BC cross-branch-audit
A universal cross-branch migration audit tool. When users need to migrate a module or specific feature from one branch to another, use this skill for pre-migration audit. Supports three input modes: (1) Module Path Mode — analyzes all commits under a specified directory; (2) Feature Mode — locates feature-related commits via keywords/commit lists/time range + author; (3) Hybrid Mode — module path + feature keywords combined. It automatically identifies commits involving external files, determines dependency types (strong/weak/resource/transitive), evaluates four-level conflict risk (🟢🟡🔴⚫), and generates an interactive HTML audit report with a critical-risk alert panel. Also supports incremental audit during migration (quick diagnosis of compilation errors) and provides a post-cherry-pick checklist. Applicable to projects of any language and framework. Trigger words: cross-branch audit, module migration analysis, commit dependency analysis, migration audit, cross-branch migration, module migration, branch migration, feature migration, cherry-pick analysis, feature audit, migration compilation error, migration conflict analysis, 跨分支审计, 模块迁移分析, commit依赖分析, 迁移审计, 跨分支迁移, 模块迁移, 分支迁移, 功能迁移, cherry-pick分析, 功能审计, 迁移编译错误, 迁移冲突分析.
As a process C 63/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, progress reporting
How to improve
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1242 chars, limit 1024 - warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: A universal cross-branch migration audit tool. When users need to … ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
body-longSKILL.md body ≈ 6586 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 63/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 6586 tokens
- 100Steps. 166 steps
- 100Failures and branches. 8 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (3 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1242: 120–800 characters recommended
- -220 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Structure: 37 headings
- +3Step-by-step instructions: 166 items
- +3Output format is stated explicitly
- +4Has examples (15 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 37.