verify-compression
Use after compressing any artifact (skill, prompt, ruleset, doc) to confirm the compressed version behaves identically at lower token cost; when the user…
Skill by sidwood
Chalk Labs
Need help deploying verify-compression?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sidwood-verify-compression
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/verify-compression
What's inside
- Skill name
verify-compression- Description
- Use after compressing any artifact (skill, prompt, ruleset, doc) to confirm the compressed version behaves identically at lower token cost; when the user invokes /verify-compression or says "check predictability", "did compression change behavior", "verify the compressed version".
- License
- unknown
- Instructions
- 26 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from sidwood/skills
- 0.534score
domain-modeling
sidwood
Build and sharpen a project's domain model.
SkillAFreshness: AClaude Code +9 - 0.527score
pr
sidwood
Use when writing a PR body.
SkillAFreshness: AClaude Code +9 - 0.525score
implement-spec
sidwood
Implement the result of /to-spec and /to-tickets in code.
SkillAFreshness: AClaude Code +9 - 0.524score
bug-report
sidwood
Interactive bug-reporting session where the user describes problems conversationally and the agent files GitHub issues.
SkillBFreshness: BClaude Code +9 - 0.523score
implement
sidwood
Implement a piece of work based on a spec or set of tickets.
SkillAFreshness: AClaude Code +9 - 0.520score
to-skill
sidwood
Use when creating, writing, editing, or auditing an agent skill, authoring a SKILL.md, or packaging a capability into a skill folder.
SkillBFreshness: BClaude Code +9 - 0.519score
resolving-rebase-conflicts
sidwood
Use when a Git rebase is paused by conflicts or the user asks to resolve rebase conflicts while preserving linear history.
SkillBFreshness: BClaude Code +9 - 0.519score
codebase-design
sidwood
Use when designing or improving a module interface, finding deepening opportunities, deciding where a seam belongs, or making code more testable or easier for…
SkillBFreshness: BClaude Code +9 - 0.519score
compress-a-skill
sidwood
Use when authoring or editing a skill (or other context-window artifact) and you want to cut its token cost; when the user invokes /compress-a-skill or says…
SkillBFreshness: BClaude Code +9 - 0.519score
humanizer
sidwood
Rewrite AI-sounding text so it reads naturally without changing what it says.
SkillBFreshness: BClaude Code +9 - 0.519score
writing-for-agents
sidwood
Use when creating, editing, or auditing AGENTS.md, CLAUDE.md, system prompts, agent-facing repository instructions, or documents reached through those…
SkillBFreshness: BClaude Code +9 - 0.519score
improve-codebase-architecture
sidwood
Use when reviewing a codebase for architectural friction, deepening opportunities, tightly coupled modules, poor test seams, or changes that would improve…
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 17, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/sidwood/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sidwood
- 0.534score
domain-modeling
sidwood
Build and sharpen a project's domain model.
SkillAFreshness: AClaude Code +9 - 0.527score
pr
sidwood
Use when writing a PR body.
SkillAFreshness: AClaude Code +9 - 0.525score
implement-spec
sidwood
Implement the result of /to-spec and /to-tickets in code.
SkillAFreshness: AClaude Code +9 - 0.524score
bug-report
sidwood
Interactive bug-reporting session where the user describes problems conversationally and the agent files GitHub issues.
SkillBFreshness: BClaude Code +9 - 0.523score
implement
sidwood
Implement a piece of work based on a spec or set of tickets.
SkillAFreshness: AClaude Code +9 - 0.520score
to-skill
sidwood
Use when creating, writing, editing, or auditing an agent skill, authoring a SKILL.md, or packaging a capability into a skill folder.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get verify-compression running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
verify-compression skill. Agent Mart. https://agentmart.dev/skills/sidwood-verify-compression (last updated 2026-10-24)