CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-harness-construction

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent's tool set, action space, or observation format.

67

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

The canonical home for this skill is tdg-personal/agent-harness-construction

SKILL.md
Quality
Evals
Security

Quality

Content

76%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.

A compact, well-organized design-principles skill that is token-efficient and concrete. Its main weakness is the absence of a sequenced workflow with validation checkpoints for the high-risk operations it references.

Suggestions

Add a short sequenced workflow (e.g., audit action space -> redesign observations -> add error-recovery contracts -> benchmark) with explicit validation/verification checkpoints, especially before high-risk operations like deploy or migration.

Include one or two brief worked examples illustrating the observation design or error-recovery contract applied to a concrete tool, to lift actionability from principles to copy-paste-ready.

Consider moving the detailed field-level contracts (observation shape, error-recovery contract) into a reference file and signaling it one level deep, which would let the overview stay lean while improving progressive disclosure.

DimensionReasoningScore

Conciseness

Lean, terse bullet-style guidance with no padding and no explanation of concepts Claude already knows; every section earns its tokens.

5 / 5

Actionability

Provides concrete, specific directives (e.g., exact observation fields 'status/summary/next_actions/artifacts' and the error-recovery contract), but lacks worked examples showing the principles applied, leaving minor gaps for an instruction-only skill.

4 / 5

Workflow Clarity

Content is organized into topical sections but presents parallel design principles rather than a sequenced workflow, and gives no validation/verification checkpoints despite referencing high-risk operations (deploy, migration, permissions), which caps this dimension at 3.

3 / 5

Progressive Disclosure

Well-organized single-file overview with clear section headers and appropriately inline concise content; slightly exceeds the simple-skill threshold and could optionally split detailed contracts into references, so it sits just below 5.

4 / 5

Total

16

/

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-structured description that clearly states capabilities and an explicit 'Use when' trigger targeting a distinct niche. Minor room to broaden trigger synonyms and surface recovery/context topics.

DimensionReasoningScore

Specificity

Names several concrete actions ('Design and optimize') applied to specific objects ('action spaces, tool definitions, and observation formatting'), but coverage is not fully comprehensive since body-only topics like recovery and context budgeting are absent from the description.

4 / 5

Completeness

Explicitly answers both what ('Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates') and when ('Use when defining or revising an agent's tool set, action space, or observation format') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good coverage of natural terms for this niche ('tool set', 'action space', 'observation format', 'tool definitions'), though a few synonyms or looser phrasings a user might say are missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (agent harness construction) with distinct, specific triggers; minimal overlap risk with other skills.

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.