CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-signal

Add Signal channel integration via signal-cli device-link. Native adapter — no Chat SDK bridge.

Quality

79%

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 ./.claude/skills/add-signal/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

An exceptionally actionable, well-validated skill body — copy-paste commands at every step, explicit sequencing, and strong feedback loops. Its weaknesses are monolithic structure (large Alternatives and Troubleshooting sections inlined where reference files should sit) and duplicated troubleshooting content that costs tokens without adding information.

Suggestions

Move 'Alternatives' (dedicated-number registration) and 'Troubleshooting' into one-level-deep reference files (e.g. references/alternatives.md, references/troubleshooting.md) and signal them from the body, keeping the core apply/link/wire flow lean.

De-duplicate the captcha-token and SMS-before-voice instructions, which appear almost verbatim in both 'Alternatives' and 'Troubleshooting' — state them once and cross-reference.

Consolidate the not_member access-granting explanation, currently given in both the 'Grant user access' wiring subsection and the 'Messages dropped with not_member' troubleshooting entry.

DimensionReasoningScore

Conciseness

The body is dense with commands and specifics and assumes Claude's competence (no explanation of what Signal or JSON-RPC is), but there is real duplication: the captcha/voice-verification instructions appear nearly verbatim in both 'Alternatives' and 'Troubleshooting', the not_member gating is explained in both 'Wiring' and 'Troubleshooting', and the QR-expiry note is stated twice. That trimmable redundancy fits anchor 4 (minor instances that could be trimmed) rather than 5; not 3 because the overwhelming majority of tokens are executable instructions, not explanation.

4 / 5

Actionability

Nearly every step is a copy-paste-ready command — install check ('command -v signal-cli ... || bash setup/install-signal-cli.sh'), pinned deps ('qrcode@1.5.4'), build/test commands, the device-link invocation, concrete SQL queries, and exact ncl commands with placeholders clearly marked. The guidance is fully executable and covers the common cases, matching anchor 5.

5 / 5

Workflow Clarity

The process is explicitly sequenced (Apply steps 1-5 → link account → persist → restart → wiring) with validation checkpoints and feedback loops throughout: a pre-check for signal-cli presence with 're-run step 1 if this fails', build guarding the typed API consumption, a registration test that 'goes red if the import line is deleted or drifts', and a structured troubleshooting section keyed to exact log messages. This matches anchor 5's explicit-validation and error-recovery pattern.

5 / 5

Progressive Disclosure

The file is well-sectioned with headers, but it is a ~330-line monolith with no bundle files: the 'Alternatives' (dedicated-number registration, ~60 lines), 'Troubleshooting' (~50 lines), and 'Channel Info' blocks are self-contained material that belongs in one-level-deep reference files, and no references exist to signal navigation. This fits anchor 3 (content that should be separate is inline) better than 4 (most content appropriately placed), since the main flow is intermixed with two large optional sections inline.

3 / 5

Total

17

/

20

Passed

Description

65%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 specific, distinctive description with good natural trigger terms, but it omits any 'Use when...' trigger guidance and enumerates only one concrete action. Adding an explicit trigger clause would lift completeness and make the description fully well-formed.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user wants to add Signal, link a Signal account, or set up Signal messaging for the assistant.'

Name one or two more concrete capabilities (e.g. sends/receives DMs and group messages as the linked number) to broaden capability coverage beyond the single 'add integration' action.

Include common synonyms such as 'messenger' or 'link a device' so natural phrasing variations still match.

DimensionReasoningScore

Specificity

The description names the domain and a concrete mechanism — "Add Signal channel integration via signal-cli device-link. Native adapter — no Chat SDK bridge" — but lists only the single add-integration action rather than several specific capabilities. It matches anchor 3 (domain and 1-2 concrete actions, not comprehensive); not 4 because no set of specific actions is enumerated, and not 2 because 'signal-cli device-link' and 'native adapter' are concrete, not generic.

3 / 5

Completeness

It clearly answers 'what' (add a Signal channel via signal-cli device-link as a native adapter) but contains no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the rubric guideline. Not 2 because the 'what' is explicit and specific, not vague.

3 / 5

Trigger Term Quality

"Signal", "signal-cli", "device-link", and "channel integration" are the natural terms a user would say when asking to add Signal; the key platform term appears twice. Not 5 because common variations like 'messenger', 'chat', 'link device', or 'set up Signal' are absent; not 3 because the primary trigger terms are present and natural rather than merely 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

"Signal channel integration via signal-cli device-link" carves out a clear niche with distinct triggers — no other plausible skill would claim these terms, and the explicit 'no Chat SDK bridge' boundary further separates it from generic chat-integration skills. Minimal conflict risk.

5 / 5

Total

15

/

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: 2 missing

Warning

Total

15

/

16

Passed

Repository

nanocoai/nanoclaw

Path

.claude/skills/add-signal/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.