spec-driven-workflow
A rigid workflow for feature implementation using pre-approved specs and evaluation gates to ensure code quality before merging.
Install
mkdir -p .claude/skills/spec-driven-workflow && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16840" && unzip -o skill.zip -d .claude/skills/spec-driven-workflow && rm skill.zipInstalls to .claude/skills/spec-driven-workflow
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
The build workflow for avaliador-tech-recruiter — risk-ordered tiers with a protected mock-mode floor, a Ready spec required before any unit is implemented, eval gates (L0 contract / L1 policy / L2 fixtures) as the merge filter, package partitioning for parallel agents, atomic Conventional Commits, and never pushing to main without explicit confirmation. Use when starting any implementation unit, deciding what to build next, splitting work across agents, opening/merging a branch, or committing. Triggers on specs/, tiers, eval gates, "what should I build next", branching, or commit/push.Key capabilities
- →Confirm a spec is `Ready` before implementing a unit of work
- →Build to acceptance criteria tagged to eval gates (L0, L1, L2)
- →Make eval gates pass as the merge filter
- →Commit atomically with Conventional Commits
- →Partition new work by package/directory to avoid conflicts
- →Build in risk-ordered tiers, starting with mock-mode
How it works
The skill enforces a spec-driven build workflow by requiring a `Ready` spec, building to acceptance criteria with eval gates, committing atomically, and partitioning work for parallel agents.
Inputs & outputs
When to use spec-driven-workflow
- →Implementing a new unit of work
- →Splitting complex features across multiple agents
- →Verifying gate compliance before merging
- →Starting new feature development
About spec-driven-workflow
This skill mandates a 'Ready' spec for all work units and enforces progress through L0, L1, and L2 evaluation gates. It uses package partitioning to enable parallel development while maintaining atomic commits and preventing unauthorized pushes to main.
The build workflow for avaliador-tech-recruiter — risk-ordered tiers with a protected mock-mode floor, a Ready spec required before any unit is implemented, eval gates (L0 contract / L1 policy / L2 fixtures) as the merge filter, package partitioning for parallel agents, atomic Conventional Commits,
When not to use it
- →When implementing a unit before its spec is `Ready`
- →When pushing to `main` without explicit confirmation
- →When batching unrelated changes into a single commit
Limitations
- →Requires a `Ready` spec before implementation begins
- →Eval gates are the merge filter, not eyeballing
- →Live model/GitHub/cloud calls never run in the default test suite
How it compares
This skill mandates a structured, spec-driven workflow with risk-ordered tiers and strict evaluation gates, ensuring quality and preventing unauthorized merges, unlike a less controlled development process.
Compared to similar skills
spec-driven-workflow side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| spec-driven-workflow (this skill) | 0 | 3mo | No flags | Advanced |
| dev | 2 | 7mo | Review | Advanced |
| overnight-development | 1 | 2mo | Review | Intermediate |
| workflow-patterns | 1 | 4mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
dev
atopile
LLM-focused workflow for working in this repo: compile Zig, run the orchestrated test runner, consume test-report.json/html artifacts, and discover/debug ConfigFlags.
overnight-development
jeremylongshore
Automates software development overnight using git hooks to enforce test-driven Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
workflow-patterns
wshobson
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
resolve-checks
flowglad
Resolve all failing CI checks and address PR review feedback on the current branch's PR. Runs tests locally, fixes failures, incorporates valid review comments, and resolves addressed feedback. Use when CI is red, after receiving PR feedback, or before merging.
git-pr-workflows-git-workflow
Anhvu1107
ALWAYS use this when the request matches GIT PR Workflows GIT Workflow: Orchestrate a comprehensive git workflow from code review through PR creation, leveraging specialized agents for quality assurance, testing, and deployment readiness.
proof-of-work
MadAppGang
Proof artifact generation patterns for task validation. Covers screenshots, test results, deployments, and confidence scoring.