Token导航 LogoToken导航

Agent Skill · 开发

spec-kitty-workflow(规格小猫工作流程)

spec-kitty-workflow 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

spec-kitty-workflow 是开发类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在开发类的 21,746 个 Skill 里排第 21,707。

总安装 24周安装 1GitHub Stars 2下载 8核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:spec-kitty-workflow(规格小猫工作流程)
来源仓库:https://github.com/richfrem/agent-plugins-skills
仓库路径:skills/spec-kitty-workflow
安装命令:
npx skills add https://github.com/richfrem/agent-plugins-skills --skill spec-kitty-workflow
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/richfrem/agent-plugins-skills --skill spec-kitty-workflow

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

spec-kitty-workflow 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中进行协作事项整理。适用于围绕仓库状态、代码变更或协作事项进行信息组织和梳理的场景。

支持对 GitHub 相关协作内容进行分类、标记和状态跟踪。安装命令:npx skills add https://github.com/richfrem/agent-plugins-skills --skill spec-kitty-workflow 建议确认权限范围和维护状态,注意可能触发联网或文件读写操作

来源仓库内路径:skills/spec-kitty-workflow

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/richfrem/agent-plugins-skills --skill spec-kit…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

spec-kitty-workflow 怎么安装?

在终端执行 npx skills add https://github.com/richfrem/agent-plugins-skills --skill spec-kitty-workflo…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

spec-kitty-workflow 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

spec-kitty-workflow 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

spec-kitty-workflow 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

spec-kitty-workflow 用的人多吗?

公开数据是累计安装 24 次,近一周安装 1 次,下载 8 次,GitHub 2 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

spec-kitty-workflow 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理开发类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
spec-kitty-workflow

规格小猫工作流程 · 本页

242只读未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Dependencies

This skill requires Python 3.8+ and standard library only. No external packages needed.

To install this skill's dependencies:

pip-compile ./requirements.in
pip install -r ./requirements.txt

See ./requirements.txt for the dependency lockfile (currently empty — standard library only).


Spec Kitty Workflow

Standard lifecycle for implementing features using Spec Kitty.

Command-specific guidance: For detailed best practices on individual commands, see the AUGMENTED.md files co-located with each auto-synced command:

  • references/AUGMENTED.md — pre-merge safety, branch protection, conflict resolution
  • references/AUGMENTED.md — worktree discipline, commit hygiene
  • references/AUGMENTED.md — review standards, batch review protocol

🚫 CRITICAL: Anti-Simulation Rules & Escalation Taxonomy

YOU MUST ACTUALLY RUN EVERY COMMAND LISTED BELOW. Describing what you "would do", summarizing expected output, or marking a step complete without pasting real tool output is a PROTOCOL VIOLATION. Proof = pasted command output. No output = not done.

Escalation Taxonomy (Protocol Violation Response)

If you detect a tool or user attempting to bypass the closure protocol or manually create spec files, you MUST interrupt the workflow using the strict 5-step Escalation Protocol:

  1. Stop: Halt workflow creation immediately.
  2. Alert: Loudly print: 🚨 PROTOCOL VIOLATION 🚨.
  3. Explain: State precisely which rule was broken (e.g., "Cannot skip review.").
  4. Recommend: Output the standard operating procedure (e.g., "Please submit WP-xx for review: spec-kitty review WP-xx").
  5. Draft: Refuse to execute the dangerous command until the state is fixed.

Anti-Pattern Vaccination (Known Agent Failure Modes)

  1. Checkbox theater: Marking [x] without running the command or verification tool
  2. Manual file creation: Writing spec.md/plan.md/tasks.md by hand instead of using CLI
  3. Kanban neglect: Not updating task lanes, so dashboard shows stale state
  4. Closure amnesia: Finishing code but skipping review/merge/closure steps
  5. Phase skipping: Advancing from specify -> plan -> tasks -> implement without user approval at each gate (see Human Gate below)

🔴 THE HUMAN GATE (Constitutional Supreme Law)

NEVER advance between phases without EXPLICIT user approval. Approval means: "Proceed", "Go", "Execute", or equivalent affirmative command. "Sounds good", "Looks right", "That's correct" are NOT approval. VIOLATION = SYSTEM FAILURE

Required Approval Gates

GateAfterBeforeWhat to Show User
Gate 0You write s specPlanning any planShow spec.md, ask for approval
Gate 1User approves specYou write a planShow plan.md, ask for approval
Gate 2User approves planYou generate tasks/WPsShow tasks.md + WP list, ask for approval
Gate 3User approves tasksYou run spec-kitty implementConfirm WP scope, ask to proceed
Gate 4WP implementation doneYou move to for_reviewShow what was built, ask for review

Gate Enforcement Rule (MANDATORY)

After each phase-generating step:

  1. STOP - Do not run the next phase command
  2. SHOW - Present the artifact to the user
  3. WAIT - End your turn with explicit request for approval
  4. PROCEED only on explicit approval word ("Proceed", "Go", "Execute")
❌ WRONG: spec -> plan -> tasks -> implement (all in one agent turn)
✅ RIGHT: spec -> [STOP, show spec, wait] -> plan -> [STOP, show plan, wait] -> tasks

0. Mandatory Planning Phase (Do NOT Skip)

Before implementing any code, you MUST generate artifacts using the CLI. Manual creation of spec.md, plan.md, or tasks/ files is STRICTLY FORBIDDEN.

