CtrlK
BlogDocsLog inGet started
Tessl Logo

nanoclaw-repl

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

56

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/nanoclaw-repl/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The body is exceptionally concise and well-organized, but it stays at the level of description rather than instruction: slash commands and extension rules lack executable examples and the operating workflow lacks validation checkpoints.

Suggestions

Add a concrete minimal example of extending the REPL, such as a small command-handler snippet for scripts/claw.js, to make the Extension Rules actionable.

Provide brief usage syntax or one-line examples for the listed slash commands so users know how to invoke them.

Insert validation/verification checkpoints into the Operating Guidance (e.g., verify a branch before high-risk changes, confirm compaction preserved context) to lift workflow clarity above 2.

DimensionReasoningScore

Conciseness

The body is lean with no padding and no explanation of concepts Claude already knows; every line (capability bullets, operating guidance, extension rules) earns its place, matching the 'lean and efficient; every token earns its place' anchor.

3 / 3

Actionability

Concrete slash commands are named ("/model", "/branch", "/compact") but no usage syntax, runnable examples, or concrete extension code is given, and the Extension Rules are abstract directives ('keep command handlers deterministic and local'), fitting the 'some concrete guidance but incomplete; missing key details' anchor rather than fully executable guidance.

2 / 3

Workflow Clarity

The Operating Guidance is a numbered sequence (1-4) but has no validation or verification checkpoints, and because it covers high-risk actions ("Branch before high-risk changes"), the judging guidelines cap workflow clarity at 2 ('steps listed but validation gaps; checkpoints missing or implicit').

2 / 3

Progressive Disclosure

The skill is under 50 lines, single-file, and organized into clearly labeled sections (Capabilities, Operating Guidance, Extension Rules) with no nested references, so per the simple-skills scoring note it qualifies for the top anchor; the `scripts/claw.js` path is the operated tool rather than a deep skill reference.

3 / 3

Total

10

/

12

Passed

Description

57%

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 distinctive and domain-rich but lacks an explicit usage trigger and lists only two broad actions. Adding a 'Use when...' clause and more concrete capability verbs would raise completeness and specificity.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when running or extending the NanoClaw REPL or when the user mentions interactive Claude sessions, REPLs, or session branching.'

Replace the two generic verbs with several concrete capability actions (e.g., 'create persistent sessions, switch models, branch, search, compact, and export').

Soften technical jargon ("claude -p", "zero-dependency") or pair it with natural user-facing terms so trigger-term coverage reaches common variations.

DimensionReasoningScore

Specificity

"Operate and extend NanoClaw v2" names the domain ("session-aware REPL built on claude -p") and two actions (operate, extend), but does not list multiple concrete capabilities, matching the 'names domain and some actions, but not comprehensive' anchor rather than the multi-action score-3 example.

2 / 3

Completeness

The description clearly states what the skill does ("Operate and extend NanoClaw v2...") but lacks any "Use when..." clause or equivalent explicit trigger, so per the judging guidelines completeness is capped at 2 ('has what, but when is missing or only implied').

2 / 3

Trigger Term Quality

Terms like "REPL" and "session" are relevant, but "claude -p" and "zero-dependency" are technical jargon and common natural variations a user would say are missing, fitting the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

Naming a specific product ("NanoClaw v2, ECC's zero-dependency session-aware REPL") carves a clear niche that is unlikely to trigger for the wrong skill, matching the 'clear niche with distinct triggers' anchor.

3 / 3

Total

9

/

12

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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
affaan-m/ECC
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.