grailautomation/implement
spec-kit/skills/implement/SKILL.md
Use when the user invokes $spec-kit:implement or /spec-kit:implement, or asks to safely execute spec-kit tasks in next, phase, or all mode.
tools
Updated Jul 5, 2026
$ install --global
skillsauthnpx skillsauth add grailautomation/claude-plugins implementInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jul 5, 2026, 2:06 AM222.5s2 files scanned
SKILL.md
- name:
- implement
- description:
- Use when the user invokes $spec-kit:implement or /spec-kit:implement, or asks to safely execute spec-kit tasks in next, phase, or all mode.
- argument-hint:
- [next|phase <name>|all]
- allowed-tools:
- [Read, Write, Edit, Bash, Glob, Grep]
- disable-model-invocation:
- true
Spec Kit Implement
This is a user-invoked Spec Kit workflow. Treat user text after the invocation as the workflow input.
Plugin Root
Use the spec-kit plugin root when running bundled scripts. In Claude Code, ${CLAUDE_PLUGIN_ROOT} resolves to this plugin root. If that variable is unavailable, resolve the plugin root as the directory two levels above this SKILL.md.
User input:
$ARGUMENTS
Execute tasks from tasks.md with a Codex-safe brownfield preflight. Default
mode is next unless the user explicitly asks for phase or all.
Feature Detection
Run from the project root:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/setup-plan.sh"
Parse JSON for SPECS_DIR, FEATURE_SPEC, IMPL_PLAN, and
PROJECT_CONTEXT. All paths must be absolute.
Required Inputs
Load:
SPECS_DIR/tasks.md(required)SPECS_DIR/plan.md(required)SPECS_DIR/spec.md(required)PROJECT_CONTEXT, if present- Optional design artifacts:
data-model.md,contracts/,research.md,quickstart.md
Abort if tasks.md or plan.md is missing.
Modes
next: complete the first unchecked task only. This is the default.phase <name>: complete unchecked tasks in the named phase.all: complete all unchecked tasks. Before proceeding, summarize scope and ask for explicit confirmation.
Safety Preflight
Before editing:
- Inspect
git status --short --branch. - Identify files with user changes. Do not overwrite, revert, or reformat unrelated changes.
- Read target files before editing them.
- Identify destructive operations, migrations, external service calls, credential use, generated artifact churn, or production-impacting commands. Ask for explicit confirmation before running those steps.
- Confirm verification commands from
tasks.md,plan.md, orproject-context.md.
If the task is too broad or lacks exact files/outcomes, stop and recommend
regenerating or editing tasks.md.
Execution Rules
- Complete only the selected mode's scope.
- Respect dependencies and phase ordering.
[P]means tasks may be done in any order, not that Codex must spawn agents.- Keep edits scoped to the task's files.
- Write tests before or alongside implementation according to the task and repo practice.
- After completing a task, mark it
[X]intasks.md. - If a non-parallel task fails, stop and report the blocker.
- For phase/all mode, run focused verification after each phase when commands are known.
Completion Validation
Before reporting:
- Confirm selected task(s) are marked
[X]. - Run the focused verification command when available and not destructive.
- Check implementation still matches the spec and plan.
- If verification could not be run, state why.
Report
Report:
- Mode used
- Tasks completed
- Files changed
- Verification result
- Any skipped tasks or blockers
- Suggested next command only when useful, usually
/spec-kit:implement nextor/spec-kit:analyze
Related Skills
grailautomation/workato-recipe
development
VerifiedTrustedCommunity
Parse and analyze Workato recipe JSON exports. Use when the user asks about a Workato recipe's logic, data flow, field mappings, error handling, or control flow. Also use when the user references a .recipe.json file or asks to debug a Workato integration.
SKILL.mdUpdated Jul 5, 2026
grailautomation/staff-plan-review
databases
VerifiedTrustedCommunity
Review implementation plans as a staff software engineer. Use when the user asks for staff engineer feedback, senior engineering review, plan review, architecture review, implementation-plan critique, approval before proceeding, risk review, or feedback on a proposed technical plan.
SKILL.mdUpdated Jul 5, 2026
grailautomation/tasks
tools
VerifiedTrustedCommunity
Use when the user invokes $spec-kit:tasks or /spec-kit:tasks, or asks to generate dependency-ordered tasks from the plan and repo context.
SKILL.mdUpdated Jul 5, 2026
grailautomation/specify
testing
VerifiedTrustedCommunity
Use when the user invokes $spec-kit:specify or /spec-kit:specify, or asks to create a brownfield-aware feature specification from a natural language description.
SKILL.mdUpdated Jul 5, 2026