zf-find-simplifications
Use on demand to find evidence-backed simplifications in ZaoFu itself, in applications developed with ZaoFu, or in an Autoresearch simplify audit.
Skill by uisee-ai
Chalk Labs
Need help deploying zf-find-simplifications?
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/uisee-ai-zf-find-simplifications
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: security
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 and code. 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/zf-find-simplifications
What's inside
- Skill name
zf-find-simplifications- Description
- Use on demand to find evidence-backed simplifications in ZaoFu itself, in applications developed with ZaoFu, or in an Autoresearch simplify audit. Proves consumers and protected seams before proposing deletion, coalescing, demotion, or dependency replacement; output is proposal-only until separately approved.
- License
- Apache-2.0
- Instructions
- 211 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# ZaoFu Find Simplifications
Use this skill to reduce real maintenance surface, not to reward a smaller diff
or a lower line count. A valid candidate has call-site evidence, states what
behavior is surrendered, respects the repository's protected seams, and deletes
or coalesces more complexity than it relocates.
## Operating Modes
Choose exactly one mode before working:
- **Audit mode:** use for broad repository surveys, architecture reduction,
release/refactor checkpoints, and every Autoresearch `simplify` request. It
is read-only and produces a proposal; it never authorizes implementation,
runtime-state mutation, task completion, or direct mainline application.
- **Recent-diff refinement mode:** use only when the current assignment already
authorizes code edits. Limit edits to the current session's owned diff, keep
observable behavior exact, and rerun the same focused verification. This is
the daily ZaoFu/application-development counterpart to a code-simplifier
pass, not permission to refactor untouched modules.
If scope or edit authorization is ambiguous, use audit mode.
## When To Use
Use it on demand in any of these contexts:
- **ZaoFu daily iteration:** repeated fallback branches, compatibility layers,
duplicate facts, oversized ownership surfaces, or code repeatedly repaired in
the same area. After an implementation, recent-diff refinement may improve
clarity without changing behavior.
- **Applications developed with ZaoFu:** hand-written infrastructure, abandoned
options, duplicated domain representations, or test-only public APIs in the
target application. The application's owner contract and product behavior
take precedence over generic ZaoFu preferences.
- **Autoresearch:** an explicit `autoresearch.loop.requested(mode=simplify)` or
a separately approved simplification checkpoint. The output remains a
`simplification_audit.v1` proposal; Autoresearch must not apply it directly.
- **Release/refactor checkpoint:** after the behavior is proven and before more
variants are added, when consolidation can be evaluated against a stable
target.
Do not auto-load this skill for every Impl, Verify, reflection, or ordinary code
review. Do not use it to turn an unrelated delivery task into a refactor.
## Recent-Diff Refinement
This narrow mode adopts the useful behavior-preserving discipline of Anthropic's
`code-simplifier` agent while keeping ZaoFu's evidence and ownership rules:
1. Pin the owned scope with `git diff -- <explicit paths>` and the current task
contract. Do not edit another driver's staged, dirty, or untracked files.
2. Read the repository's current `AGENTS.md` / `CLAUDE.md` and existing nearby
patterns. Project rules replace hard-coded language/framework preferences.
3. Preserve public APIs, outputs, errors, side effects, ordering, persistence,
events, config defaults, security boundaries, timing/concurrency semantics,
and accepted compatibility behavior.
4. Reduce unnecessary nesting, duplicate branches, redundant abstractions,
vague names, and comments that only narrate syntax. Consolidate only logic
with one owner and one invariant.
5. Prefer readable, explicit control flow over dense expressions, clever
one-liners, nested ternaries, or line-count reduction. Fewer lines are not a
success metric.
6. Apply the smallest refinement, inspect the resulting diff, and rerun the
pre-refinement focused tests plus any direct caller/contract checks crossed.
7. If a candidate changes supported behavior, requires migration, crosses the
task's allowed paths, or cannot be proved equivalent, do not apply it. Move
it to an audit proposal or reject it.
No edit is a valid outcome when the current diff is already the clearest safe
implementation.
## Scope First
State the repository, target commit, bounded directories or subsystem, and the
reason simplification is being considered. Read the applicable `AGENTS.md`,
current owner/design documents, dependency manifest, and recent incident or
change evidence before searching for candidates.
For ZaoFu itself, load `zf-cr` and
`zf-harness-design-impl-game-review` when the audit needs architecture-wide
adjudication, verify claims against current code/tests, and preserve these
boundaries unless the owner explicitly approves an architecture change:
- `zf.yaml` remains the single control-plane configuration.
- EventLog ordering/causation, canonical Stores, artifact bodies/refs/digests,
and SQLite projections have different owners; do not collapse truth into a
read model or duplicate semantic bodies into events.
- The deterministic Kernel and a configured `orchestrator` role agent are not
interchangeable.
- Product Flow and supported Legacy routes may intentionally differ.
- Provider, transport, worktree, session, and security seams may have dynamic
consumers that a static symbol search cannot see.
- `skills/` is canonical; tracked provider copies are synchronized mirrors, not
independent implementations.
For an application, derive the protected seams from its PRD, public API,
persisted data, deployment/runtime contract, and real E2E behavior. Never infer
that a product feature is disposable merely because ZaoFu does not use it.
