perf(icp-cli): reduce skill body by 33 lines for token efficiency#199
Merged
Conversation
Remove alternative installation methods (brew/shell script) and inline pitfall 4's verbose wrong-example block. Quality verified via skill-creator eval loop: 18/18 assertions pass, avg -212 tokens/run.
Skill Validation ReportValidating skill: /home/runner/work/icskills/icskills/skills/icp-cliStructure
Frontmatter
Markdown
Tokens
Content Analysis
References Content Analysis
Contamination Analysis
References Contamination Analysis
Result: passed Project Checks |
raymondk
approved these changes
May 31, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
npm install -g, and the alternatives added noise without valueResult: 405 → 372 lines (−8%), skill body 4,037 tokens (down from ~4,500).
Context
Found during a skill-creator testrun done as part of reviewing #198. The testrun ran 3 eval cases (full-stack Motoko+React,
createActormigration, Vite dev server) against the original and trimmed skill using the skill-creator eval loop.Eval results
Iteration-2 benchmark (trimmed vs original)
All 18 assertions pass on the trimmed skill. The one old-skill assertion failure (93% shown in benchmark) is a false positive —
CANISTER_ID_appeared in an explanatory "don't use this" sentence, not as an instruction.