speckit-implement

Imported from iamrgalisanao/itrack (.claude/skills/speckit-implement/SKILL.md). Install upstream with npx skills add iamrgalisanao/itrack --skill speckit-implement. Copyright stays with the author.

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty).

Pre-Execution Checks

Check for extension hooks (before implementation):

• Check if .specify/extensions.yml exists in the project root.
• If it exists, read it and look for entries under the hooks.before_implement key
• If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normally
• Filter out hooks where enabled is explicitly false. Treat hooks without an enabled field as enabled by default.
• For each remaining hook, do not attempt to interpret or evaluate hook condition expressions:
  • If the hook has no condition field, or it is null/empty, treat the hook as executable
  • If the hook defines a non-empty condition, skip the hook and leave condition evaluation to the HookExecutor implementation
• When constructing slash commands from hook command names, replace dots (.) with hyphens (-). For example, speckit.git.commit → /speckit-git-commit.
• For each executable hook, output the following based on its optional flag:
  • Optional hook (optional: true):

    ## Extension Hooks
    
    **Optional Pre-Hook**: {extension}
    Command: `/{command}`
    Description: {description}
    
    Prompt: {prompt}
    To execute: `/{command}`
    

  • Mandatory hook (optional: false):

    ## Extension Hooks
    
    **Automatic Pre-Hook**: {extension}
    Executing: `/{command}`
    EXECUTE_COMMAND: {command}
    
    Wait for the result of the hook command before proceeding to the Outline.
    

    After emitting the block above you MUST actually invoke the hook and wait for it to finish before continuing. Run it the same way you would run the command yourself in this agent/session (the invocation may differ from the literal {command} id shown above, e.g. a skills-mode agent runs it as /skill:speckit-... or $speckit-...). Emitting the block alone does not run the hook.
• If no hooks are registered or .specify/extensions.yml does not exist, skip silently

Outline

1. Run .specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'''m Groot' (or double-quote if possible: "I'm Groot").

2. Check checklists status (if FEATURE_DIR/checklists/ exists):

   • Scan all checklist files in the checklists/ directory

   • For each checklist, count:

     • Total items: All lines matching - [ ] or - [X] or - [x]
     • Completed items: Lines matching - [X] or - [x]
     • Incomplete items: Lines matching - [ ]

   • Create a status table:

     | Checklist | Total | Completed | Incomplete | Status |
     |-----------|-------|-----------|------------|--------|
     | ux.md     | 12    | 12        | 0          | ✓ PASS |
     | test.md   | 8     | 5         | 3          | ✗ FAIL |
     | security.md | 6   | 6         | 0          | ✓ PASS |

   • Calculate overall status:

     • PASS: All checklists have 0 incomplete items
     • FAIL: One or more checklists have incomplete items

   • If any checklist is incomplete:

     • Display the table with incomplete item counts
     • STOP and ask: "Some checklists are incomplete. Do you want to proceed with implementation anyway? (yes/no)"
     • Wait for user response before continuing
     • If user says "no" or "wait" or "stop", halt execution
     • If user says "yes" or "proceed" or "continue", proceed to step 3

   • If all checklists are complete:

     • Display the table showing all checklists passed
     • Automatically proceed to step 3

3. Load and analyze the implementation context:

   • REQUIRED: Read tasks.md for the complete task list and execution plan
   • REQUIRED: Read plan.md for tech stack, architecture, and file structure
   • IF EXISTS: Read data-model.md for entities and relationships
   • IF EXISTS: Read contracts/ for API specifications and test requirements
   • IF EXISTS: Read research.md for technical decisions and constraints
   • IF EXISTS: Read .specify/memory/constitution.md for governance constraints
   • IF EXISTS: Read quickstart.md for integration scenarios

3a. Precondition: Software Architect verification gate on this plan. /speckit-plan's step 7 requires plan.md to carry a ## Software Architect Verification section recording that gate's outcome. Check it now, before touching any task:

• Section absent, or present but not recording PASSED (clean) or PASSED (accepted exceptions): this plan has not cleared review (predates the gate, was interrupted mid-iteration, or is genuinely unresolved). STOP. Do not execute any task. Tell the user the plan needs the Software Architect gate run (or resumed) via /speckit-plan before implementation can start, and offer to run that verification now (dispatch the Software Architect subagent per speckit-plan step 7, iterating revise → re-verify the same way, then write the section into plan.md) rather than silently proceeding.
• Section present and PASSED: proceed to step 4. If it recorded accepted exceptions, treat those exact exceptions as known/expected — do not re-litigate them as new Code Reviewer findings in step 10 unless the implementation touches the excepted area differently than what was accepted.
• This check exists so a plan that was never actually reviewed (or whose review never converged) cannot silently reach implementation just because tasks.md happens to exist.

