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/askidmobile-create-spec-implement
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.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/create-spec-implement
What's inside
- Skill name
create-spec-implement- Description
- Phase-by-phase plan implementation. Takes one phase, implements it, validates, records progress. Describes DOING — one phase at a time.
- License
- MIT
- Instructions
- 269 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Phase-by-phase Plan Implementer (IMPLEMENT) You are a senior engineer. Your task is to implement one phase of the plan: **$ARGUMENTS** > **Implementation = one phase at a time. Write code, verify, record.** > Input is an approved plan from `docs/plans/`. ## PHASE 1: Recon (SILENT, no output) ### 1.1. Find the plan If `$ARGUMENTS` contains a file path → read it. If `$ARGUMENTS` is a name → find it: ``` Glob: docs/plans/*$ARGUMENTS* ``` If not found → show the list: `ls docs/plans/` and suggest `/create-spec-plan <name>`. ### 1.2. Determine progress Read the plan in full. For each phase, determine status: - ✅ **Completed** — all `[x]` in the checklist - 🔄 **In progress** — some `[x]`, some `[ ]` - ⬜ **Not started** — all `[ ]` ### 1.3. Find the linked spec Read the `**Specification:**` field in the plan → load the linked spec from `docs/specs/`. ### 1.4. Check for unresolved questions Read the "Deferred questions" section in both the plan and the spec. For each entry: - If `When the answer is needed` points to the CURRENT plan phase or earlier → that question **blocks** implementation. Add to the queue. - If the entry concerns a phase that's NOT selected right now — skip, you'll deal with it on the next `/create-spec-implement` call for that phase. If the queue is non-empty — ask the questions **one at a time** via `AskUserQuestion` (see [interactive questions rules](#interactive-questions-rules-shared-block)). After each answer: 1. Open the source file (plan or spec) and move the entry from "Deferred" to "Plan decisions" / "Spec decisions". 2. If the answer changes the phase's tasks — update the phase's checklist in the plan. Don't advance to Phase 2 until the queue is empty. ### 1.5. Pre-flight 1. Read the brief's **Principles** (`docs/brief/PROJECT-BRIEF.md`, if present) — they bind implementation choices too. 2. Verify the toolchain runs on the **current** tree before touching code: the project's check command (`cargo check` / `tsc --noEmit` / equivalent) and test runner. A broken baseline → report and stop; fixing pre-existing breakage is not part of the phase (offer it as a separate task). ## PHASE 2: Phase selection Show the user **in a single message**: ``` 📋 Plan: [Plan name] 📄 Spec: [path to spec] Phase progress: ✅ Phase 1: [Name] — completed 🔄 Phase 2: [Name] — in progress (3/5 tasks) ⬜ Phase 3: [Name] — not started ⬜ Phase 4: [Name] — not started → Proposing: Phase N — [Name] (estimate: X h) Tasks: - [ ] Task 1 - [ ] Task 2 - ... ``` If the user specified a phase number in `$ARGUMENTS` → propose that one. Otherwise → propose the next unfinished one (the first ⬜ or 🔄). If the user specified a different phase — wait for their input. Otherwise, proceed automatically. ## PHASE 3: Loading context (SILENT, no output) After phase confirmation: ### 3.1. Phase files Read ALL files listed in the selected phase's tasks (paths from the checklist `→ path/to/file`). ### 3.2. Related requirements In the "Traceability: Requirements → Tasks" table, find which FR-XXX this phase covers. Read those requirements in the spec. ### 3.3. Project patterns Study analogous implementations in the codebase — how similar modules, error handling, tests are organized. ## PHASE 4: Approval checkpoint Show the user **in a single message** the attack plan: ``` 🎯 Phase N: [Name] Covers requirements: FR-001, FR-002, ... Tasks: 1. [Task] → `path/to/file` Approach: [brief description of what and how we change] 2. [Task] → `path/to/file` Approach: [brief description] ... Validation after implementation: - [ ] cargo check / tsc --noEmit (compilation) - [ ] [Relevant tests] - [ ] [Manual check if needed] ``` Proceed to implementation automatically after displaying this plan. If the user wants to adjust — they will interrupt.
From askidmobile/ai-spec-kit, MIT.
More from askidmobile/ai-spec-kit
- 0.525score
task-tracker
askidmobile
Manage project tasks in TASKS.md.
SkillBFreshness: BClaude Code +9 - 0.521score
wiki-compiler
askidmobile
Core compilation algorithm for the LLM Wiki Compiler.
SkillBFreshness: BClaude Code +9 - 0.521score
create-spec
askidmobile
Create a technical specification for a new feature or task.
SkillBFreshness: BClaude Code +9 - 0.521score
create-spec-plan
askidmobile
Create a detailed implementation plan based on an approved specification.
SkillBFreshness: BClaude Code +9 - 0.521score
create-spec-review
askidmobile
Post-implementation retrospective.
SkillBFreshness: BClaude Code +9 - 0.520score
project-brief
askidmobile
Coverage-driven project brief engine.
SkillBFreshness: BClaude Code +9 - 0.518score
wiki-visualize
askidmobile
Launch a local interactive knowledge-graph visualization of the compiled wiki.
SkillBFreshness: BClaude Code +9 - 0.518score
wiki-init
askidmobile
Interactive setup of .wiki-compiler.json — mode, sources, output, article sections.
SkillBFreshness: BClaude Code +9 - 0.518score
wiki-migrate
askidmobile
One-time migration — replace raw file reads in the CLAUDE.md/AGENTS.md startup sequence with wiki articles.
SkillBFreshness: BClaude Code +9 - 0.518score
wiki-query
askidmobile
Answer a question from the compiled wiki instead of scanning raw source files.
SkillBFreshness: BClaude Code +9 - 0.518score
wiki-upgrade
askidmobile
Update the installed ai-spec-kit — git pull for symlink installs, reinstall for copies.
SkillBFreshness: BClaude Code +9 - 0.518score
commit
askidmobile
Commit and push in one go — reviews status and diff, writes a conventional commit message in the repo's style.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 9, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/askidmobile/ai-spec-kit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from askidmobile
- 0.525score
task-tracker
askidmobile
Manage project tasks in TASKS.md.
SkillBFreshness: BClaude Code +9 - 0.521score
wiki-compiler
askidmobile
Core compilation algorithm for the LLM Wiki Compiler.
SkillBFreshness: BClaude Code +9 - 0.521score
create-spec-plan
askidmobile
Create a detailed implementation plan based on an approved specification.
SkillBFreshness: BClaude Code +9 - 0.521score
create-spec-review
askidmobile
Post-implementation retrospective.
SkillBFreshness: BClaude Code +9 - 0.521score
create-spec
askidmobile
Create a technical specification for a new feature or task.
SkillBFreshness: BClaude Code +9 - 0.520score
project-brief
askidmobile
Coverage-driven project brief engine.
SkillBFreshness: BClaude Code +9
Cite this page
create-spec-implement skill. Agent Mart. https://agentmart.dev/skills/askidmobile-create-spec-implement (last updated 2026-10-24)