Pre-Execution Workflow Commitment

Visual Reference: pure-spec-kitty-workflow.mmd This diagram shows the full lifecycle including all HITL Gate nodes (red diamonds) where agent execution MUST stop and wait for user approval before advancing.

Before starting, display the following visual map to commit to the workflow state:

┌────────────────────────────────────────────────────────┐
│               SPEC-KITTY LIFECYCLE MAP                 │
├────────────────────────────────────────────────────────┤
│ [ ] Phase 0: Plan (specify -> plan -> tasks)           │
│ [ ] Phase 1: Implement (implement WP -> code -> review)│
│ [ ] Phase 2: Close (accept -> retro -> merge -> sync)  │
└────────────────────────────────────────────────────────┘

*Check the box corresponding to your current execution phase.*

Step 0a: Specify

To specify a feature, read the workflow instructions in .windsurf/workflows/spec-kitty.specify.md or use the CLI:

spec-kitty agent feature create-feature "<slug>"

PROOF: Paste output confirming spec.md was generated.

⛔ HUMAN GATE 0: Show the user spec.md and STOP. Do NOT proceed to plan until the user explicitly approves with "Proceed", "Go", or "Execute".

Step 0b: Plan

To plan a feature, read the workflow instructions in .windsurf/workflows/spec-kitty.plan.md or use the CLI:

spec-kitty agent feature setup-plan --feature <SLUG>

PROOF: Paste output confirming plan.md was generated.

⛔ HUMAN GATE 1: Show the user plan.md and STOP. Do NOT proceed to task generation until the user explicitly approves.

Step 0c: Tasks

To generate tasks, read the workflow instructions in .windsurf/workflows/spec-kitty.tasks.md.

/spec-kitty.tasks

PROOF: Paste output confirming tasks.md and WP files were generated.

⛔ HUMAN GATE 2: Show the user tasks.md (the WP breakdown) and STOP. Do NOT run spec-kitty implement until the user explicitly approves.

1. Start a Work Package (WP)

Step 1a: Create worktree

spec-kitty agent workflow implement --task-id <WP-ID> --agent "<AGENT-NAME>"

PROOF: Paste the output. Extract the worktree path from it.

If output is truncated or unclear:

git worktree list

CRITICAL: Do NOT guess the path. Verify it exists before proceeding.

Step 1b: Update kanban

python3 .kittify/scripts/tasks/tasks_cli.py update <FEATURE-SLUG> <WP-ID> doing --note "Starting implementation"

PROOF: Paste the CLI output confirming lane change.

Then verify the board:

/spec-kitty.status

PROOF: Paste the kanban board. Confirm your WP shows in "doing" lane. STOP: Do NOT start coding until the kanban shows the WP in "doing".


2. Implementation Loop

  1. Navigate: cd.worktrees/<WP-ID> — verify with pwd
  2. Setup: Install dependencies if needed
  3. Code: Implement the feature
  4. Test: Run tests or manual verification
  5. Commit: git add. && git commit -m "feat(<WP>): description" (local worktree)

3. Review & Handover

Pre-Review Checklist (verify ALL before proceeding)

  • All files committed in worktree (git status shows clean)
  • Worktree path confirmed (pwd matches .worktrees/<WP-ID>)
  • WP lane is doing (not already for_review or done)
  • No untracked files that should be committed

Step 3a: Verify clean state

Run git status to ensure all files are committed. PROOF: Paste the output. Must show "nothing to commit, working tree clean". STOP: Do NOT proceed if there are uncommitted changes.

Step 3b: Update kanban to for_review

python3 .kittify/scripts/tasks/tasks_cli.py update <FEATURE-SLUG> <WP-ID> for_review --note "Implementation complete, ready for review"

PROOF: Paste the CLI output.

Step 3c: Verify kanban updated

/spec-kitty.status

PROOF: Paste the board. WP must show in "for_review" lane.

Step 3d: Sync specs in main repo

cd <PROJECT_ROOT>
git add kitty-specs
git commit -m "docs(specs): mark <WP-ID> complete"

4. Deterministic Closure Protocol

CRITICAL: Every step below is MANDATORY. Skipping any step is a protocol violation. The closure chain is: Review → Accept → Retrospective → Merge → Verify → Intel Sync

Step 4a: Review each WP

spec-kitty agent workflow review --task-id <WP-ID>

PROOF: Paste the review output. WP must move to done lane.

