simplicity-review
Review code or proposed changes using Grokking Simplicity's data, calculations, actions, shared-value ownership, and effect timing across languages.
Skill by abossard
Chalk Labs
Need help deploying simplicity-review?
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/abossard-simplicity-review
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: design, data
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/simplicity-review
What's inside
- Skill name
simplicity-review- Description
- Review code or proposed changes using Grokking Simplicity's data, calculations, actions, shared-value ownership, and effect timing across languages. Use when a diff or design moves side effects, mutates shared state, changes effect ordering or retries, or when the user asks for a Grokking Simplicity, functional-core, or over-engineering review.
- License
- MIT
- Instructions
- 49 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Simplicity review Accept a question, proposal, code scope, or diff. Treat implementation and tests as read-only; save only requested review artifacts in the permitted output scope. ## 1. Trace the changed behavior Read affected operations, callers, and required outcomes. Identify inputs, shared values, state owners, and external effects. When available, invoke `ponytail-review` for a diff, or `ponytail-audit` for an explicitly requested whole-repository complexity audit. Pass the requested scope and mutation limits. Otherwise continue this review directly. Treat Ponytail's findings as complexity input; apply the correctness criteria and verification below even when it finds nothing to cut. Complete when the scope and material behavior are known or their gaps are explicit. ## 2. Apply the review criteria Apply the criteria below to actual operations, reachable calls, aliases, and nested values. Interpret language guarantees at their actual scope. Complete when each relevant operation has a supported classification and source-backed ownership/timing checks, or explicit uncertainty. ## 3. Verify the relevant cases Use existing tests and project tools through production interfaces or existing internal access. Exercise parameterized decision cases, input preservation where mutation is a risk, and relevant effect/failure paths. Single-threaded decision cases do not establish concurrent action behavior. Complete when the affected claims have observed evidence or an explicit verification gap. ## 4. Return the review Report concrete findings with source references, behavior impact, the smallest useful refactoring proposals, and remaining uncertainty. Keep proposed extraction within existing owners and interfaces. Finish when the scoped operations are accounted for. ## Review criteria ### Data Treat shared data as immutable. Return new values for updates, copying changed nested paths and protecting values passed to mutating code. Local mutation of fresh, unshared values can stay private. Check aliasing before treating a mutability annotation as proof. ### Calculations Calculations return results from explicit value inputs or immutable constants. Keep them free of mutable external reads and effects. An action can call a calculation without making that helper an action. Keep unknown callees uncertain. ### Actions Actions depend on when or how often they run: mutable reads, I/O, time, and randomness. Inspect default arguments, getters, callbacks, and injected implementations for hidden effects. Receiving an effectful service is different from invoking it. For moved actions, check lock, transaction, retry, and cancellation scopes and required ordering, frequency, errors, and concurrency. Record intentional changes or unresolved risks.
From abossard/virtucon, MIT.
More from abossard/virtucon
- 0.592score
blueprint
abossard
Turn a coding request, idea or correction into a short blueprint of facts.
SkillAFreshness: A★ 1Claude Code - 0.592score
extract
abossard
Capture reusable lessons from a finished minime blueprint into the minime wiki, or lint the wiki.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
inspect
abossard
Independently verify a change against its minime blueprint in a fresh context.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
ousterhout-review
abossard
Apply Ousterhout's deep modules and information hiding to architecture reviews and improvement surveys in any language.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
replicate
abossard
Implement a minime blueprint test-first.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
lab
abossard
Bootstrap or verify the minime knowledge root under VIRTUCON_HQ, with no repository writes.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 22, 2026 (8 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/abossard/virtucon
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from abossard
- 0.592score
blueprint
abossard
Turn a coding request, idea or correction into a short blueprint of facts.
SkillAFreshness: A★ 1Claude Code - 0.592score
extract
abossard
Capture reusable lessons from a finished minime blueprint into the minime wiki, or lint the wiki.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
replicate
abossard
Implement a minime blueprint test-first.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
inspect
abossard
Independently verify a change against its minime blueprint in a fresh context.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
ousterhout-review
abossard
Apply Ousterhout's deep modules and information hiding to architecture reviews and improvement surveys in any language.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
lab
abossard
Bootstrap or verify the minime knowledge root under VIRTUCON_HQ, with no repository writes.
SkillAFreshness: A★ 1Claude 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 simplicity-review 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
simplicity-review skill. Agent Mart. https://agentmart.dev/skills/abossard-simplicity-review (last updated 2026-10-24)