/ase-meta-diff

name: ase-meta-diff
argument-hint: "[--help|-h] [--coherence|-c] [--risk|-r] [--blast|-b]"
description: >
    Summarize the currently staged Git changes as a human-readable,
    intent-grouped narrative. Use when the user wants a concise and
    brief report of what changed and why. Optionally can check the diff
    for intent coherence and show a risk and blast radius report.
user-invocable: true
disable-model-invocation: false
effort: high
allowed-tools:
    - "Bash(git diff *)"
    - "Bash(git grep *)"
    - "Bash(git ls-files *)"
    - "Bash(grep *)"
    - "Agent"

@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md

<purpose name="ase-meta-diff"> Summarize Diff </purpose>

<expand name="getopt" arg1="ase-meta-diff" arg2="--coherence|-c --risk|-r --blast|-b"> $ARGUMENTS </expand>

<objective> Summarize the currently staged Git changes into a *concise*, *human-readable* narrative of what changed and why, *grouped by intent* rather than by file. Optionally *reconstruct the change's single intended purpose* and *flag hunks that do not serve it*. Optionally *score* the diff against a *coupling-criticality-coverage-reversibility* rubric and emit a *graded risk report* with *mitigations*. Optionally render a *blast-radius map*. </objective>

Procedure ---------

<flow>

1. <step id="STEP 1: Determine Change Set">

1. Determine the *diff details* by running the corresponding command (taken exactly as given) and capturing the full diff output into <diff/> for the subsequent analysis:

`git diff --cached HEAD`

2. Determine the *diff statistics* by running the corresponding command (taken exactly as given) and capturing the full stat output into <stat/> for the subsequent analysis:

`git diff --cached --numstat HEAD`

</step>

2. <step id="STEP 2: Summarize By Intent">

1. <if condition="<diff/> is empty"> Only output the following <template/> and then *STOP* immediately:

<template> ⧉ **ASE**: ✪ skill: **ase-meta-diff**, ▶ status: **no changes to summarize** </template> </if>

2. Analyze the <diff/> and <stat/> and synthesize a *concise* narrative of WHAT changed and WHY, *grouped by intent* rather than by file. Honor the following intents:

• `FEATURE`: new functionality or configuration
• `IMPROVEMENT`: improved functionality or configuration
• `BUGFIX`: corrected functionality or configuration
• `UPDATE`: updated functionality or configuration
• `CLEANUP`: cleaned up functionality or configuration
• `REFACTOR`: refactored functionality or configuration

3. <if condition="<diff/> is NOT empty"> 1. First, output the following header <template/>:

<template>

<ase-tpl-bullet-normal/> **CHANGE INTENT REPORT**:

</template>

2. Render a *three-column table* with one row per discovered *intent group* present in the <diff/>. Output the following table header <template/>:

<template> | Intent | Changes (LoC) | Files &amp; Description | | ------ | ------------- | ----------------------- | </template>

3. For each discovered *intent group*, emit the following row <template/>, where <intent/> is the intent label, <changes/> is the total number of lines changed per intent group in format `+N/-M`, <files/> is the list of affected file references, and <description/> is a *brief* one-to-two-sentence narrative of what changed and why:

<template> | **<intent/>** | <changes/> | <files/>: <description/> | </template>

In the <files/> part of the second column, markup all file references as code (with backticks), prepend them with `▢ `, append ` [+N/-M]` (based on the information in <stat/>) to them, and separate them with `, ` (a comma and space). Do *not* repeat file references in the <description/>.

Keep the overall report *concise* and *brief*. Try to keep the number of intent groups (table rows) in the range of 1-10. Do *not* output any further explanation. </if>

4. <if condition=" <ase-project-boxing/> is equal `black` and (<getopt-option-coherence/> is equal `true` or <getopt-option-risk/> is equal `true` or <getopt-option-blast/> is equal `true`) "> The project source artifacts are classified as a *black box*, so the user does *not* want the staged changes scrutinized or their coherence, risk, and blast-radius findings surfaced. The requested scrutiny of STEP 3 through STEP 5 is therefore suppressed: only output the following <template/> and then *SKIP* the remaining steps STEP 3 through STEP 5:

<template> <ase-tpl-bullet-normal/> **DIFF SCRUTINY**: *suppressed* (`project.boxing` is `black`) </template> </if>

</step>

3. <step id="STEP 3: Assess Intent Coherence" condition="<getopt-option-coherence/> is equal `true` and <diff/> is NOT empty and <ase-project-boxing/> is not equal `black`">

1. From the *same* captured <diff/> and <stat/>, *reconstruct the single intended change* as a thesis - the one logical, coherent purpose the diff *as a whole* is trying to accomplish.

If the <diff/> genuinely spans *several* unrelated purposes, pick the *dominant* one as the thesis (the residue will surface as flagged hunks below).

Multiple intents discovered in STEP 2 are a strong indicator of incoherence. In this case, be very sceptica