build-evidence-pack
Build or verify a hash-addressed evidence pack for an Azure TrustOps system.
Skill by AAH20
Chalk Labs
Need help deploying build-evidence-pack?
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/aah20-build-evidence-pack
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: cloud, 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. 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/build-evidence-pack
What's inside
- Skill name
build-evidence-pack- Description
- Build or verify a hash-addressed evidence pack for an Azure TrustOps system. Use for proof bundles, validation manifests, audit evidence, or claim verification.
- License
- MIT
- Instructions
- 19 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: missing
Files (1)
- SKILL.md
SKILL.md (first lines)
# Build an evidence pack Use `contracts/evidence-manifest.schema.json` as the minimum contract. 1. Inventory claims before artifacts. Every claim must be `verified`, `unverified`, `inferred`, or `contradicted`. 2. Link verified claims to direct evidence; never use a screenshot merely showing that a portal page exists as proof of runtime behavior. 3. Record repository, full commit SHA, package version, UTC observation time, cloud, deployment scope, evaluator version, and result. 4. Record each artifact's media type, byte count, SHA-256, source, and redaction. 5. Separate public-safe evidence from restricted evidence. 6. Declare freshness and limitations. Expired evidence can remain historical but cannot support a current-state claim. 7. Recompute hashes and validate the manifest before reporting success. Do not modify original evidence. Produce a new manifest for a new run.
From AAH20/azure-trustops, MIT.
More from AAH20/azure-trustops
- 0.522score
investigate-sentinel-pr
AAH20
Investigate a Microsoft Sentinel pull request and all related review context.
SkillBFreshness: BClaude Code +9 - 0.517score
evaluate-response-safety
AAH20
Evaluate a Sentinel detection-to-response workflow against deterministic safety invariants, adversarial cases, outcome semantics, and regression gates.
SkillBFreshness: BClaude Code +9 - 0.517score
prepare-live-briefing
AAH20
Prepare a current, audience-specific live Azure architecture demonstration and grounded Q&A from TrustOps evidence.
SkillBFreshness: BClaude Code +9 - 0.517score
validate-azure-portal
AAH20
Validate a Sentinel solution in an isolated Azure environment and capture evidence.
SkillBFreshness: BClaude Code +9 - 0.512score
assess-sovereign-portability
AAH20
Assess whether an Azure architecture can port to Azure Government or another sovereign cloud without overstating support.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 27, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/AAH20/azure-trustops
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from AAH20
- 0.522score
investigate-sentinel-pr
AAH20
Investigate a Microsoft Sentinel pull request and all related review context.
SkillBFreshness: BClaude Code +9 - 0.517score
evaluate-response-safety
AAH20
Evaluate a Sentinel detection-to-response workflow against deterministic safety invariants, adversarial cases, outcome semantics, and regression gates.
SkillBFreshness: BClaude Code +9 - 0.517score
prepare-live-briefing
AAH20
Prepare a current, audience-specific live Azure architecture demonstration and grounded Q&A from TrustOps evidence.
SkillBFreshness: BClaude Code +9 - 0.517score
validate-azure-portal
AAH20
Validate a Sentinel solution in an isolated Azure environment and capture evidence.
SkillBFreshness: BClaude Code +9 - 0.512score
assess-sovereign-portability
AAH20
Assess whether an Azure architecture can port to Azure Government or another sovereign cloud without overstating support.
SkillBFreshness: BClaude Code +9 - 0.503score
Agent Action Gate
AAH20
Gate/Prove: deny unattended destructive agent tools.
ConnectorAFreshness: ALocalRead-onlyClaude Desktop
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 build-evidence-pack 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
build-evidence-pack skill. Agent Mart. https://agentmart.dev/skills/aah20-build-evidence-pack (last updated 2026-10-24)