4. Project Setup Verification:

   • REQUIRED: Create/verify ignore files based on actual project setup:

   Detection & Creation Logic:

   • Check if the following command succeeds to determine if the repository is a git repo (create/verify .gitignore if so):

     git rev-parse --git-dir 2>/dev/null

   • Check if Dockerfile* exists or Docker in plan.md → create/verify .dockerignore

   • Check if .eslintrc* exists → create/verify .eslintignore

   • Check if eslint.config.* exists → ensure the config's ignores entries cover required patterns

   • Check if .prettierrc* exists → create/verify .prettierignore

   • Check if .npmrc or package.json exists → create/verify .npmignore (if publishing)

   • Check if terraform files (*.tf) exist → create/verify .terraformignore

   • Check if .helmignore needed (helm charts present) → create/verify .helmignore

   If ignore file already exists: Verify it contains essential patterns, append missing critical patterns only If ignore file missing: Create with full pattern set for detected technology

   Common Patterns by Technology (from plan.md tech stack):

   • Node.js/JavaScript/TypeScript: node_modules/, dist/, build/, *.log, .env*
   • Python: __pycache__/, *.pyc, .venv/, venv/, dist/, *.egg-info/
   • Java: target/, *.class, *.jar, .gradle/, build/
   • C#/.NET: bin/, obj/, *.user, *.suo, packages/
   • Go: *.exe, *.test, vendor/, *.out
   • Ruby: .bundle/, log/, tmp/, *.gem, vendor/bundle/
   • PHP: vendor/, *.log, *.cache, *.env
   • Rust: target/, debug/, release/, *.rs.bk, *.rlib, *.prof*, .idea/, *.log, .env*
   • Kotlin: build/, out/, .gradle/, .idea/, *.class, *.jar, *.iml, *.log, .env*
   • C++: build/, bin/, obj/, out/, *.o, *.so, *.a, *.exe, *.dll, .idea/, *.log, .env*
   • C: build/, bin/, obj/, out/, *.o, *.a, *.so, *.exe, *.dll, autom4te.cache/, config.status, config.log, .idea/, *.log, .env*
   • Swift: .build/, DerivedData/, *.swiftpm/, Packages/
   • R: .Rproj.user/, .Rhistory, .RData, .Ruserdata, *.Rproj, packrat/, renv/
   • Universal: .DS_Store, Thumbs.db, *.tmp, *.swp, .vscode/, .idea/

   Tool-Specific Patterns:

   • Docker: node_modules/, .git/, Dockerfile*, .dockerignore, *.log*, .env*, coverage/
   • ESLint: node_modules/, dist/, build/, coverage/, *.min.js
   • Prettier: node_modules/, dist/, build/, coverage/, package-lock.json, yarn.lock, pnpm-lock.yaml
   • Terraform: .terraform/, *.tfstate*, *.tfvars, .terraform.lock.hcl
   • Kubernetes/k8s: *.secret.yaml, secrets/, .kube/, kubeconfig*, *.key, *.crt

5. Parse tasks.md structure and extract:

   • Task phases: Setup, Tests, Core, Integration, Polish
   • Task dependencies: Sequential vs parallel execution rules
   • Task details: ID, description, file paths, parallel markers [P]
   • Execution flow: Order and dependency requirements

6. Execute implementation following the task plan:

   • Phase-by-phase execution: Complete each phase before moving to the next
   • Respect dependencies: Run sequential tasks in order, parallel tasks [P] can run together
   • Follow TDD approach: Execute test tasks before their corresponding implementation tasks
   • File-based coordination: Tasks affecting the same files must run sequentially
   • Validation checkpoints: Verify each phase completion before proceeding

7. Implementation execution rules:

   • Setup first: Initialize project structure, dependencies, configuration
   • Tests before code: If you need to write tests for contracts, entities, and integration scenarios
   • Core development: Implement models, services, CLI commands, endpoints
   • Integration work: Database connections, middleware, logging, external services
   • Polish and validation: Unit tests, performance optimization, documentation

8. Progress tracking and error handling:

   • Report progress after each completed task
   • Halt execution if any non-parallel task fails
   • For parallel tasks [P], continue with successful tasks, report failed ones
   • Provide clear error messages with context for debugging
   • Suggest next steps if implementation cannot proceed
   • IMPORTANT For completed tasks, make sure to mark the task off as [X] in the tasks file.

9. Completion validation:

   • Verify all required tasks are completed
   • Check that implemented features match the original specification
   • Validate that tests pass and coverage meets requirements
   • Confirm the implementation follows the technical plan

10. Mandatory Code Reviewer verification of the implementation: After completion validation passes, and before the Post-Execution Hooks and Completion Report, the orchestrating session MUST dispatch a Code Reviewer subagent (Agent tool, subagent_type: "Code Reviewer") to independently review the implemented changes. This is automatic — the user does not need to ask for it.

