Closed
Conversation
Add CLIO (Command Line Intelligence Orchestrator) detection and improve detection patterns for diverse codebases. agent-configs.mjs: - Add .clio and .clio/instructions.md to TOOL_SIGNALS - Add 5 CLIO-specific checks (dir, instructions, ltm, memory, sessions) grounding-docs.mjs: - Add docs/DEVELOPER_GUIDE.md and variants to conventions-doc paths testing.mjs: - Add Perl test directory 't/' to test-dir paths - Add Perl test configs (t/test.pl, tests/test.pl) to test-config ai-deps.mjs: - Recognize self-contained AI tools (projects that ARE AI tools) - CLIO with lib/CLIO/ detected as 'native-ai-tool' Testing: - All 447 tests pass - CLIO-dist score improved: 5.0 -> 5.7/10 - AI Deps: 0% -> 100% (native-ai-tool detected) - Grounding Docs: 44% -> 75% (DEVELOPER_GUIDE.md detected)
Add --tools flag to show per-tool readiness breakdown, scoring each AI tool based only on checks relevant to that tool. New files: - src/tool-profiles.mjs: Define per-tool requirements - required: checks that must pass - valuable: checks that improve experience - alternatives: check pairs where either satisfies - notApplicable: checks excluded from tool's score Supported tools: - CLIO (Perl AI assistant) - Cursor - Claude Code - Windsurf - GitHub Copilot Modified files: - src/scorer.mjs: Add scoreForTool(), scoreAllTools() - src/reporter.mjs: Add reportTools(), reportToolsInteractive() - bin/cli.mjs: Add --tools/-t flag Usage: $ check-ai --tools # Show per-tool breakdown $ check-ai --json --tools # JSON output with tool scores Example output: Per-Tool Readiness CLIO ████████████████ 100% (20/20) Cursor ████████████░░░░ 76% (13/17) Claude Code ███████████░░░░░ 68% (13/19) Testing: - All 447 tests pass - CLIO-dist scores 100% for CLIO tool
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
1 participant
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.
Just an idea, it shows scoring by tool in addition to the general score:
Add --tools flag to show per-tool readiness breakdown, scoring each
AI tool based only on checks relevant to that tool.
New files:
Supported tools:
Modified files:
Usage:
$ check-ai --tools # Show per-tool breakdown
$ check-ai --json --tools # JSON output with tool scores
Example output:
Per-Tool Readiness
CLIO ████████████████ 100% (20/20)
Cursor ████████████░░░░ 76% (13/17)
Claude Code ███████████░░░░░ 68% (13/19)
Testing: