Skip to content
Skills Library
AI & agents · Building & coding

forge-agent

/forge-agent

Generate a project-specific agent definition for a ticketmill pipeline role (implementer, code reviewer, test validator, etc). Use when mill-init finds a role gap, or when asked to create an agent for a repo. Produces .claude/agents/<name>.md grounded in domain research and the actual codebase.

Repository
ticketmill ↗
Licence
MIT
Last repository change
09.08.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 09.08.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Generate a project-specific agent definition for a ticketmill pipeline role (implementer, code reviewer, test validator, etc). Use when mill-init finds a role gap, or when asked to create an agent for a repo. Produces .claude/agents/<name>.md grounded in domain research and the actual codebase.

Original author description

Generate a project-specific agent definition for a ticketmill pipeline role (implementer, code reviewer, test validator, etc). Use when mill-init finds a role gap, or when asked to create an agent for a repo. Produces .claude/agents/<name>.md grounded in domain research and the actual codebase.

How it works

  1. Inputs
  2. Step 1: Research the domain
  3. Step 2: Ground it in the codebase
  4. Step 3: Write the agent
  5. Step 4: Check it
  6. Step 5: Deliver
Original SKILL.md headings · 89 lines, 527 words
SKILL.md preview
---
name: forge-agent
description: Generate a project-specific agent definition for a ticketmill pipeline role (implementer, code reviewer, test validator, etc). Use when mill-init finds a role gap, or when asked to create an agent for a repo. Produces .claude/agents/<name>.md grounded in domain research and the actual codebase.
---

# forge-agent: generate a project agent for a pipeline role

Writing an agent is Test-Driven Development applied to a role definition: gather
evidence first (domain best practices + how THIS codebase actually works), write the
persona against that evidence, then check it against representative tasks. An agent
written from generic knowledge alone is a generic agent. The codebase context is
what earns its keep.

## Inputs

- The ROLE it fills (one of ticketmill's: implementer for a domain, task_reviewer,
  spec_reviewer, code_reviewer, contrarian, test_validator, simplifier,
  docblock_writer, doc_writer; or any role the user names).
- The target repo root.

## Step 1: Research the domain

Use WebSearch for the agent's domain, current year:
- "[domain/framework] best practices [year]"
- "[domain] anti-patterns" / "common mistakes"
- "[technology] security considerations" (when applicable)

Harvest concrete, actionable items: these feed the anti-patterns section. Skip
generic advice ("write clean code") that changes no behavior.

## Step 2: Ground it in the codebase

1. Read the repo's CLAUDE.md and README for hard conventions.
2. Explore the structure the agent will work in (key directories, existing services/
   modules, naming patterns, test layout).
3. Read 1-2 existing agents in `.claude/agents/` for coordination conventions and
   deferral relationships to keep consistent.

## Step 3: Write the agent

File: `<ROOT>/.claude/agents/<kebab-case-name>.md`

```markdown
---
name: agent-name
description: [Role statement]. Use for [specific task types].
---

You are a [specific role] with expertise in [domains], working on [this project].

## Core competencies
- [Capability]: specifics

**Not in scope** (defer to [other-agent]): [excluded domains]

## Anti-patterns to avoid
- **[Specific mistake]**: [what to do instead]   <- from research AND this codebase

## Project context
[Directory structure the agent works in; key commands (test, build, lint);
conventions from CLAUDE.md that constrain this agent's work]

## Coordination
[How it reports completion; who it defers to]
```

Quality bars (all must hold):
- Description under 500 chars, states triggers, contains NO process summary
  (a process in the description gets followed INSTEAD of the agent body).
- Persona names the project and stack. Never "you are a helpful assistant".
- Every anti-pattern is actionable and specific; at least a few must come from
  THIS codebase, not just the web research.
- Explicit scope boundaries with deferral targets when sibling agents exist.
- Omit `model:` frontmatter unless the role demonstrably needs a specific tier.

## Step 4: Check it

Pick 1-2 representative tasks for the role (e.g. for a code_reviewer: review the
repo's most recent real PR diff). Walk through how the agent body handles them.
Close the loopholes you find (scope violations, missing project commands, vague
guidance) before delivering.

## Step 5: Deliver

1. Show the user the file and where it landed.
2. If invoked from mill-init: update the role map entry to the new agent name.
3. Mark expectations honestly: the agent is **unvetted** until it has been observed
   on real tasks. Recommend watching its first mill run's review/fix iterations
   (the run report's per-issue timeline shows exactly where an agent thrashed).
4. Note the session-restart caveat: ticketmill's engine uses the agent file
   immediately (stage subagents read it directly), but the agent will not appear
   in the Task tool's registry for direct use until the session restarts.

Versions

RepositoryScoreLicence
This page · aaddrick/ticketmill100MIT
mjha-arya/claude-code-skills100MIT

Database snapshot: 13.11.2026 · package version 640bd7119617 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 96agent
    Create a provider-neutral agent definition for this repo in .reins/agents/, and optionally generate a Claude Code wrapper. Use it when the person asks to create, add or design an agent (a reviewer, an explorer, a tester, a migration helper…).
  • 100forge-install
    This skill should be used when the user wants to "install the Forge plugin", "set up Forge", "install forge-agent-lens-for-claude-code", "configure Forge for the first time", "get started with Forge tracing", or needs to complete the initial setup of the Forge Agent Lens for…
  • 96reins-agent
    Create a provider-neutral agent definition for this repo in .reins/agents/, and optionally generate a Claude Code wrapper. Use it when the person asks to create, add or design an agent (a reviewer, an explorer, a tester, a migration helper…).
  • 100generate-agents-md
    Generate a lean, high-signal CLAUDE.md for a repository from codebase analysis. Grounded in Anthropic best practices and empirical studies; built to pass review-agents-md (a bundled validator enforces the same critical checks). Use when the user asks to "generate CLAUDE.md",…
  • 91create-agent
    Create new agents for the code-forge application. Agents are stored as .md files in the <cwd>/.forge/agents directory with YAML frontmatter (id, title, description, reasoning, tools, user_prompt) and markdown body containing agent instructions. Use when users need to add new…
  • 100init
    This skill should be used when a user asks to initialize a repository for AI agents, create or update an AGENTS.md file, scaffold agent instructions for a codebase, or improve existing agent guidance. Triggers include phrases like 'create an AGENTS.md', 'set up agent…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.