CtrlK
BlogDocsLog inGet started
Tessl Logo

covalent

Covalent integration. Manage Organizations, Projects, Pipelines, Users, Goals, Filters. Use when the user wants to interact with Covalent data.

59

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/covalent/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 a well-structured, largely executable guide to driving Covalent through the Membrane CLI, with clear state-handling and polling feedback loops. Its main weaknesses are minor padding, placeholder-only examples without a worked end-to-end call, and an undefined 'Step 2' reference.

DimensionReasoningScore

Conciseness

The body is mostly command- and table-driven with little concept explanation Claude lacks, but it carries minor padding such as the marketing intro ("Covalent is a unified API that provides access to blockchain data... building web3 applications") and phrases like "so you can focus on the integration logic rather than auth plumbing", fitting the 'efficient with minor trim opportunities' anchor rather than the fully lean 5.

4 / 5

Actionability

It provides concrete, copy-pasteable CLI commands (install, login, connection ensure, action list/run, request) with flags and a popular-actions table, but every example uses unsubstituted placeholders (<actionId>, CONNECTION_ID) with no end-to-end worked example using real values, leaving minor gaps that cap it at 4 rather than 5.

4 / 5

Workflow Clarity

The install → authenticate → connect → poll-until-ready → handle clientAction states → search → run/proxy flow is clearly sequenced with a genuine feedback loop (poll connection state, act on CLIENT_ACTION_REQUIRED, re-poll), but the "skip to Step 2" reference points at an undefined Step 2 and the 1b subsection lacks a labeled 1a, introducing minor sequencing gaps.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ all absent) and the skill is self-contained with clear section headers; the inlined popular-actions table and proxy-flag reference could arguably live in separate reference files, but the organization is good enough to sit at 4 rather than the 3 anchor for content that should be separated.

4 / 5

Total

16

/

20

Passed

Description

62%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 covers both what and when and is anchored by a distinct brand name, but it relies on one generic verb and a thin set of trigger keywords. Tightening the action verbs and adding natural blockchain-data phrases would lift the lower dimensions.

Suggestions

Replace the single generic verb 'Manage' with concrete actions that reflect the skill's actual capabilities (e.g., 'Query token balances, fetch NFT metadata, retrieve log events, list block heights').

Add natural trigger terms users actually say, such as 'blockchain data', 'on-chain data', 'token balances', 'wallet address', or 'NFT metadata', to the 'Use when...' clause.

Align the listed entities with the real Covalent surface area — the current list (Organizations, Projects, Pipelines, Users, Goals, Filters) does not match the blockchain-data actions the body documents, raising conflict risk with unrelated skills.

DimensionReasoningScore

Specificity

The description names the domain (Covalent) and enumerates six managed objects ("Organizations, Projects, Pipelines, Users, Goals, Filters"), but every object shares the single generic verb "Manage", so the concrete actions are minimal rather than comprehensive, fitting the 1-2 concrete actions anchor better than the multi-verb 4 anchor.

3 / 5

Completeness

It states both a 'what' ("Covalent integration. Manage Organizations, Projects, Pipelines, Users, Goals, Filters.") and an explicit 'when' ("Use when the user wants to interact with Covalent data."), but the trigger is generic rather than packed with concrete trigger phrases, so it sits at 4 rather than 5.

4 / 5

Trigger Term Quality

The only natural keyword present is the brand name in "Use when the user wants to interact with Covalent data"; common user phrases like blockchain data, on-chain data, token balances, or wallet/NFT lookups are missing, matching the 'some relevant keywords but missing variations' anchor.

3 / 5

Distinctiveness Conflict Risk

Naming the specific product "Covalent" gives it a clear niche with low conflict risk, though the generic managed-entity list (Organizations, Projects, Users, etc.) could overlap with adjacent project/CRM skills, keeping it just below the minimal-conflict 5 anchor.

4 / 5

Total

14

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
membranedev/application-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.