CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

nanoclaw-repl

Operate and extend NanoClaw v2, ECC's zero-dependency session-aware REPL built on claude -p.

Quality

67%

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 ./skills/nanoclaw-repl/SKILL.md

The canonical home for this skill is nanoclaw-repl in affaan-m/ECC

SKILL.md
Quality
Evals
Security

Quality

Content

68%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.

The body is an exemplar of token efficiency — terse, well-sectioned, and free of padding — but it is thin on execution detail: it never shows how to run or extend claw.js, and the operating guidance lacks validation checkpoints. A short run/extend example would lift actionability and workflow clarity without hurting conciseness.

Suggestions

Add a minimal executable run command (e.g. 'Launch: node scripts/claw.js' or equivalent) and a pointer to where command handlers live, so 'extending' is actionable rather than descriptive.

Add explicit validation checkpoints around the risky guidance steps, e.g. 'After /branch, verify the new session file exists before continuing' and 'After /compact, confirm recent context is preserved.'

Either ship scripts/claw.js in the bundle or state where it lives, since the body's central instruction ('running or extending scripts/claw.js') currently points to a file that is not present.

DimensionReasoningScore

Conciseness

The ~25-line body is lean and efficient with zero padding — every line ('persistent markdown-backed sessions', 'keep zero external runtime dependencies') adds information Claude would not infer. This matches anchor 5; there is no over-explanation to trim, so it is not 4.

5 / 5

Actionability

Concrete guidance exists (specific slash commands '/model', '/branch', '/compact' and explicit rules 'keep zero external runtime dependencies'), but key execution details are missing — no command to run claw.js, no location/structure of command handlers to extend. This matches anchor 3 ('some concrete guidance but incomplete... missing key details'), not 4, because the core run/extend instructions are absent.

3 / 5

Workflow Clarity

The Operating Guidance section lists a real sequence ('Branch before high-risk changes', 'Compact after major milestones', 'Export before sharing or archival'), but validation checkpoints are absent or only implicit. This matches anchor 3 ('steps listed but validation gaps'); not 4 because there are no explicit checkpoints for the risky operations (branching, compaction).

3 / 5

Progressive Disclosure

The under-50-line body is well organized into Capabilities, Operating Guidance, and Extension Rules, and needs no external reference files. It is not 5 because the body directs the reader to 'scripts/claw.js' which is not present in the bundle (no references/, scripts/, or assets/ directories), a minor organization gap matching anchor 4.

4 / 5

Total

15

/

20

Passed

Description

52%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.

The description is concise and highly distinctive thanks to the named tool, but it relies on two generic verbs ('Operate and extend') and completely lacks trigger guidance. Adding a 'Use when...' clause and one or two concrete capabilities would raise specificity, trigger quality, and completeness together.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when the user mentions NanoClaw, wants to run or resume a claw.js session, or asks to add commands/handlers to the REPL.'

Replace the generic 'Operate and extend' with concrete capabilities, e.g. 'Run persistent markdown-backed sessions, switch models, branch sessions, and compact history' — mirroring the command list already in the body.

Include natural trigger terms and synonyms users would say (e.g. 'REPL', 'session', 'claude -p wrapper', '/branch', '/compact') to improve trigger term coverage.

DimensionReasoningScore

Specificity

The domain is named with concrete technical attributes ('zero-dependency session-aware REPL built on claude -p'), but the only actions offered are the generic verbs 'Operate and extend' — no concrete capabilities are listed. This matches anchor 2 ('names the domain but actions are minimal or generic'); it falls short of anchor 3 because there is no concrete action equivalent to 'extracts content'.

2 / 5

Completeness

There is a clear 'what' (operate and extend a specific named REPL), but there is no 'when' guidance at all — the judging guidelines explicitly cap completeness at 3 for a missing 'Use when...' clause. Not 2 because the 'what' is concrete rather than vague.

3 / 5

Trigger Term Quality

'NanoClaw', 'REPL', and 'claude -p' are relevant keywords and the product name is the natural trigger, but there are no synonyms, variations, or usage phrases. This matches anchor 3 ('some relevant keywords but missing common variations'), not 4, since coverage rests entirely on the domain name.

3 / 5

Distinctiveness Conflict Risk

'NanoClaw v2, ECC's...' names a specific niche tool with distinct triggers, so it is clearly distinguishable from any other skill and unlikely to fire for the wrong one. Not 4 because no overlap risk with related skills is identifiable.

5 / 5

Total

13

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository

valeriibeck-star/claude-skills

Path

skills/nanoclaw-repl/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.