discovery

Use the discovery tools to find and use services through a service matcher. Do not rely on prior knowledge of services, providers, or APIs.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./packages/agentmask/openclaw-plugin-discovery/skills/discovery/SKILL.md

Quality

Content

78%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 well-structured, actionable, and self-contained, with a clear required workflow and hard rules that constrain behavior. Minor gains are available by trimming repeated anti-drift emphasis and making the worked example's call arguments more concrete.

Suggestions

Consolidate the repeated 'do not rely on prior knowledge' guidance so it appears once in the intro and is referenced, not restated, in the hard rules.

Replace the generic placeholders in the worked example with a realistic intent and concrete args so the example is copy-paste ready.

Add an explicit error-recovery feedback loop (e.g. what to do when a service_call fails or a method is not found in the description) to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete tool list, a tight workflow, and a generic worked example, but the 'do not rely on prior knowledge' message is restated across the intro and hard rules, which could be trimmed slightly.	4 / 5
Actionability	It gives concrete tool names, parameter shapes, and a worked example with real calls, but the example uses generic placeholders ('do X with my Y', '["…"]') rather than fully copy-paste-ready invocations.	4 / 5
Workflow Clarity	The numbered 'Required workflow' is a clear sequence with explicit branch/stop checkpoints (no candidates → stop; non-public → stop), though it lacks an explicit fix-and-retry feedback loop for error recovery.	4 / 5
Progressive Disclosure	The skill is self-contained with no bundle files and is organized into clearly labeled sections (Tools, Required workflow, Hard rules, Worked example), giving easy navigation with no nested references.	5 / 5
	Total	17 / 20 Passed

Description

61%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.

The description is clear and reasonably specific about the discovery workflow, but it omits an explicit 'when to use' trigger and only lightly enumerates concrete actions. Adding a 'Use when...' clause and naming the discrete operations would raise completeness and specificity.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to locate or invoke a service and you have no prior knowledge of available providers.'

Name the concrete actions the skill performs (query the matcher, inspect a service description, initiate contact, invoke a method) to lift specificity above 3.

Include a couple of natural user phrasings or synonyms (e.g. 'find available services', 'look up a provider') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain and two concrete actions ('find and use services through a service matcher') but does not enumerate the specific operations the tools perform, leaving coverage non-comprehensive.	3 / 5
Completeness	It clearly states what the skill does but lacks an explicit 'Use when...' trigger clause, so per the judging guideline completeness is capped at 3 with only a weakly implied 'when'.	3 / 5
Trigger Term Quality	It surfaces natural terms a user would say ('services', 'providers', 'APIs', 'discovery') with good coverage, though a few common synonyms or phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	The 'service matcher' / 'discovery tools' framing carves a fairly distinct niche with minimal overlap risk, though the broad term 'services' leaves slight overlap with other integration skills.	4 / 5
	Total	14 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: Consensys-Incorporated/ocap-kernel
Path: packages/agentmask/openclaw-plugin-discovery/skills/discovery/SKILL.md
Commit: 3d5aea9

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.