CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

customize

Add new capabilities or modify NanoClaw behavior. Use when user wants to add channels (Telegram, Slack, email input), change triggers, add integrations, modify the router, or make any other customizations. This is an interactive skill that asks questions to understand what the user wants.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

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.

A strong, well-structured instruction skill: concrete commands, a useful key-files map, and per-pattern question lists make it highly actionable. The main gaps are minor — a redundant example section, elided command flags, and a verification step that tells rather than shows.

Suggestions

Cut or compress the 'Example Interaction' section — it duplicates the 'Adding a New Input Channel' pattern — and turn the vague 'Tell the user how to verify' step into a concrete validation checkpoint (e.g., a test message to send or an ncl command to confirm the wiring).

Spell out the full flag list for 'ncl groups config add-mcp-server' and 'ncl wirings update' instead of eliding with '...' so the commands are copy-paste ready.

Consider moving the 'Common Customization Patterns' detail into a references/ file, keeping SKILL.md as a lean overview with clearly signaled one-level-deep links.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence — a key-files table, concrete ncl commands, and no explanations of known concepts. Minor redundancy: the 'Example Interaction' section repeats the 'Adding a New Input Channel' pattern almost step-for-step, and 'Always tell the user.' pads without adding information.

4 / 5

Actionability

Mostly executable guidance: 'pnpm exec tsx scripts/q.ts <db> "<sql>"', 'ncl groups config add-mcp-server --id <group-id> --name <name> ...', and a concrete rebuild/restart bash block. Falls short of 5 because the ncl invocations elide flags with '...' and $(launchd_label) is not defined inline, leaving minor gaps.

4 / 5

Workflow Clarity

A clear five-step workflow (understand, prefer a dedicated skill, plan, implement, test guidance) plus per-pattern 'Questions to ask' and implementation steps. Verification exists only as a pointer ('Tell the user how to verify') rather than an explicit checkpoint with concrete validation commands, so it sits at 4 rather than 5.

4 / 5

Progressive Disclosure

No bundle files exist, and the single external reference ('See docs/isolation-model.md for the three isolation levels') is clearly signaled and one level deep. Sections are well organized with headers and a table, though the ~120-line body's Common Customization Patterns could arguably live in reference files.

4 / 5

Total

16

/

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 explicitly states what the skill does and when to use it, with concrete, natural trigger terms in third-person voice. It is not fully comprehensive (a vague catch-all clause and slight overlap with dedicated add-channel skills), but it comfortably clears every rubric floor.

DimensionReasoningScore

Specificity

Names the domain (NanoClaw) and several concrete actions: 'add channels (Telegram, Slack, email input), change triggers, add integrations, modify the router'. The catch-all 'or make any other customizations' leaves a minor coverage gap, so it does not reach the comprehensive level of 5.

4 / 5

Completeness

Explicitly answers both: 'what' ('Add new capabilities or modify NanoClaw behavior') and 'when' ('Use when user wants to add channels..., change triggers, add integrations, modify the router') with concrete trigger phrases. Voice is third-person throughout, so no pronoun penalty applies.

5 / 5

Trigger Term Quality

Good natural-term coverage — 'add channels', 'Telegram', 'Slack', 'email input', 'change triggers', 'add integrations' — phrases a user would actually say. A few natural synonyms ('customize', 'connect a channel') are missing, keeping it below 5.

4 / 5

Distinctiveness Conflict Risk

The 'NanoClaw' product name and specific trigger list give it a clear niche, but 'add channels (Telegram, Slack...)' and 'add integrations' overlap with the dedicated /add-<channel> and /add-<service>-tool skills in the same bundle, a minor conflict risk.

4 / 5

Total

17

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

nanocoai/nanoclaw

Path

.claude/skills/customize/SKILL.md

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.