Semantic Slicing

Community

vincentkoc

semantic-slicing

Build local semantic review slices by combining clawpatch feature maps, deepsec threat candidates, visual review maps, and optional gitcrawl/discrawl evidence for repos such as openclaw/openclaw.

Overview

Publisher	vincentkoc
Repository	`dotskills`
Skill name	`semantic-slicing`
Stars	112
Forks	9
Bundled files	7
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
7 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by vincentkoc on GitHub. Read the source before you install it.

Installation

Install the Semantic Slicing AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/vincentkoc/dotskills/tree/main/skills/semantic-slicing
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/vincentkoc/dotskills.git /tmp/dotskills
mkdir -p .claude/skills
cp -r /tmp/dotskills/skills/semantic-slicing .claude/skills/semantic-slicing

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Semantic Slicing in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Semantic Slicing on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Semantic Slicing is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Semantic Slicing

Purpose

Turn a large repo into reviewable semantic slices with evidence. Use code shape, threat candidates, issue clusters, and support chatter together so review budget lands on the right parts of the system.

Default stance: map locally first, rank second, spend agent/security-review budget last.

When to use

Setting up or running openclaw/clawpatch against a target repo.
Setting up or running vercel-labs/deepsec against a target repo.
Producing a local visual map of feature slices, risky files, ownership clusters, or review targets.
Cross-checking code slices against gitcrawl issue/PR data or discrawl Discord/support data.
Planning a focused security, regression, architecture, or maintainer-review pass for a large repo.

Workflow

Reuse suitable tool state. Create task-owned temporary storage only when a tool requires files.
Read target repo instructions before scanning. For OpenClaw, read root AGENTS.md; subtree guides matter when reviewing a slice.
Verify tool setup:
- clawpatch: clone/build openclaw/clawpatch, then run clawpatch init, clawpatch map, clawpatch status.
- deepsec: clone/build vercel-labs/deepsec, scaffold a scratch workspace, then run deepsec scan.
- gitcrawl: run gitcrawl doctor --json, then pull clusters/threads for related issue evidence.
- discrawl: run discrawl doctor --json and discrawl status --json; use search/digest only when support chatter is relevant.
Run deterministic maps before AI review:
- Clawpatch feature map for entrypoints/packages/config/test slices.
- Deepsec regex scan for candidate threat surfaces.
- Optional repo git overlay for CODEOWNERS routing, tracked files, code/test/doc shape, and recent churn.
- Optional gitcrawl/discrawl lookups for historical pain around the same files, components, or symptoms.
Run scripts/semantic-map.mjs to merge the evidence into JSON on stdout.
- Select bounded fields for agent inspection. Do not save intermediate output by default.
- Use --out <path> only for a requested deliverable or required evidence. It retains HTML and JSON by default.
- Use --format html|json|both to select output. A single format writes only the exact --out path.
- Sparse mode is on by default and omits dotfile/config trees, docs, changelog files, and mobile app trees so core review stays focused.
- Use --no-sparse or --sparse false for the full repo; use --sparse-exclude <csv> and --sparse-include <csv> to tune the filter.
When a visual board is requested, review it in product order:
- review lanes first: semantic shape, ownership routing, development pressure, security pressure, issue pressure, support pressure,
- focus controls second: lens and system filters that narrow the matrix without duplicating rows,
- overall lens matrix third: the single slice-row table with comparable bars for semantic, ownership, development, security, issue, and support lenses,
- agent handoff packet fourth: compact JSON for follow-up agents,
- evidence tables last: raw-ish overlays for audit, not the primary reading path.
Choose a cost size before running AI stages:
- low: deterministic maps only; no deepsec process or real clawpatch review.
- medium: one to three explicit files/features with high-risk slugs, batch size 1, concurrency 1, and a turn cap.
- high: broader AI processing or multiple feature reviews; requires an explicit budget/time decision.
Run AI only at the chosen size:
- clawpatch review --feature <id> or a small --limit.
- deepsec process --files <csv> or tightly scoped --filter plus --only-slugs.
Report retained paths, run IDs, counts, cost size, exclusions, and skipped expensive stages in chat. Remove only task-owned disposable scratch when no longer needed or in use. Preserve named deliverables and recovery evidence.

Flow

Inputs

target_repo: local checkout path and/or GitHub owner/repo.
scratch_root: optional task-owned temporary directory for tools that require physical state.
out: optional requested deliverable or required evidence path. Omit it for stdout.
format: html, json, or both. Default: json without out, otherwise both.
clawpatch_repo: local clone of openclaw/clawpatch, optional if clawpatch is already on PATH.
deepsec_repo: local clone of vercel-labs/deepsec, optional if deepsec is already on PATH.
focus: optional path prefixes, issue numbers, slugs, components, or channels to prioritize.
sparse: optional map filter, default true; excludes dotfile/config, docs/changelog, and mobile app paths unless configured.
cost_size: low, medium, or high; default low.
budget_mode: map-only, targeted-ai, or full-ai; default follows cost_size.

Outputs

Tool setup status and blocker list.
Clawpatch feature counts and contamination checks.
Deepsec scan run ID, candidate counts, top slugs, and top files.
Optional repo overlays from --repo: CODEOWNERS routing, tracked files, code/test/doc shape, 90-day churn, and test-gap pressure.
Optional gitcrawl cluster/thread evidence and discrawl support evidence.
Machine-readable semantic map on stdout by default. Retained HTML and JSON only when requested.
Clean semantic buckets, ownership overlay, development overlay, security overlay, issue overlay, support overlay, and normalized queues.
Human review lanes, focus controls, agent handoff packet, and ranked next commands per lens with cost-size rationale.

Guardrails

Keep generated artifacts out of the target repo unless the user explicitly wants checked-in config.
Do not run full deepsec process or broad clawpatch review without an explicit high-cost decision; these can be expensive and noisy.
Treat local nested worktrees and dot-agent folders as contamination unless intentionally in scope: .claude/, .codex/, .agents/, .deepsec/, .semantic-slicing/.
If a tool maps contaminated paths, post-filter before ranking and call out the upstream limitation.
Never paste secrets from scan outputs. Scrub absolute personal paths before external PRs/comments.
For OpenClaw, use Testbox/Crabbox only when the task moves from mapping into validation.

References

Read references/workflow.md for concrete local setup and run commands.
Read references/slicing-taxonomy.md when choosing slice types or map layers.
Read references/openclaw-profile.md when the target is openclaw/openclaw.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Semantic Slicing AI skill do?

Build local semantic review slices by combining clawpatch feature maps, deepsec threat candidates, visual review maps, and optional gitcrawl/discrawl evidence for repos such as openclaw/openclaw.

Why use Semantic Slicing on TypingMind?

Because you install it once and use it with any model. Semantic Slicing is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Semantic Slicing in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vincentkoc/dotskills/tree/main/skills/semantic-slicing. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Semantic Slicing?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Semantic Slicing?

As many as you like. As long as a model supports skills, you can use Semantic Slicing with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Semantic Slicing AI skill free?

Yes. It is published on GitHub by vincentkoc under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Feishu Perm

openclaw

OrganizationPopular

Feishu collaborator and permission workflows. Activate when the user explicitly asks to inspect or change sharing, permissions, or collaborators.

Block Kit

Use proactively for structured or interactive Slack replies, and when asked to author or validate native Slack Block Kit JSON.

1password

Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.

Apple Reminders

List, add, edit, complete, or delete Apple Reminders and reminder lists via remindctl.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Semantic Slicing

Purpose

When to use

Workflow

Flow

Inputs

Outputs

Guardrails

References

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now