Crossframe Critical
sickn33/agentic-awesome-skills
Use only when the user explicitly names crossframe-critical for a Chinese structural critique dossier, article plan, or long-form critical essay.
Critically audit or explicitly trim an existing agent skill to its behavioral core, including narrowing over-broad trigger metadata.
MITAuto-check passed
Install Skill Cutter
$ npx skills add swyxio/skills --skill skill-cutter -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install swyxio/skills skill-cutter --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/swyxio/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skill-cutter .claude/skills/skill-cutter && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "skill-cutter" agent skill from https://github.com/swyxio/skills/tree/main/skill-cutter into .claude/skills/skill-cutter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-cutter", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/swyxio/skills/tree/main/skill-cutterType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add swyxio/skills --skill skill-cutter -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install swyxio/skills skill-cutter --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swyxio/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skill-cutter .agents/skills/skill-cutter && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "skill-cutter" agent skill from https://github.com/swyxio/skills/tree/main/skill-cutter into .agents/skills/skill-cutter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-cutter", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add swyxio/skills --skill skill-cutter -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install swyxio/skills skill-cutter --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swyxio/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skill-cutter .cursor/skills/skill-cutter && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "skill-cutter" agent skill from https://github.com/swyxio/skills/tree/main/skill-cutter into .cursor/skills/skill-cutter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-cutter", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/swyxio/skills.git --path skill-cutter--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add swyxio/skills --skill skill-cutter -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install swyxio/skills skill-cutter --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swyxio/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skill-cutter .gemini/skills/skill-cutter && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "skill-cutter" agent skill from https://github.com/swyxio/skills/tree/main/skill-cutter into .gemini/skills/skill-cutter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-cutter", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install swyxio/skills skill-cutterInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add swyxio/skills --skill skill-cutter -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/swyxio/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skill-cutter .github/skills/skill-cutter && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "skill-cutter" agent skill from https://github.com/swyxio/skills/tree/main/skill-cutter into .github/skills/skill-cutter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-cutter", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add swyxio/skills --skill skill-cutter -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install swyxio/skills skill-cutter --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swyxio/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skill-cutter .opencode/skills/skill-cutter && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "skill-cutter" agent skill from https://github.com/swyxio/skills/tree/main/skill-cutter into .opencode/skills/skill-cutter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-cutter", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
skill-cutter- GitHub stars
- 176
- Token cost
- ~1.5k tokens
- SKILL.md length
- 728 words
- Files
- 2
- Skills in repo
- 89
- Repo updated
- First seen
- Licence
- MIT
At a glance
Critically audit or explicitly trim an existing agent skill to its behavioral core, including narrowing over-broad trigger metadata.
- The user asks to cut
- SKILL.md covers Choose the mode, Find the behavioral core, Cut trigger aggression and Apply the cut, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Reduce the context cost
What it does
Skill Cutter is an agent skill from swyxio/skills. Critically audit or explicitly trim an existing agent skill to its behavioral core, including narrowing over-broad trigger metadata. Use when the user asks to cut, simplify, shorten, de-slop, or reduce the context cost or trigger aggressiveness of a SKILL.md or skill folder. Do not trigger merely because a skill is long or is being edited for another purpose.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
The repository describes itself as: Agent skills for Claude Code and other AI agents. The licence is MIT.
When your agent uses it
- The user asks to cut
- Reduce the context cost
- Trigger aggressiveness of a SKILL.md
- Merely because a skill is long
Example prompts
- “/skill-cutter”
What it can do on your machine
Read from SKILL.md and the folder at commit 038ef34. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Skill Cutter loads about 1.5k tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 728 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from swyxio/skills at commit 038ef34, republished under its MIT licence (© swyxio). 728 words, ~1,493 tokens.
Download SKILL.mdSave it as
.claude/skills/skill-cutter/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- skill-cutter
- description
- Critically audit or explicitly trim an existing agent skill to its behavioral core, including narrowing over-broad trigger metadata. Use when the user asks to cut, simplify, shorten, de-slop, or reduce the context cost or trigger aggressiveness of a SKILL.md or skill folder. Do not trigger merely because a skill is long or is being edited for another purpose.
Skill Cutter
Reduce context cost and accidental activation without weakening the behavior the skill exists to provide. Treat line count as evidence, not the objective.
Choose the mode
- Audit: When asked to review, critique, or identify cuts, inspect and report without editing.
- Cut: An explicit request to cut, trim, shorten, simplify, or de-slop the skill authorizes local edits within that skill. It does not authorize commit, push, publication, or changes to consumers outside the requested scope.
