CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

71

Quality

88%

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

87%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and token-efficient, with a clean structure of Key Files plus per-pattern question/implementation pairs. The gap is workflow validation — destructive and deployment steps lack explicit verify checkpoints, which caps workflow clarity.

Suggestions

Add an explicit verification step after rebuild/restart (e.g., check the service is running, confirm the new channel replies) so deployment and DB changes have a feedback loop.

Insert a "verify" checkpoint in the channel-install pattern between `/add-telegram` build and `/manage-channels` wiring so a failed build is caught before wiring.

DimensionReasoningScore

Conciseness

Lean prose throughout — the Key Files table and Common Customization Patterns deliver dense, scannable guidance with no padding or explanation of concepts Claude already knows.

3 / 3

Actionability

Concrete, copy-pasteable commands throughout: `ncl messaging-groups create`, `ncl wirings update --id <wiring-id> ...`, `pnpm exec tsx scripts/q.ts <db> "<sql>"`, and a full build/restart shell block.

3 / 3

Workflow Clarity

The five-step Workflow is clearly sequenced and each pattern pairs "Questions to ask" with "Implementation", but there are no validation/verification checkpoints — the rebuild-and-restart block and DB/migration changes have no explicit "verify it worked" step, capping clarity at 2 for these batch/deployment operations.

2 / 3

Progressive Disclosure

No bundle files exist and none are needed; the skill is a well-organized single-file overview with a Key Files table, pattern sections, and pointers to dedicated skills and one external doc (`docs/isolation-model.md`), all one level deep.

3 / 3

Total

11

/

12

Passed

Description

88%Weight 40%Scale 1-3

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 strong: concrete, third-person, with explicit trigger guidance and natural keywords. Its main weakness is a catch-all "any other customizations" clause that blurs the boundary with the dedicated add-* skills it references.

Suggestions

Narrow the catch-all "or make any other customizations" to reduce overlap with the dedicated /add-<channel> and /add-<service>-tool skills it should defer to.

Consider signaling that dedicated add-* skills exist for common cases, so this skill is clearly the fallback for custom core/router work.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "add channels (Telegram, Slack, email input), change triggers, add integrations, modify the router" — naming specific surfaces rather than abstract capability language.

3 / 3

Completeness

Answers "what" ("Add new capabilities or modify NanoClaw behavior") and "when" via an explicit "Use when user wants to add channels..." clause with concrete triggers.

3 / 3

Trigger Term Quality

Covers natural user phrasings — "add channels", "Telegram, Slack, email input", "change triggers", "add integrations", "modify the router" — the words a user would actually say when requesting a customization.

3 / 3

Distinctiveness Conflict Risk

The trigger list is broad — "or make any other customizations" — so it could overlap with the dedicated /add-* skills it itself enumerates, risking selection for tasks those skills better cover.

2 / 3

Total

11

/

12

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

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
nanocoai/nanoclaw
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.