Repeat for each WP. Verify all WPs are in done lane:

/spec-kitty.status

PROOF: Paste the board. ALL WPs must show in "done" lane before proceeding.

Step 4b: Accept feature

cd <PROJECT_ROOT>
spec-kitty accept --feature <SLUG>

The agent will ask for acceptance mode:

  • --mode local: Merge locally (no branch protection on target)
  • --mode pr: Push to feature branch and create PR (for protected branches)
  • --mode checklist: Readiness check only, no merge

PROOF: Paste the JSON output showing summary.ok: true.

Known Issue: Accept may fail with "missing shell_pid in WP frontmatter". Fix: Add shell_pid: N/A to the WP frontmatter, or use --lenient flag: ``bash spec-kitty accept --mode local --feature <SLUG> --lenient ``

STOP: Do NOT proceed if accept fails. Resolve all outstanding issues first.

Step 4c: Retrospective (MANDATORY)

/spec-kitty_retrospective

PROOF: Paste confirmation that kitty-specs/<SPEC-ID>/retrospective.md was created/updated.

This step is NOT optional. Every feature closure MUST include a retrospective. The retrospective file MUST exist in kitty-specs/<SPEC-ID>/ before merge.

Step 4d: Pre-merge remote backup (MANDATORY)

⚠️ DATA SAFETY: Before ANY merge or worktree cleanup, ALL WP branches MUST be pushed to GitHub origin and verified. This prevents data loss if the merge fails or worktrees are deleted before content is preserved.

Push each WP branch to origin:

cd <PROJECT_ROOT>
for wt in .worktrees/<FEATURE>-WP*/; do
  branch=$(basename "$wt")
  echo "Pushing $branch..."
  git -C "$wt" push origin "$branch"
done

PROOF: Paste push output for each branch.

Verify remote state:

for wt in .worktrees/<FEATURE>-WP*/; do
  branch=$(basename "$wt")
  local_sha=$(git -C "$wt" rev-parse HEAD)
  remote_sha=$(git ls-remote origin "$branch" | cut -f1)
  if [ "$local_sha" = "$remote_sha" ]; then
    echo "✅ $branch: verified on origin ($local_sha)"
  else
    echo "❌ $branch: MISMATCH (local=$local_sha remote=$remote_sha)"
  fi
done

PROOF: Paste verification output. ALL branches must show ✅. STOP: Do NOT proceed to merge if any branch shows ❌.

⚠️ RESEARCH/PLANNING FILES IN WORKTREE: Any files created under kitty-specs/ INSIDE a worktree directory are physically located in the worktree's filesystem only. When spec-kitty merge runs git worktree remove, ALL untracked files in that directory are permanently deleted. You MUST sync them to the main checkout first: ``bash rsync -av --ignore-existing \ .worktrees/<FEATURE>-WP01/kitty-specs/<FEATURE>/research/ \ kitty-specs/<FEATURE>/research/ git add kitty-specs/<FEATURE>/ git commit -m "docs: sync research artifacts from worktree to main before merge" ` Also: kitty-specs/` is blocked by the pre-commit hook on WP branches. It can ONLY be committed from the main/target branch. This is by design.

Step 4e: Pre-merge safety check (deterministic forecasting)

cd <PROJECT_ROOT>
git status
git worktree list
spec-kitty merge --feature <SLUG> --dry-run --json

PROOF: Paste all outputs. From the JSON, verify:

  • You are in the main repo root (NOT inside a worktree)
  • git status shows clean working tree
  • effective_wp_branches lists only the branches that need merging
  • all_wp_branches may be larger than effective_wp_branches (expected)
  • No conflict warnings in the output
v1.0.1 Feature: The --dry-run --json flag outputs a deterministic merge plan showing exactly which branches will be merged. Confirm the effective tips before proceeding.

Step 4f: Merge from main repo

cd <PROJECT_ROOT>
spec-kitty merge --feature <SLUG> --push
ALWAYS use --push to ensure merged main is immediately backed up to origin. Without --push, worktree cleanup can destroy the only copies of feature branches.
LOCATION RULE: ALWAYS run merge from the main repository root. NEVER cd into a worktree to merge. The @require_main_repo decorator will block execution from worktrees.

If merge fails mid-way:

spec-kitty merge --feature <SLUG> --resume

PROOF: Paste the merge output showing success.