Find the behavioral core
Read the complete SKILL.md, its UI metadata, and only the directly relevant
resources. Identify the concrete tasks that should trigger it and the decisions
an otherwise capable agent would get wrong without it.
Classify material before cutting. Use acceptance force as well as content class so useful advice does not survive as accidental governance:
| Acceptance force | Treatment |
|---|---|
| Invariant | Keep explicit and narrow. |
| Action-required | Keep only for the named task type. |
| Risk-triggered gate | Name the triggering risk and proportional proof. |
| Recommendation | Label or phrase as non-blocking; condense when useful. |
| Opportunity | Move out of the critical path or delete. |
Then classify its content:
| Class | Default treatment |
|---|---|
| Non-obvious domain constraint or fragile required sequence | Keep |
| Useful optional expert recommendation | Condense and label as optional |
| Generic knowledge or ordinary engineering advice | Delete |
| Policy already enforced by system or repository instructions | Delete |
| Duplicate instruction or example | Keep the clearest instance |
| Project- or incident-specific policy in a generic skill | Move or delete |
| Stale, unverifiable, or overclaimed fact | Verify, qualify, or delete |
| Detail needed only for one variant | Move to a selectively loaded reference |
Report which class justified every material keep, move, or deletion. Do not hide subjective policy behind claims that a provider or tool requires it.
Use this acceptance model when auditing a skill:
User outcome + higher-level invariants + risks created by the action
= blocking acceptance criteria. Everything else is advice or follow-up.Flag checklist language that silently promotes recommendations, asks a broken subsystem to approve its own repair, coordinates unrelated or read-only work, or keeps gathering proof after the requested outcome is established. For a bounded task, more than one or two skill-added gates needs a direct correctness, privacy, security, data-integrity, or irreversible-action justification.
Cut trigger aggression
The frontmatter description is always-loaded routing context. Make it narrow and concrete:
- name positive user intents and artifacts that should activate the skill;
- remove phrases such as “any task,” “all requests,” and broad product-name-only triggers unless universal activation is truly intended;
- add concise exclusions for nearby tasks that should not activate it;
- move no trigger rules into the body, which is read only after activation; and
- keep
agents/openai.yamldisplay text and default prompt aligned with the narrowed contract.
Do not make the description so timid that explicit requests stop matching.
Show full SKILL.md (294 more words)Show less
Apply the cut
Prefer deletion over compression. Preserve:
- task-specific decision rules and failure modes;
- domain-specific safety or authorization boundaries;
- exact tool or file contracts that are easy to misuse; and
- routing to resources that are genuinely needed conditionally.
Remove:
- explanations written for a novice human when the agent already knows them;
- exhaustive product catalogs, copied manuals, and speculative edge cases;
- mandatory-sounding ceremony that applies only to one project or incident;
- repeated summaries, principles, checklists, and completion language; and
- historical justification that does not change future execution.
Also remove or reclassify adjacent improvements presented as prerequisites, global coordination without a concrete shared mutation surface, and exhaustive verification whose result cannot change acceptance of the requested outcome. Preserve exact-target, authorization, privacy, secret, user-data, migration, rollback, and irreversible-action controls where the named risk exists.
Do not preserve text merely because it is correct. Do not replace readable
instructions with dense slogans, and do not move bulk into references simply to
make SKILL.md look shorter. Do not delete scripts, assets, or operational
references based only on apparent non-use; inspect their callers and purpose.
For unstable provider claims, check current primary documentation. Separate provider constraints from optional recommendations and local policy.
Validate and report
Preserve unrelated work. After editing, update broken links and UI metadata, run the repository's skill validator, and inspect the final diff.
Report:
- before/after lines, words, and files;
- the retained behavioral contract;
- a compact keep/condense/move/delete classification with reasons;
- trigger changes and exclusions;
- validation performed; and
- uncertain material deliberately left untouched.
For acceptance-model audits, also report the stop condition, any skill-added blocking criteria, and why each remaining gate is action-required or risk-triggered.
A successful cut is smaller and less eager to trigger while still changing the agent's behavior in every case the skill was created to handle.