    • Give the agent the changed surface (the diff of files created/modified during this implementation run — e.g. via git diff/git status against the state before implementation began) plus the paths to spec.md, plan.md, tasks.md, and .specify/memory/constitution.md.
    • Instruct it to review for:
      1. Correctness — the implementation actually satisfies the spec's functional requirements and the plan's design; tests cover the happy path and at least one denied/unauthorized path for anything role-gated (Constitution Principle III).
      2. Access control and tenant isolation — role checks go through the HasRole trait predicates (never inline role-string comparisons, fail-closed), read-scoping uses AccessContext::user($request) / Project::accessibleTo(), and no new query can reach data outside the acting user's accessible projects/organizations (Constitution Principles I and VIII.2–3).
      3. API contracts — endpoints return API Resources or curated arrays, never raw models (Principle II); sensitive mutations are audited via AuditLogger (Principle IV); migrations are additive/nullable (Principle V).
      4. Code quality — conformance with the installed php-best-practices/laravel-best-practices/react-vite-best-practices skills (Principle VII) and absence of AI-slop patterns per the code-slop skill; for any frontend surface, the Frontend Design and Review Governance review criteria apply, including running /impeccable audit <target> and /impeccable critique <target> and folding their findings into this review's classification (Constitution: Mandatory Skill Usage, scoped to Operate mode).
    • Specialist reviewers (Constitution: Specialist Agent Routing): in addition to the Code Reviewer, dispatch the specialist(s) the changed surface requires — Section 508 Accessibility Specialist for any accessibility surface (contrast, ARIA, keyboard, focus order, colour carrying meaning), Data Visualization Engineer for chart/timeline/encoding surfaces, Identity & Access Engineer for auth, Database Optimizer for query/index work. Route by the surface the diff touches, not by how the task was described. /impeccable audit does not substitute for the accessibility specialist: it checks what can be computed from markup, not whether an encoding is discriminable or an interaction is operable. Fold their findings into the same Critical/Major/Minor/Suggestion classification.
    • The agent MUST report findings classified as Critical, Major, Minor, or Suggestion, each naming the affected file, the observed problem, and the recommended correction — or an explicit "no findings" verdict.
    • The orchestrating session MUST fix every Critical and Major finding (re-running the affected tests and re-dispatching review on the changed surface), OR document the finding and the reason it is accepted alongside the feature's artifacts. Completion MUST NOT be reported while unresolved, undocumented Critical/Major findings remain. Minor/Suggestion findings may be fixed, deferred, or noted at the orchestrator's discretion, but must be listed in the Completion Report.
    • This review complements, and does not replace, the Definition-of-Done Gate (Principle VIII) — the OWASP and code-slop skill passes still run on the changed surface.
    • If subagent dispatch is unavailable in the current environment, run the identical review checklist as a dedicated inline pass over the diff and note that the review ran inline — the gate itself is never skipped.

Note: This command assumes a complete task breakdown exists in tasks.md. If tasks are incomplete or missing, suggest running /speckit-tasks first to regenerate the task list.

Mandatory Post-Execution Hooks

You MUST complete this section before reporting completion to the user.

Check if .specify/extensions.yml exists in the project root.

• If it does not exist, or no hooks are registered under hooks.after_implement, skip to the Completion Report.
• If it exists, read it and look for entries under the hooks.after_implement key.
• If the YAML cannot be parsed or is invalid, skip hook checking silently and continue to the Completion Report.
• Filter out hooks where enabled is explicitly false. Treat hooks without an enabled field as enabled by default.
• For each remaining hook, do not attempt to interpret or evaluate hook condition expressions:
  • If the hook has no condition field, or it is null/empty, treat the hook as executable
  • If the hook defines a non-empty condition, skip the hook and leave condition evaluation to the HookExecutor implementation
• When constructing slash commands from hook command names, replace dots (.) with hyphens (-). For example, speckit.git.commit → /speckit-git-commit.
• For each executable hook, output the following based on its optional flag:
  • Mandatory hook (optional: false) — You MUST emit EXECUTE_COMMAND: for each mandatory hook:

    ## Extension Hooks
    
    **Automatic Hook**: {extension}
    Executing: `/{command}`
    EXECUTE_COMMAND: {command}
    

    After emitting the block above you MUST actually invoke the hook and wait for it to finish before continuing. Run it the same way you would run the command yourself in this agent/session (the invocation may differ from the literal {command} id shown above, e.g. a skills-mode agent runs it as /skill:speckit-... or $speckit-...). Emitting the block alone does not run the hook.
  • Optional hook (optional: true):

    ## Extension Hooks
    
    **Optional Hook**: {extension}
    Command: `/{command}`
    Description: {description}
    
    Prompt: {prompt}
    To execute: `/{command}`
    

Completion Report

Report final status with summary of completed work, plus the Code Reviewer verification outcome from step 10 (no findings / Critical-Major findings resolved / findings accepted with documented rationale), including any deferred Minor/Suggestion findings.

Done When

• Software Architect verification gate (step 3a) confirmed PASSED on plan.md before any task ran
• All tasks in tasks.md completed and marked [X]
• Implementation validated against specification, plan, and test coverage
• Code Reviewer verification (step 10) dispatched, along with any specialist reviewer the changed surface routes to, and every Critical/Major finding resolved or documented as accepted
• Extension hooks dispatched or skipped according to the rules in Mandatory Post-Execution Hooks above
• Completion reported to user with summary of completed work and the review outcome