Defame1297
591b9cccb8
Two review passes on PR #91 (correctness + simplification) found the
prior fixup commit (d6fd9b6) left the deprecation notice it added
half-applied, cited a nonexistent ADR, and introduced/compounded a
few duplicate restatements of the same facts across apm-workflow's
skill files and apm-orchestrate's Hard rules.
- plugin-author/SKILL.md cited ADR-0016 (doesn't exist) instead of
ADR-0006 for the version-parity invariant.
- The deprecation banner on plugin-author/marketplace-author wasn't
reflected in their routing `description:` frontmatter, forge's
routing table, either kyberforge README skill table, or CONTEXT.md
— now propagated consistently; routing behavior is unchanged since
issue #90 (repo-wide apm conversion) hasn't landed yet.
- apm-orchestrate's `configure` operation only covered scaffolding a
new package, not editing an existing apm.yml (e.g. removing a
marketplace.packages[] entry, which has no dedicated `apm` CLI verb
and is just a manifest edit). Added `edit-config`, intentionally
ungated — a local file edit isn't the same class of irreversible
action as `apm publish`, and normal review already gates the commit.
- Deduplicated facts restated 3-4x across SKILL.md/references/ADR
boundaries (audit semantics, reserved name prefixes, marketplace-add
direction, registries precondition), and trimmed configure.md's
~55-line apm.yml schema dump — copied near-verbatim from the
research doc — down to a compact key list with a pointer, matching
install.md's existing terse cross-referencing style.
Deliberately left as-is: apm-orchestrate's parallel/sequential
fan-out logic stays inline rather than extracted to a shared
reference, since neither git-orchestrate nor gitea-orchestrate need
it yet — premature extraction for a single caller.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0186ERbyACLRuRxPRnqwpa4m
83 lines
8.2 KiB
Markdown
83 lines
8.2 KiB
Markdown
---
|
|
name: forge
|
|
description: >
|
|
Use when the user wants to build, add, or improve something
|
|
but hasn't yet named which of it (skill, agent, plugin, or marketplace
|
|
entry) they need — "I want to add something to kyberforge", "not sure if
|
|
this should be a skill or a plugin", "help me figure out what to build",
|
|
"I have an idea but don't know where it belongs". Grills the intent first,
|
|
classifies the target artifact type, then routes to the matching author
|
|
skill. Do not use when the user already names the target artifact type or
|
|
skill/agent explicitly (e.g. "run /skill-author on my-skill", "create an
|
|
agent for X") — route directly to that author skill instead, bypassing
|
|
forge.
|
|
metadata:
|
|
category: factory
|
|
source_keys:
|
|
- claude-code-subagents-docs
|
|
- context7-websites-code-claude
|
|
- agentskills-spec
|
|
---
|
|
|
|
## Gotchas
|
|
|
|
- forge is an optional guided entry point, not a gate — the six existing factory skills (`skill-author`, `skill-audit`, `agent-author`, `agent-audit`, `plugin-author`, `marketplace-author`) remain directly invokable and forge does not intercept those calls. Note `plugin-author` and `marketplace-author` are deprecated per ADR-0015 — superseded by `apm-workflow`, pending issue #90 — but still function normally until that lands.
|
|
- Claude Code's skill-level `context: fork` frontmatter field and the `/fork` subagent command are opposites despite sharing a name — `context: fork` isolates (fresh context, no parent access), while `/fork` inherits the full conversation. Keep this straight when deciding how to invoke a subagent in Step 3.
|
|
|
|
## Step 1 — Grill the intent
|
|
|
|
Call `bin:grill-with-docs` unless a grill session was already performed and is available in the context.
|
|
Grilling may surface that the artifact type assumed at the start is wrong, or that the idea splits into more than one artifact.
|
|
This step always runs inline, in the current conversation — grilling is interactive and a subagent cannot hold the back-and-forth.
|
|
|
|
## Step 2 — Classify the artifact type
|
|
|
|
Match the grilled intent against exactly one row (or more than one, if the intent genuinely spans several):
|
|
|
|
| Intent | Artifact type | Route to |
|
|
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -----------------------------| ---------------------------------|
|
|
| A reusable capability or workflow the agent should load inline in the main conversation — triggered automatically by description-matching, not a fresh context, and free to bundle its own `references/`, `scripts/`, or `assets/` | Skill | `kyberforge:skill-author` |
|
|
| A recurring task needs its own reusable agent/subagent definition — dedicated system prompt, tools, and description, invokable by name across sessions | Agent / subagent definition | `kyberforge:agent-author` |
|
|
| A new distributable unit is needed — no existing plugin is the right home for the skill/agent/hook/MCP server being built, or the bundle needs its own manifest, versioning, and install lifecycle separate from what already exists | Plugin | `kyberforge:plugin-author` |
|
|
| The plugin itself already exists (or was just created) and only its marketplace-facing metadata needs to change — listing it for the first time, or updating its version/description entry — never the plugin's contents | Marketplace entry | `kyberforge:marketplace-author` |
|
|
|
|
If the intent is genuinely ambiguous between rows even after grilling, ask the user directly rather than guessing.
