Index of every page on this site: llms.txt
All skills
egonex-ai avatar

/understand-diff

@bb70fdb
by EgonexAIegonex-ai/understand-anything93k stars
7,959
Run it yourself

Use when you need to analyze git diffs or pull requests to understand what changed, affected components, and risks

Requires /understand
Use this Skill: https://skilld.dev/gh/egonex-ai/understand-anything/understand-diff

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈33 tokens for metadata: the name and description. ≈1.4k when used: this file.

Description uses 1.7% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈132 characters, or 1.7%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

/understand-diff

Analyze the current code changes against the knowledge graph in the project's data directory (.ua/knowledge-graph.json, or the legacy .understand-anything/knowledge-graph.json when that directory is present).

Graph Structure Reference

The knowledge graph JSON has this structure:

  • project — {name, description, languages, frameworks, analyzedAt, gitCommitHash}
  • nodes[] — each has {id, type, name, filePath?, summary, tags[], complexity, languageNotes?}
    • Code node types: file, function, class, module, concept
    • Non-code node types: config, document, service, table, endpoint, pipeline, schema, resource
    • Domain/knowledge node types: domain, flow, step, article, entity, topic, claim, source
    • IDs use the node type as prefix, e.g. file:path, function:path:name, config:path, article:path
  • edges[] — each has {source, target, type, direction, weight}
    • Key types: imports, contains, calls, depends_on, configures, documents, deploys, triggers, contains_flow, flow_step, related, cites
  • layers[] — each has {id, name, description, nodeIds[]}
  • tour[] — each has {order, title, description, nodeIds[]}

How to Read Efficiently

  1. Use Grep to search within the JSON for relevant entries BEFORE reading the full file
  2. Only read sections you need — don't dump the entire graph into context
  3. Node names and summaries are the most useful fields for understanding
  4. Edges tell you how components connect — follow imports and calls for dependency chains

Instructions

  1. Resolve the data directory $UA_DIR. Run UA_DIR=$([ -d .understand-anything ] && echo .understand-anything || echo .ua) — this is the legacy .understand-anything/ when it already exists, otherwise the new .ua/. Check that $UA_DIR/knowledge-graph.json exists. If not, tell the user to run /understand first.

  2. Get the changed files list (do NOT read the graph yet):

    • If on a branch with uncommitted changes: git diff --name-only
    • If on a feature branch: git diff main...HEAD --name-only (or the base branch)
    • If the user specifies a PR number: get the diff from that PR
  3. Read project metadata and check graph freshness — use Grep or Read with a line limit to extract the "project" section, including gitCommitHash as GRAPH_COMMIT_RAW, then:

    • Resolve it as a commit before using it in any Git diff. From the project root, compare the resolved commit with git rev-parse HEAD and inspect project-scoped committed and working-tree changes:
      GRAPH_COMMIT=$(git rev-parse --verify --end-of-options "${GRAPH_COMMIT_RAW}^{commit}" 2>/dev/null)
      git rev-parse HEAD
      git diff --name-only "$GRAPH_COMMIT" HEAD -- .
      git diff --cached --name-only -- .
      git diff --name-only -- .
      git ls-files --others --exclude-standard -- .
    • The -- . pathspec is required: commits that only touch a sibling monorepo project must not make this graph stale. A hash mismatch alone is not stale when the project diff is empty.
    • Ignore the selected data directory (.ua/ or legacy .understand-anything/) in every command's output because it contains generated graph artifacts, not project source drift.
    • If the committed diff or any working-tree command reports project files, warn before impact analysis that the graph may omit those changes. Suggest: Run /understand to refresh the graph.
    • Run the commit diff only when GRAPH_COMMIT_RAW resolves successfully. If the graph commit or Git metadata is missing, invalid, or unavailable, give a brief best-effort warning and continue instead of blocking.
  4. Find nodes for changed files — for each changed file path, use Grep to search the knowledge graph for:

    • Nodes with matching "filePath" values (e.g., grep "changed/file/path")
    • This finds file-level nodes (including non-code types) AND function/class nodes defined in those files
    • Note the id values of all matched nodes
  5. Find connected edges (1-hop) — for each matched node ID, Grep for that ID in the edges to find:

    • What imports or depends on the changed nodes (upstream callers)
    • What the changed nodes import or call (downstream dependencies)
    • These are the "affected components" — things that might break or need updating
  6. Identify affected layers — Grep for the matched node IDs in the "layers" section to determine which architectural layers are touched.

  7. Provide structured analysis:

    • Changed Components: What was directly modified (with summaries from matched nodes)
    • Affected Components: What might be impacted (from 1-hop edges)
    • Affected Layers: Which architectural layers are touched and cross-layer concerns
    • Risk Assessment: Based on node complexity values, number of cross-layer edges, and blast radius (number of affected components)
    • Suggest what to review carefully and any potential issues
  8. Write diff overlay for dashboard — after producing the analysis, write the diff data to $UA_DIR/diff-overlay.json so the dashboard can visualize changed and affected components. The file contains:

    {
      "version": "1.0.0",
      "baseBranch": "<the base branch used>",
      "generatedAt": "<ISO timestamp>",
      "changedFiles": ["<list of changed file paths>"],
      "changedNodeIds": ["<node IDs from step 4>"],
      "affectedNodeIds": ["<node IDs from step 5, excluding changedNodeIds>"]
    }

    After writing, tell the user they can run /understand-anything:understand-dashboard to see the diff overlay visually.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts4mo3 checks · Risk SAFE
  • Gen Agent Trust Hub4mo

    The skill analyzes git changes using a local knowledge graph file and shell commands like grep. While standard for development workflows, it presents a surface for indirect prompt injection and command injection if repository file names or metadata are maliciously crafted.

  • Socket4mo

    No alerts

  • Snyk4mo

    Risk: LOW · No issues

Signed by skilld at bb70fdb. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 4 months ago

README badge

README badge for egonex-ai/understand-anything/understand-diff