CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

canton-network-repos

Canton Network, DAML, and Splice repository knowledge. Use when working with Canton participants, DAML smart contracts, Splice applications, LF version compatibility, or package ID mismatches. Triggers on Canton, DAML, Splice, decentralized-canton-sync, or LF version queries.

2.08x
Quality

76%

Does it follow best practices?

Impact

98%

2.08x

Average score across 3 eval scenarios

SecuritybySnyk

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./data/skills-md/0xbigboss/claude-code/canton-network-repos/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 highly actionable, well-structured reference with concrete commands, exact file paths, and useful troubleshooting entries. The main costs are redundancy — the same LF-2.2 conclusion restated in four sections — and date/version-stamped verification logs that will age poorly and would be better split into a reference file.

Suggestions

Merge the four sections that repeat the LF-2.2-available-in-SDK-3.4.9 conclusion ('Root Cause', 'Key insight', 'Building with LF 2.2', 'Fully Open-Source LF 2.2 Build') into one workflow section.

Move the LanguageVersion.scala excerpts, dated verification logs, and expected package ID hashes into a references/ file (e.g., versions.md), keeping SKILL.md as the navigable overview.

Resolve the inconsistent assembly targets ('community/app/assembly' vs 'canton-community-app/assembly') and note that the perl '**/daml.yaml' commands require bash globstar (shopt -s globstar).

DimensionReasoningScore

Conciseness

Most content is repo-specific fact Claude cannot know (file paths, version mappings, build commands), but the LF-2.2 conclusion is repeated across four sections ('Root Cause (Verified)', 'Key insight', 'Building with LF 2.2', 'Fully Open-Source LF 2.2 Build'), and dated verification logs ('Verified Results (2025-12-24)', snapshot hashes, May/Oct 2025 dates) are time-sensitive detail not quarantined in an old-patterns section. Mostly efficient but could be tightened, matching anchor 3.

3 / 5

Actionability

Concrete executable guidance throughout: 'sbt "community/app/assembly"', 'nix-shell -p daml-sdk --run "daml build -p daml/splice-amulet"', perl one-liners, and exact file edits with code blocks. Minor gaps keep it below anchor 5: the assembly target is inconsistent ('community/app/assembly' vs 'canton-community-app/assembly') and 'perl -pi -e ... **/daml.yaml' requires globstar to recurse.

4 / 5

Workflow Clarity

The LF-2.2 migration is a clear numbered 5-step sequence, the expected output hashes ('canton-builtin-admin-workflow-ping-3.4.9-fbeb863dab36da66d99...') act as verification targets, and the Troubleshooting section gives cause/check/fix recovery for the three common failures. It misses anchor 5 because no explicit post-build validation step (e.g., compare produced package IDs against the listed hashes) is embedded in the workflow itself.

4 / 5

Progressive Disclosure

No bundle files exist, and the single SKILL.md is well-sectioned (hierarchy, repository details, version mapping, build, troubleshooting, key files table) making navigation easy. Some deep reference material — LanguageVersion.scala source excerpts, dated verified-results logs, the enterprise/community feature table — reads like content that belongs in separate reference files, matching anchor 4 rather than 5.

4 / 5

Total

15

/

20

Passed

Description

73%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 with an explicit, concrete trigger list and a clearly delineated niche. Its main weakness is the generic 'what' ('repository knowledge') — replacing it with the specific capabilities offered (version mapping, package ID mismatch debugging, build instructions) would lift specificity and completeness to top level.

Suggestions

Replace the vague 'repository knowledge' with concrete capabilities, e.g., 'Maps Splice/Canton/DAML SDK versions to LF versions, debugs package ID mismatches and LF version errors, and gives build steps for community Canton and Splice artifacts.'

Add missing natural trigger terms users are likely to say, such as 'DAR', 'Canton Coin', 'package upgrade', or 'daml-lf', to the trigger list.

Mention the repository names users may paste verbatim (e.g., digital-asset/canton, decentralized-canton-sync) as triggers to catch error messages containing repo paths.

DimensionReasoningScore

Specificity

The description names the domain clearly ('Canton Network, DAML, and Splice repository knowledge') and cites concrete problem areas ('LF version compatibility, or package ID mismatches'), but the 'what' is the generic action 'knowledge' rather than listed concrete actions. It sits above anchor 2 (domain named but actions minimal) and below anchor 4 (several specific actions listed).

3 / 5

Completeness

Both 'what' ('Canton Network, DAML, and Splice repository knowledge') and 'when' ('Use when working with... Triggers on...') are present, with the when clause explicit and concrete. The what clause is vaguer than anchor 5's clearly enumerated capabilities, matching anchor 4 ('both what and when; when could be more explicit') inverted — here the what could be more explicit.

4 / 5

Trigger Term Quality

The explicit trigger list ('Triggers on Canton, DAML, Splice, decentralized-canton-sync, or LF version queries') plus 'Use when working with Canton participants, DAML smart contracts, Splice applications' gives good natural-term coverage. A few natural variants users might say (DAR, Canton Coin, daml-lf) are missing, so it falls just short of anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

A clear niche with distinct triggers: Canton, DAML, and Splice are unambiguous project names unlikely to collide with other skills, and the description enumerates them as literal trigger terms. Minimal conflict risk.

5 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

NeverSight/learn-skills.dev

Path

data/skills-md/0xbigboss/claude-code/canton-network-repos/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.