zagrosi-forge
Take a software request through the appropriate Forge workflow, from a brief or existing plan to verified code. Use for end-to-end feature work, fixes, or continuing Forge work in Codex or Claude Code.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1.6k
- Forks
- 491
01 前言 Front Matter
- name
- zagrosi-forge
- description
- Take a software request through the appropriate Forge workflow, from a brief or existing plan to verified code. Use for end-to-end feature work, fixes, or continuing Forge work in Codex or Claude Code.
- allowed-tools
- [ "Bash(python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/zagrosi_skills.py\" team status *)", "Bash(python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/zagrosi_skills.py\" status *)", "Bash(python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/zagrosi_skills.py\" next-section *)", "Bash(python \"${CLAUDE_PLUGIN_ROOT}/scripts/zagrosi_skills.py\" team status *)", "Bash(python \"${CLAUDE_PLUGIN_ROOT}/scripts/zagrosi_skills.py\" status *)", "Bash(python \"${CLAUDE_PLUGIN_ROOT}/scripts/zagrosi_skills.py\" next-section *)", "Bash(py -3 \"${CLAUDE_PLUGIN_ROOT}/scripts/zagrosi_skills.py\" team status *)", "Bash(py -3 \"${CLAUDE_PLUGIN_ROOT}/scripts/zagrosi_skills.py\" status *)", "Bash(py -3 \"${CLAUDE_PLUGIN_ROOT}/scripts/zagrosi_skills.py\" next-section *)" ]
02 资源文件 3
- 参考文档agents/openai.yaml267 B
- 参考文档references/collaboration.md8.2 KB
- 参考文档references/providers.md8.1 KB
03 SKILL.md 正文
Forge
For a Git target, check team status --target-dir "{target_dir}" with Forge’s
helper before work or resume.
Follow team coordination when configured or unavailable;
reuse the same task across phases and delegated agents.
Resolve absolute plugin_root: the plugin directory two levels above this skill's
folder, containing scripts/zagrosi_skills.py; never the target repo. Claude Code
substitutes it when loading this skill: ${CLAUDE_PLUGIN_ROOT}. Literal text there
means the file was read directly: derive the path; no such shell variable exists.
Run every helper command, including returned argv arrays, with the exact prefix
python3 "{plugin_root}/scripts/zagrosi_skills.py" (Python 3.11+; python or
py -3 on Windows); host pre-approvals match that text.
Choose the shortest route that completes the user's request. Inspect repository instructions, the working tree, relevant callers/tests, and any existing Forge artifacts before creating new ones. Preserve unrelated work.
Route once
| Starting point | Load |
|---|---|
| Several independent products or planning units | Project, then each ready unit |
| Feature, bug, or coherent change without an admitted plan | Plan, then Implement |
| Unfinished or unadmitted plan | Plan; finish its existing contract |
| Admitted plan or interrupted implementation | Implement; resume persisted progress |
| Simplify a repository or remove accumulated bad code | Cleanup |
Load a phase by invoking its skill, such as zagrosi-forge:zagrosi-plan, where the
host supports skill invocation; otherwise read and follow its SKILL.md.
For a small change, keep one compact section; do not split it into a project.
Use lean unless the user requests standard/deep or material risk warrants
more investigation. Explain a depth change briefly. Every depth preserves the
same behavior, ownership, and verification obligations. State-first
lean is opt-in: use it only when the user asks or status.json already exists.
An implementation request authorizes moving through planning and implementation; continue without asking again at each phase. A plan, audit, or review-only request stops at that deliverable. Ask only about unresolved decisions that materially affect the result. Existing user authorization governs commits and publication.
Quality and review
Apply the shared engineering standard throughout. Repair encountered bad code within the task's execution path, with before/after behavioral checks. Before delivery, review the changed code and relevant callers once for unnecessary complexity and regressions. Record broader debt separately instead of expanding a completed PR indefinitely.
When the user requests multiple providers/models, or another provider's perspective addresses a concrete risk, use provider reviews. Keep one primary writer and consolidate findings into the existing review. Never substitute another provider/model silently or treat reviewer agreement as proof that tests pass.
Finish with the result, actual verification, remaining limitations, and the saved artifact location. Distinguish code completion, PR/CI state, and deployment.
04 同仓库更多 Skills
worktable-review-with-annotations
Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.
worktable-find-and-synthesize-context
Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.
worktable-create-or-update-docs
Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.
worktable-create-or-manage-records
Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.
worktable-create-or-manage-interactive-html
Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.
worktable-collaborate-threads
Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.