debug-cli

Use when users need to debug, modify, or extend the code-forge application's CLI commands, argument parsing, or CLI behavior. This includes adding new commands, fixing CLI bugs, updating command options, or troubleshooting CLI-related issues.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

70%Weight 40%Scale 1-3

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

The body is highly actionable with concrete, executable commands and a clear conceptual workflow, but it is verbose with heavy repetition across sections and lacks explicit validation checkpoints. Progressive disclosure is limited by keeping all material inline rather than linking to the bundle.

Suggestions

Consolidate the repeated guidance (always --help first, use -p, never commit, clone conversations) into a single 'Core Principles' block and reference it rather than restating in Workflow, Quick Reference, and Tips.

Add explicit validation checkpoints to the workflow — e.g. verify the build succeeds ('cargo build && ...') and confirm command output matches expectations before declaring a step complete.

Move the longer example sets (e.g. edge-case and prompt-optimization snippets) into the existing scripts/ reference or a dedicated file and link to it from the body to reduce inline bulk.

Dimension	Reasoning	Score
Conciseness	Mostly actionable but verbose — the same commands and tips repeat across 'Workflow', 'Common Testing Patterns', 'Integration', 'Quick Reference', and 'Tips' (e.g. 'Always --help first', 'Use -p for testing', 'Never commit' each restated 3+ times).	2 / 3
Actionability	Fully executable commands throughout — 'cargo build', './target/debug/forge --help', 'forge conversation dump --html <id>', 'cat ... \| jq ...' — copy-paste ready with concrete examples.	3 / 3
Workflow Clarity	Sequences are present and numbered, and the 'Reproduce Reported Bugs' checklist has a clear clone→build→test→iterate loop, but there is no validation checkpoint verifying a build succeeded or output matched expectations before proceeding, and the destructive/batch-adjacent 'clone' workflow lacks explicit verification feedback.	2 / 3
Progressive Disclosure	Well-organized into sections, but the body is monolithic — nearly all reference material is inline with only the scripts/README.md bundle present and never linked from the body; content that could be split (e.g. the reference examples) is kept inline.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, specific description that clearly states capabilities and an explicit trigger. It answers both 'what' and 'when' and is narrowly scoped to the code-forge CLI, minimizing conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'debug, modify, or extend the code-forge application's CLI commands, argument parsing, or CLI behavior' plus 'adding new commands, fixing CLI bugs, updating command options, or troubleshooting'.	3 / 3
Completeness	Explicitly answers what ('debug, modify, or extend the code-forge application's CLI commands, argument parsing, or CLI behavior') and when ('Use when users need to...'), with an explicit 'Use when' trigger clause.	3 / 3
Trigger Term Quality	Covers natural terms a user would say — 'debug', 'CLI commands', 'argument parsing', 'CLI behavior', 'adding new commands', 'fixing CLI bugs', 'command options', 'troubleshooting' — with strong variation coverage.	3 / 3
Distinctiveness Conflict Risk	Scoped narrowly to the code-forge application's CLI with distinct triggers; unlikely to fire for non-CLI or non-code-forge skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

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: tailcallhq/forgecode
Path: .forge/skills/debug-cli/SKILL.md
Commit: 1ca089a

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.