Tessl • The management layer for AI agent skills

SkillPublic

setup

Run initial NanoClaw setup. Use when user wants to install dependencies, authenticate messaging channels, register their main channel, or start the background services. Triggers on "setup", "install", "configure nanoclaw", or first-time setup requests.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

82%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 highly actionable, well-sequenced setup runbook with executable commands, explicit status-block parsing, and strong verification/feedback loops. Its few weaknesses are a broken cross-reference ('continue to 4b' in the Docker branch), some duplicated credential-path options, and inline troubleshooting content that could be offloaded to a reference file.

Suggestions

Fix the 3a-docker branch pointer: 'DOCKER=running → continue to 4b' should read 'continue to 3c', since 4b is the Apple Container credential path and the Docker flow proceeds to build and test in 3c.

Deduplicate the credential section: state the Dashboard-vs-CLI AskUserQuestion once with a VALUE placeholder instead of repeating near-identical option blocks for both the subscription and API-key paths.

Move the Troubleshooting section into a reference file (e.g. references/troubleshooting.md) and ensure diagnostics.md ships in the bundle so the step-9 reference resolves.

Dimension	Reasoning	Score
Conciseness	The body is dense, imperative, and free of explanations of concepts Claude already knows, but includes some avoidable duplication: the Dashboard/CLI AskUserQuestion options are repeated nearly verbatim in both the subscription and API-key paths, and the Troubleshooting section partially re-covers error handling already specified in steps 7 and 8.	4 / 5
Actionability	Commands are copy-paste ready throughout — 'bash setup.sh', 'npx tsx setup/index.ts --step <name>', 'curl -fsSL onecli.sh/install \| sh', the PATH-persistence grep/echo blocks, the setfacl fixes, and the systemd heredoc — with branching keyed to concrete parsed status fields (NODE_OK, DOCKER, BUILD_OK, SERVICE_LOADED).	5 / 5
Workflow Clarity	Steps 0-9 are clearly sequenced with explicit validation checkpoints and feedback loops (step 8 Verify with per-failure remediation, 'onecli secrets list' re-verification, 'git remote -v' checks), but the 3a-docker branch says 'DOCKER=running → continue to 4b' — 4b is the Apple Container credential path, so this pointer is wrong (should be 3c) and could derail the flow.	4 / 5
Progressive Disclosure	Good structure with numbered sections and sound offloading of channel-specific and conversion logic to sibling skills, but it is a long single file whose inline Troubleshooting section could live in a reference, and its one file reference (.claude/skills/setup/diagnostics.md) is not part of the bundle and thus unverifiable.	4 / 5
	Total	17 / 20 Passed

Description

83%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 description that clearly and explicitly states both what the skill does and when to use it, in third person, with concrete actions and natural trigger terms. Its only weaknesses are minor: a few capability gaps and generic 'setup'/'install' trigger words that could collide with other skills.

Dimension	Reasoning	Score
Specificity	Lists several specific actions ('install dependencies, authenticate messaging channels, register their main channel, or start the background services'), but omits capabilities the skill actually covers such as container runtime selection and credential/API-key setup — minor gaps rather than comprehensive coverage, so above the 1-2-action level but below the comprehensive anchor.	4 / 5
Completeness	Explicitly answers both what ('Run initial NanoClaw setup' plus the enumerated actions) and when ('Use when user wants to...' and 'Triggers on...' with concrete trigger phrases), matching the top anchor exactly.	5 / 5
Trigger Term Quality	Natural trigger terms users would actually say are present ('setup', 'install', 'configure nanoclaw', 'first-time setup requests'), but common synonyms like 'get started', 'initialize', or 'onboard' are missing, so coverage is good but not comprehensive.	4 / 5
Distinctiveness Conflict Risk	'NanoClaw' and 'configure nanoclaw' carve a clear niche with distinct triggers, but the bare generic terms 'setup' and 'install' could overlap with other projects' setup/install skills, leaving minor conflict risk.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: jbaruch/nanoclaw-telegram
Path: .claude/skills/setup/SKILL.md
Revision: bc4f114

Reviewed: 7 hours ago

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.

setup

Table of Contents

Is this your skill?