CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

init-first-agent

Walk the operator through wiring the first NanoClaw agent to a DM channel — resolve the operator's channel identity, select or create the agent, and trigger a welcome DM via the normal delivery path. Use after channel credentials are configured and the service is running.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 high-quality operational skill: every step is backed by an executable command, the workflow is well-sequenced with verification and a failure-diagnosis branch, and the troubleshooting section anticipates real failure modes with concrete fixes. The main improvement opportunity is structural — moving the channel-specific resolution matrix and pair-code details into a one-level-deep reference file would trim the main body further.

DimensionReasoningScore

Conciseness

The body is dense and nearly every token carries repo-specific knowledge Claude could not know (CLI flags, DB schemas, adapter policies); it does not explain general concepts. A few spots could still be tightened — e.g. the unknown_sender_policy two-level model explanation in Troubleshooting and the provider-selection paragraph in step 5 run slightly long. Not a 5 because a handful of sentences restate what the surrounding commands already show; not a 3 because there is no padding or taught material.

4 / 5

Actionability

Fully executable throughout: complete copy-paste commands with exact flags (`pnpm exec tsx scripts/q.ts data/v2.db "SELECT ..."`, `npx tsx scripts/init-first-agent.ts --channel ... --platform-id ...`, `ncl groups list --json`), explicit variable conventions (CHANNEL lowercase, PLATFORM_ID=${CHANNEL}:${USER_HANDLE}), and exact per-step user prompts. Placeholders are all defined earlier in the flow.

5 / 5

Workflow Clarity

Six numbered steps in a coherent sequence with prerequisites up front, an explicit validation step (step 6 asks the user to confirm receipt), and a diagnosis branch with concrete DB/log checks if the welcome DM does not arrive. Troubleshooting maps each failure mode to a fix, and idempotency is stated up front. The skill is non-destructive and idempotent, so the missing-validation cap does not apply.

5 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), so the skill is a self-contained single file with clear section headers (Prerequisites, steps 1–6, Troubleshooting) — well-organized and easy to navigate. It falls short of 5 only because at ~145 lines some channel-specific detail (the per-channel cold-DM resolution matrix and the pair-code path) would sit more appropriately in a one-level-deep reference file; it is not a 3 because what is inline is clearly sectioned and nothing is buried.

4 / 5

Total

18

/

20

Passed

Description

92%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: concrete, third-person, explicitly scoped, and paired with a clear 'Use when' precondition clause. The only minor gap is trigger-term breadth — adding channel names or common user phrasings would make it easier to match naturally.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions covering the full workflow — "resolve the operator's channel identity", "select or create the agent", and "trigger a welcome DM via the normal delivery path" — with no vague filler. Coverage is comprehensive for what the skill does; it does not merely name the domain.

5 / 5

Completeness

Both 'what' and 'when' are answered explicitly: the 'what' is the three concrete wiring actions, and the 'when' is the explicit clause "Use after channel credentials are configured and the service is running". Neither is vague, so the completeness cap for a missing trigger clause does not apply.

5 / 5

Trigger Term Quality

Good natural keywords users would say: "first NanoClaw agent", "DM channel", "welcome DM", "channel credentials". A few natural trigger terms are missing — no channel names (Discord, Slack, Telegram) or common phrasings like "set up" or "connect" that a user might use when asking for this.

4 / 5

Distinctiveness Conflict Risk

"wiring the first NanoClaw agent to a DM channel" carves out a clear niche with distinct triggers (NanoClaw, welcome DM, first agent); it is unlikely to fire for unrelated skills. The description stays in third person ("Walk the operator through"), so no voice penalty applies.

5 / 5

Total

19

/

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: 3 missing

Warning

Total

15

/

16

Passed

Repository

nanocoai/nanoclaw

Path

.claude/skills/init-first-agent/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.