|
|
|
|
Note: `kyberforge:plugin-author` and `kyberforge:marketplace-author` are deprecated per ADR-0015, superseded by `apm-workflow` — pending issue #90, so routing to them is unchanged for now.
|
|
|
|
This table classifies what to build, not how to run it — a one-off task that merely needs an isolated vs. context-inheriting run (rather than a new, reusable definition) isn't an artifact at all; there's nothing here to route it to.
|
|
|
|
## Step 3 — Announce, then route
|
|
|
|
State the classification and which skill(s) will run before invoking anything.
|
|
|
|
**Invoking the author skill(s).** Default to a fork subagent — it inherits the full grilled-intent conversation, so the author skill doesn't need to be re-briefed. Fall back to an inline invocation (same conversation, no subagent) when either is true:
|
|
- **Fork is technically unavailable** — already running inside a fork (a fork cannot spawn another fork), a nesting-depth cap is reached, or the environment doesn't support forking.
|
|
- **The routed flow needs live user interaction mid-run** that a backgrounded fork can't surface in real time — clarifying questions, confirmation checkpoints, or a HITL gate (e.g. `plugin-author`'s release step). Judge this from context: if nothing about the routed flow signals a live checkpoint, prefer the fork subagent.
|
|
|
|
`plugin-author` and `marketplace-author` routes always run inline — their flows are short, prompt-heavy, or gated, and get no follow-up audit-recheck step to justify running detached (see below).
|
|
|
|
**After a skill or agent route finishes.** `skill-author` and `agent-author` already close out with their own inline audit (`skill-author` runs `/skill-audit`, `agent-author` invokes `kyberforge:agent-audit` directly) in the same context as the authoring work — that's unchanged. Once that author skill's run has finished, spin up a separate **clean-context subagent** (fresh, not forked, no inherited context) to independently re-run the same audit skill against the finished artifact. This is a distinct verification layer, not a duplicate: the inline audit shares context with the work it's checking and can share its blind spots, while the clean rerun has no stake in the result.
|
|
|
|
If the clean audit surfaces any unresolved finding — not only a disagreement with the inline pass, any actionable finding on its own — loop: re-invoke the author skill (same fork-vs-inline judgment as the initial invocation) to resolve it, then re-run the clean audit again. Repeat until the clean audit comes back with nothing unresolved. Only then is the route done — the same resolve-before-close discipline `skill-author`/`agent-author` already apply to their own inline audit.
|
|
|
|
When the intent spans multiple artifact types (e.g. a new skill inside a new plugin, then registering that plugin via `kyberforge:marketplace-author`), chain the routes in dependency order — an artifact that must exist on disk before another skill can target it goes first (e.g. `plugin-author` creates the plugin directory before `skill-author` scaffolds a skill inside it).
|
|
|
|
## Step 4 — Bump plugin version (if applicable)
|
|
|
|
After the routed skill finishes, check if the artifact was created or updated inside a plugin directory (any directory containing a `plugin.json`).
|
|
|
|
**Skip this step if:**
|
|
- The artifact is standalone (not in any plugin) or scoped to user agent directories
|
|
- The author skill already bumped the plugin version (check the skill's audit output or completion message for version bump evidence)
|
|
|
|
**If the artifact is in a plugin and no version bump was done:**
|
|
|
|
Invoke `kyberforge:plugin-author` as a **clean-context subagent** (fresh, not forked) with this brief:
|
|
|
|
> "The plugin at `<plugin-path>` gained a new `<artifact-type>` (`<artifact-name>`). Run the UPDATE flow to bump `version` in both manifests (Copilot and CC). Determine whether to bump minor (0.1.0) or patch (0.0.1) based on whether this is a new capability (minor) or a fix/refactor (patch). Do not release or tag — just update the manifests and commit."
|
|
|
|
Use a clean-context subagent (not forked) so the version bump decision is made independently without anchoring to the earlier authoring context. This gives plugin-author a clear, isolated directive.
|
|
|
|
Report completion to the user: "Updated `<plugin-name>` version from X.Y.Z to X.Y.Z to reflect the new `<artifact-name>`."
|