Skip to content
Agentmart
Submit a tool
This entry duplicates skillforge-authoring, which is the one we list in search.

skillforge-authoring

Add or modify Skillforge personas, verticals, canonical agents, policy constraints, and agent skills.

Skill by aws-samplesOfficial

IndexedApache-2.0★ 3
Write a review

Chalk Labs

Need help deploying skillforge-authoring?

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.

Book a call

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/aws-samples-skillforge-authoring-81ddf4

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.

We use your email only for this newsletter. Privacy

About

Add or modify Skillforge personas, verticals, canonical agents, policy constraints, and agent skills. Use when asked to add, create, or change a persona or audience pack, a vertical or domain/compliance add-on, an agent or per-host tool grant, a profile branch, a constraint, or a source SKILL.md in a Skillforge repository. Do not use only to install an already-built pack.

Use cases: security, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions: not checked yet.

What's inside

Skill name
skillforge-authoring
Description
Add or modify Skillforge personas, verticals, canonical agents, policy constraints, and agent skills. Use when asked to add, create, or change a persona or audience pack, a vertical or domain/compliance add-on, an agent or per-host tool grant, a profile branch, a constraint, or a source SKILL.md in a Skillforge repository. Do not use only to install an already-built pack.
License
Apache-2.0
Metadata
category: development
Instructions
51 lines in SKILL.md · view on GitHub

Files (7)

  • .skillforge-generated
  • SKILL.md
  • add-agent.md · references/
  • add-persona.md · references/
  • add-vertical.md · references/
  • harness-contracts.md · references/
  • skill-quality.md · references/

SKILL.md (first lines)

# Author Skillforge content

Work in the canonical source trees. Do not hand-edit generated packs, marketplaces, or host copies
of this authoring skill.

## Route the change

- For a persona or audience pack, read [references/add-persona.md](references/add-persona.md).
- For a vertical, domain pack, or compliance add-on, read
  [references/add-vertical.md](references/add-vertical.md).
- For a canonical agent or per-host tool grant, read
  [references/add-agent.md](references/add-agent.md).
- For a new or changed canonical skill, constraint, profile block, or MCP mention, read
  [references/skill-quality.md](references/skill-quality.md).
- When changing build, install, validation, marketplace, or host-specific output behavior, also
  read [references/harness-contracts.md](references/harness-contracts.md).

Read only the references needed by the current request.

## Shared invariants

- Personas swap; verticals add.
- Every conditional group names every persona, including explicit empty branches.
- Prefer a constraint for different boundaries and a profile block for genuinely different work.
- A vertical-tagged skill is excluded from every persona's `include_skills`.
- Persona frontmatter is shared and cannot make promises that only one resolved branch fulfils.
- MCP entitlement is derived; do not declare it on a persona.
- Every canonical agent declares explicit grants for Claude Code, Codex, Kiro, and Amazon Quick.

## Finish

If this canonical authoring skill changed, run:

```bash
python3 -m skillforge sync-harness
```

Then build and verify the complete matrix:

```bash
python3 -m skillforge build --all --vertical all
python3 -m skillforge validate
python3 -m skillforge eval
python3 -m skillforge mutate-test
python3 -m unittest discover -s tests -v
```

Inspect the resulting diff. Source changes should be intentional; generated changes should follow
from the build or harness sync.

From aws-samples/sample-skillforge, Apache-2.0.

More from aws-samples/sample-skillforge

Signals

Stars
3
Forks
1
Open issues
0
Last commit (this folder)
Sep 11, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from aws-samples

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 skillforge-authoring 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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying skillforge-authoring?

CallGet help
Cite this page

skillforge-authoring. Agent Mart. https://agentmart.dev/skills/aws-samples-skillforge-authoring-81ddf4 (last updated 2026-10-24)