deadwood
Find deadwood in test suites — tests that add maintenance cost without catching real bugs.
Skill by cah4a
Chalk Labs
Need help deploying deadwood?
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/cah4a-deadwood
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: testing
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 Nov 2, 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/deadwood
What's inside
- Skill name
deadwood- Description
- Find deadwood in test suites — tests that add maintenance cost without catching real bugs.
- License
- unknown
- Instructions
- 3 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from cah4a/skills
- 0.604score
spike
cah4a
Drive an uncertain coding task by exploring approaches on a live, backtrackable stack — checkpoint the code, send a subagent down one route, judge what comes…
SkillAFreshness: A★ 3Claude Code +9 - 0.599score
simplifier
cah4a
Simplification expert.
SkillAFreshness: A★ 3Claude Code +9 - 0.599score
coder
cah4a
Code-writing expert.
SkillAFreshness: A★ 3Claude Code +9 - 0.596score
lfg
cah4a
Manually invoked end-to-end coding workflow that unfolds a task into subagent-implemented steps and holds the result to a senior-engineer bar.
SkillAFreshness: A★ 3Claude Code +9 - 0.593score
rules-check
cah4a
Check the current diff against the repo's written rules, one subagent per rule bucket.
SkillAFreshness: A★ 3Claude Code +9 - 0.593score
polisher
cah4a
Finishing pass — applies the safe list of mechanical refactors to changed code, reports the rest.
SkillAFreshness: A★ 3Claude Code +9 - 0.593score
self-grill
cah4a
Grill a task's unknowns with one cold interrogator until nothing blocks building.
SkillAFreshness: A★ 3Claude Code +9 - 0.593score
doc-verifier
cah4a
Test how well a document transfers shared understanding to a reader with no prior context.
SkillAFreshness: A★ 3Claude Code +9 - 0.593score
legit
cah4a
Breakage audit — reports what will actually break, never fixes.
SkillAFreshness: A★ 3Claude Code +9 - 0.563score
humanizer
cah4a
Find source code that needs refactoring because it is unnecessarily hard for humans to understand.
SkillAFreshness: A★ 3Claude Code +9 - 0.514score
wiki
cah4a
Project knowledge base for decisions, patterns, and architectural insights.
SkillCFreshness: C★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 3, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/cah4a/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from cah4a
- 0.604score
spike
cah4a
Drive an uncertain coding task by exploring approaches on a live, backtrackable stack — checkpoint the code, send a subagent down one route, judge what comes…
SkillAFreshness: A★ 3Claude Code +9 - 0.599score
simplifier
cah4a
Simplification expert.
SkillAFreshness: A★ 3Claude Code +9 - 0.599score
coder
cah4a
Code-writing expert.
SkillAFreshness: A★ 3Claude Code +9 - 0.596score
lfg
cah4a
Manually invoked end-to-end coding workflow that unfolds a task into subagent-implemented steps and holds the result to a senior-engineer bar.
SkillAFreshness: A★ 3Claude Code +9 - 0.593score
rules-check
cah4a
Check the current diff against the repo's written rules, one subagent per rule bucket.
SkillAFreshness: A★ 3Claude Code +9 - 0.593score
polisher
cah4a
Finishing pass — applies the safe list of mechanical refactors to changed code, reports the rest.
SkillAFreshness: A★ 3Claude 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 deadwood 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
deadwood skill. Agent Mart. https://agentmart.dev/skills/cah4a-deadwood (last updated 2026-10-24)