a cron run, verify task completion and handle errors before proceeding) to satisfy the batch-operations workflow bar.

Move the detailed Setup Guide, the Replacing Hermes table, and the Example Workflows into separate one-level-deep reference files linked from the overview to improve progressive disclosure.

Trim explanatory padding (Computer Use capabilities list, the large ASCII architecture diagram) to content Claude cannot infer from the component names.

DimensionReasoningScore

Conciseness

Mostly action-oriented with code examples, but padded in places (e.g., the Computer Use capabilities list and the large ASCII architecture diagram explain structure Claude can infer), and could be tightened throughout.

3 / 5

Actionability

Provides mostly executable guidance: concrete MCP tool calls, curl dispatch examples, claude -p commands, an MCP config JSON block, and a task-queue file format, with only minor illustrative gaps.

4 / 5

Workflow Clarity

Setup steps and example workflows are numbered, but because this skill drives batch/automated operations (crons, dispatch) and the workflows lack explicit validate-fix-retry checkpoints, the batch-operations cap holds it at 3 despite the rough sequence.

3 / 5

Progressive Disclosure

Has clear section headers and structure, but at ~268 lines it is a monolithic single file with no bundle references; content like the detailed setup guide, Hermes comparison table, and example workflows could live in separate one-level-deep files.

3 / 5

Total

13

/

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, well-scoped description that clearly states both capability and activation triggers in third person. It is specific and distinctive, with only minor room to add more granular action verbs and everyday synonyms.

DimensionReasoningScore

Specificity

Lists several specific concrete capabilities ("persistent memory, scheduled operations, computer use, and task queuing"; "native crons, dispatch, MCP tools, and memory") but they are capability categories rather than granular actions, leaving minor coverage gaps relative to the level-5 anchor.

4 / 5

Completeness

Explicitly answers both what ("Transform Claude Code into a fully autonomous agent system with...") and when ("Use when the user wants continuous autonomous operation, scheduled tasks, or a self-directing agent loop") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural phrases ("continuous autonomous operation", "scheduled tasks", "self-directing agent loop") plus named frameworks ("Hermes, AutoGPT") users would cite, but misses common everyday synonyms like "run this every day" or "automate".

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (autonomous agent harness) and names specific competing frameworks, making it unlikely to trigger for unrelated skills; minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
affaan-m/ECC
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.