© swyxio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in skill-cutter of swyxio/skills.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 038ef34
Compare with similar skills
Skill Cutter next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Skill Cutter this skillswyxio/skills | 176 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Crossframe Criticalsickn33/agentic-awesome-skills | 47k | 1 repos | ~1.3k | Automated safety check: Pass | MIT | |
| No Explicit Anythedaviddias/Front-End-Checklist | 74k | — | ~565 | Automated safety check: Pass | MIT | |
| CSS Criticalthedaviddias/Front-End-Checklist | 74k | — | ~441 | Automated safety check: Pass | MIT | |
| Criticism Self CriticismHughYau/qiushi-skill | 3.8k | — | ~423 | Automated safety check: Pass | MIT | |
| Critical Imagesthedaviddias/Front-End-Checklist | 74k | — | ~392 | Automated safety check: Pass | MIT |
Similar skills
No Explicit Any
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing TypeScript files for type safety regressions, during code review of functions that handle external data, or when the codebase has ESLint warnings for…
CSS Critical
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing stylesheets, component styles, and responsive behavior related to Inline critical CSS for faster rendering.
Criticism Self Criticism
HughYau/qiushi-skill
批评与自我批评：在工作完成、阶段验收、收到批评或同类错误反复出现时，对成果和过程做诚实、具体、基于事实的审视，输出可执行的改进项，并处理外来批评而不辩解。触发信号包括 review、复盘、审查、"帮我看看有没有问题"、"你确定吗"；任务刚开始或只是单步查询时不触发。
Critical Images
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing image assets, markup, and CDN or build transforms related to Prioritize loading critical images.
Critical Request Chains
thedaviddias/Front-End-Checklist
A skill your agent uses when auditing slow page loads, heavy assets, or rendering delays related to Minimize critical request chains.
More from swyxio/skills
All 89 skills in this repoProgrammatic Agents
swyxio/skills
Run a selected coding-agent CLI programmatically, with latency, error, usage, cost, and trace logging.
Reserved Handle Policy
swyxio/skills
Design, implement, audit, or refresh protected username and handle namespaces for public products.
New Mac Setup
swyxio/skills
Fully automated new Mac setup for fullstack web developers and AI engineers.
Youtube API
swyxio/skills
Manage YouTube videos programmatically via the YouTube Data API v3 — upload video files, upload custom thumbnails, update video metadata (titles, descriptions, tags), and query video/channel info…
Youtube Studio Batch Upload
swyxio/skills
Batch YouTube Studio upload workflow for videos sourced from Airtable, Google Drive, Loom, YouTube, or local files.
Deep Trajectory Analysis
swyxio/skills
Reconstruct and visually analyze paired agent, game, or policy trajectories to determine whether changed actions produced their intended effects.
Questions about Skill Cutter
What does Skill Cutter do?
Critically audit or explicitly trim an existing agent skill to its behavioral core, including narrowing over-broad trigger metadata. Skill Cutter is an agent skill from swyxio/skills. Critically audit or explicitly trim an existing agent skill to its behavioral core, including narrowing over-broad trigger metadata.
When should I use Skill Cutter?
Skill Cutter fits situations like: the user asks to cut; reduce the context cost; trigger aggressiveness of a SKILL.md; merely because a skill is long.
How do I install Skill Cutter in Claude Code?
Run `npx skills add swyxio/skills --skill skill-cutter -a claude-code`. Or copy the skill folder (skill-cutter in swyxio/skills) into .claude/skills/skill-cutter in your project. Claude Code loads it when a task matches its description.
How do I install Skill Cutter in Codex?
Run `npx skills add swyxio/skills --skill skill-cutter -a codex`. Or copy the skill folder (skill-cutter in swyxio/skills) into .agents/skills/skill-cutter in your project. Codex loads it when a task matches its description.
Can I use Skill Cutter in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add swyxio/skills --skill skill-cutter -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-cutter, .gemini/skills/skill-cutter, .github/skills/skill-cutter and .opencode/skills/skill-cutter in your project.
What does Skill Cutter need to run?
SKILL.md names no scripts, command-line tools or credentials: Skill Cutter is instructions for the agent only.
Does Skill Cutter access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Skill Cutter safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Skill Cutter use?
Skill Cutter is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Skill Cutter use?
About 1.5k tokens (SKILL.md is roughly 6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Skill Cutter?
Skills that share tags, products or a category with Skill Cutter: Crossframe Critical (sickn33/agentic-awesome-skills, 47k stars), No Explicit Any (thedaviddias/Front-End-Checklist, 74k stars), CSS Critical (thedaviddias/Front-End-Checklist, 74k stars) and Criticism Self Criticism (HughYau/qiushi-skill, 3.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Skill Cutter?
swyxio (a GitHub user) maintains it in swyxio/skills, which has 176 GitHub stars. The repository holds 89 skills in this directory. The repository was last updated on October 5, 2026.
Source: swyxio/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.