## Survey Method
1. Start with the largest recent production deltas and repeatedly changed
modules. Use `git log`, `git diff --stat`, line counts, incident reports, and
rework evidence to prioritize the survey.
2. Search exact symbols, event names, config keys, routes, wire strings, artifact
kinds, CLI commands, and reflective registry names with `rg`.
3. Read every plausible caller. Classify consumers as:
- `production_static`: direct runtime callers;
- `production_dynamic`: registries, config, events, plugins, serialization,
templates, provider or transport loading;
- `operations`: migration, recovery, CLI, runbook, compatibility;
- `non_production`: tests, fixtures, docs, examples, snapshots;
- `unresolved`: evidence is insufficient.
4. Draw the fact/ownership or lifecycle graph when two mechanisms appear to
represent the same state. Similar names are not proof of duplication.
5. Check existing design decisions and prior incidents. A defensive branch that
looks redundant may encode a recovered production failure.
6. Estimate **net surface delta**: removed implementation, tests, config, docs,From uisee-ai/zaofu, Apache-2.0.
More from uisee-ai/zaofu
- 0.653score
zf-browser-e2e-contract
uisee-ai
ZaoFu browser/E2E (Docker Playwright) command-shape and clean-checkout environment checklist for writer, review, verify, and operator roles.
SkillAFreshness: A★ 34Claude Code +9 - 0.650score
zf-channel-discussion-synthesizer
uisee-ai
Use for the designated synthesizer in a ZaoFu fanout-then-synthesis Channel.
SkillAFreshness: A★ 34Claude Code +9 - 0.650score
zf-channel-discussion-participant
uisee-ai
Use for every active lens in a ZaoFu fanout-then-synthesis Channel.
SkillAFreshness: A★ 34Claude Code +9 - 0.615score
zf-record-browser-demo
uisee-ai
Use on demand to record a short, truthful browser workflow as deterministic frames plus an optimized GIF and provenance artifact.
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-channel-research-synthesizer
uisee-ai
Use when synthesizing a ZaoFu research-review Channel.
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-workflow-start-planner
uisee-ai
Use when a ZaoFu operator, Kanban Agent, Channel member, or Coding Agent must classify a tracked Task, clarify missing workflow inputs, recommend one active…
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-research-fanout-trigger
uisee-ai
ZaoFu project-level trigger for starting the fixed-role research fanout workflow from a channel or Kanban Agent request.
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-refactor-generalization-audit
uisee-ai
ZaoFu refactor portability audit for Claude or Codex.
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-backlog-batch-closeout
uisee-ai
ZaoFu backlog/task batch closeout workflow for Codex or Claude.
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-cr
uisee-ai
Read-only architecture review of the ZaoFu repository before development.
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-dynamic-artifact-gate
uisee-ai
Use in ZaoFu issue, PRD, or refactor workflows when plan, verify, judge, or replan stages must generate run-specific fact artifacts and artifact/matrix gate…
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-harness-design-handoff
uisee-ai
Use when you are arch about to emit arch.proposal.done OR critic about to emit design.critique.done.
SkillBFreshness: B★ 34Claude Code +9
Signals
- Stars
- 34
- Forks
- 4
- Open issues
- 0
- Last commit (this folder)
- Aug 18, 2026 (2 months ago)
- Last release
- Aug 21, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/uisee-ai/zaofu
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.368score
zf-find-simplifications
uisee-ai
Use on demand to find evidence-backed simplifications in ZaoFu itself, in applications developed with ZaoFu, or in an Autoresearch simplify audit.
SkillBFreshness: B★ 34Claude Code +9 - 0.368score
zf-find-simplifications
uisee-ai
Use on demand to find evidence-backed simplifications in ZaoFu itself, in applications developed with ZaoFu, or in an Autoresearch simplify audit.
SkillBFreshness: B★ 34Claude Code +9
More from uisee-ai
- 0.653score
zf-browser-e2e-contract
uisee-ai
ZaoFu browser/E2E (Docker Playwright) command-shape and clean-checkout environment checklist for writer, review, verify, and operator roles.
SkillAFreshness: A★ 34Claude Code +9 - 0.650score
zf-channel-discussion-participant
uisee-ai
Use for every active lens in a ZaoFu fanout-then-synthesis Channel.
SkillAFreshness: A★ 34Claude Code +9 - 0.650score
zf-channel-discussion-synthesizer
uisee-ai
Use for the designated synthesizer in a ZaoFu fanout-then-synthesis Channel.
SkillAFreshness: A★ 34Claude Code +9 - 0.615score
zf-record-browser-demo
uisee-ai
Use on demand to record a short, truthful browser workflow as deterministic frames plus an optimized GIF and provenance artifact.
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-research-fanout-trigger
uisee-ai
ZaoFu project-level trigger for starting the fixed-role research fanout workflow from a channel or Kanban Agent request.
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-refactor-generalization-audit
uisee-ai
ZaoFu refactor portability audit for Claude or Codex.
SkillBFreshness: B★ 34Claude 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 zf-find-simplifications 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
zf-find-simplifications skill. Agent Mart. https://agentmart.dev/skills/uisee-ai-zf-find-simplifications (last updated 2026-10-24)