evidence-first-communication
Lead every factual claim with evidence.
Skill by amirulhazym
Chalk Labs
Need help deploying evidence-first-communication?
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/amirulhazym-evidence-first-communication
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: sales, 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/evidence-first-communication
What's inside
- Skill name
evidence-first-communication- Description
- Lead every factual claim with evidence. When challenged, provide the evidence and reasoning — never reverse position without verification. Covers correct response to user corrections and challenges.
- License
- unknown
- Instructions
- 593 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- body: 593 lines (spec recommends under 500)
Files (21)
- SKILL.md
- antigravity-live-catalog-and-wire-routing.md · references/
- background-suite-status-and-baseline-attribution.md · references/
- capability-vs-instance-state.md · references/
- cc-live-runtime-recheck-20260819.md · references/
- cloud-backup-artifact-verification.md · references/
- compact-time-confirmations.md · references/
- dexa-chart-vs-json-reconciliation-20260825.md · references/
- git-backed-final-suite-materialization-parity.md · references/
- git-identity-and-attribution-preflight.md · references/
- git-live-byte-forensics-and-evidence-packaging.md · references/
- live-resolver-vs-static-mapping.md · references/
- med-confirm-provenance-and-parser-gates-20260814.md · references/
- plugin-provider-boundary-check.md · references/
- reviewer-claim-audit-and-final-suite-readiness.md · references/
- runtime-config-provenance.md · references/
- screenshot-live-state-reconciliation.md · references/
- session-resume-lineage-and-title-verification.md · references/
- session-status-reconciliation.md · references/
- single-repo-migration-claim-audit-20260828.md · references/
- structured-output-exit-status.md · references/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from amirulhazym/hermes-agent-personal_assistant
- 0.548score
independent-review-verification
amirulhazym
Use when reviewer flags candidate; reproduce it first.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
self-improving-agent
amirulhazym
Use when facing repeated corrections, discovering recurring failure patterns, or needing a systematic way to compound learning across sessions.
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
baseline-first-reconciliation
amirulhazym
Use before recovery or post-merge reconciliation plans.
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
caveman
amirulhazym
Ultra-compressed response mode.
SkillBFreshness: B★ 1Claude Code +9 - 0.534score
evidence-first-feasibility-assessment
amirulhazym
Multi-phase feasibility gatekeeping before building solutions.
SkillBFreshness: B★ 1Claude Code +9 - 0.521score
writing-plans
amirulhazym
Use when you have a spec or requirements for a multi-step task, before touching code
SkillBFreshness: B★ 1Claude Code +9 - 0.519score
brainstorming
amirulhazym
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.
SkillBFreshness: B★ 1Claude Code +9 - 0.516score
executing-plans
amirulhazym
Use when you have a written implementation plan to execute in a separate session with review checkpoints
SkillBFreshness: B★ 1Claude Code +9 - 0.516score
dispatching-parallel-agents
amirulhazym
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
SkillBFreshness: B★ 1Claude Code +9 - 0.516score
subagent-driven-development
amirulhazym
Use when executing implementation plans with independent tasks in the current session
SkillBFreshness: B★ 1Claude Code +9 - 0.505score
verification-before-completion
amirulhazym
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output…
SkillBFreshness: B★ 1Claude Code +9 - 0.294score
4R-design-skills
amirulhazym
No description from the publisher yet.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 31, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from amirulhazym
- 0.548score
independent-review-verification
amirulhazym
Use when reviewer flags candidate; reproduce it first.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
self-improving-agent
amirulhazym
Use when facing repeated corrections, discovering recurring failure patterns, or needing a systematic way to compound learning across sessions.
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
baseline-first-reconciliation
amirulhazym
Use before recovery or post-merge reconciliation plans.
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
caveman
amirulhazym
Ultra-compressed response mode.
SkillBFreshness: B★ 1Claude Code +9 - 0.534score
evidence-first-feasibility-assessment
amirulhazym
Multi-phase feasibility gatekeeping before building solutions.
SkillBFreshness: B★ 1Claude Code +9 - 0.521score
writing-plans
amirulhazym
Use when you have a spec or requirements for a multi-step task, before touching code
SkillBFreshness: B★ 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 evidence-first-communication 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
evidence-first-communication skill. Agent Mart. https://agentmart.dev/skills/amirulhazym-evidence-first-communication (last updated 2026-10-24)