Step 4f: Post-merge verification

git log --oneline -5
git worktree list
git branch
git status
rm -f .kittify/workspaces/<SLUG>-WP*.json

PROOF: Paste all outputs. Verify:

  • Merge commit(s) visible in log
  • No orphaned worktrees remain for this feature
  • WP branches have been deleted
  • Working tree is clean
  • Workspace tracking JSONs removed from .kittify/workspaces/
  1. 2. Step 4g: Update kanban to done
python3 .kittify/scripts/tasks/tasks_cli.py update <FEATURE-SLUG> <WP-ID> done --note "Merged and cleaned up"

PROOF: Paste CLI output + final /spec-kitty.status board.


Known Back-End Failure Modes

FailureRoot CauseFix
Merge blocked by @require_main_repoAgent ran merge from inside a worktreecd <PROJECT_ROOT> first, then spec-kitty merge --feature <SLUG>
Accept fails with "missing shell_pid"WP frontmatter missing shell_pid fieldAdd shell_pid: N/A to frontmatter, or use --lenient
Orphaned worktrees after mergeMerge failed mid-cleanupgit worktree remove.worktrees/<WP-FOLDER> then git branch -d <WP-BRANCH>
Lost data during mergeAgent merged from worktree instead of main repoAlways use --feature <SLUG> flag from project root
Retrospective skippedAgent treated it as optionalRetrospective file must exist before merge is allowed
No closure state recordedNo post-merge verification stepRun Step 4f verification checklist
Merge preflight: "uncommitted changes" despite restored tracked filesspec-kitty uses git status --porcelain which includes ?? untracked filesRun git stash -u before merge, then git stash pop after
Research/planning files deleted when worktree removedUntracked files in worktree physical dir are deleted by git worktree removeCopy files to main checkout before merge: rsync -av --ignore-existing.worktrees/<WP>/kitty-specs/ kitty-specs/ then commit on main
spec-kitty can't read WP lane for skeleton WPsWP files without YAML frontmatter (---) are invisible to spec-kitty lane trackingAdd minimal frontmatter: ---\nlane: "planned"\ndependencies: []\nbase_branch: main\n---
Accept fails: unchecked tasks in tasks.md- [] items anywhere in tasks.md block accept even with --lenientRun sed -i '' 's/- \[\]/- [x]/g' kitty-specs/<FEATURE>/tasks.md
accept --actor or --test flags rejectedThese flags are NOT supported by spec-kitty agent feature accept CLIUse only: `--feature SLUG --mode local
Path violations: research/data/findings/reports not foundresearch mission requires these dirs in feature dirCreate at planning time: mkdir -p kitty-specs/<FEATURE>/{research,data,findings,reports} && touch kitty-specs/<FEATURE>/{data,findings,reports}/.gitkeep

5. Dual-Loop Mode (Protocol 133)

When Spec Kitty runs inside a Dual-Loop session, roles are split:

StepWhoAction
Specify/Plan/TasksOuter Loop (Antigravity)Generates all artifacts
ImplementOuter Loop creates worktree, then Inner Loop codesInner Loop receives Strategy Packet
Review/MergeOuter LoopVerifies output, commits, merges

Inner Loop constraints:

  • No git commands — Outer Loop owns version control
  • Scope limited to the Strategy Packet — no exploratory changes
  • If worktree is inaccessible, may implement on feature branch (fallback — log in friction log)

Cross-reference: dual-loop skill


6. Task Management CLI

The tasks CLI manages WP lane transitions. Always use this instead of manually editing frontmatter or checkboxes.

# Move a WP between lanes (planned -> doing -> for_review -> done)
python3 .kittify/scripts/tasks/tasks_cli.py update <FEATURE-SLUG> <WP-ID> <LANE> --note "reason"

# Force-move (when kitty-specs artifacts leak from serial implementation)
python3 .kittify/scripts/tasks/tasks_cli.py update <FEATURE-SLUG> <WP-ID> done --force --note "reason"

# View kanban board
/spec-kitty.status

# Accept feature readiness
spec-kitty accept --feature <FEATURE-SLUG>

# Validate encoding (prevents dashboard blank pages)
spec-kitty validate-encoding --feature <FEATURE-SLUG>
spec-kitty validate-encoding --feature <FEATURE-SLUG> --fix

Valid lanes: planned, doing, for_review, done

Dashboard: /spec-kitty.dashboard reads lane data from WP frontmatter.


Common Issues

  • "Base workspace not found": WP depends on a merged WP. Create worktree off main: git worktree add.worktrees/<WP-FOLDER> main cd.worktrees/<WP-FOLDER> git checkout -b <WP-BRANCH-NAME>
  • "Already on main": Merge commands must run from project root, not inside a worktree.
  • Kanban not updating: Verify you're using the CLI, not manually editing frontmatter.

平台分布

Codex

38.89%
按下载量换算3

Claude

29.32%
按下载量换算2

Cursor

18.85%
按下载量换算2

Gemini CLI

10.17%
按下载量换算1

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills