How do I install the Setup CI skill?

Run npx skillmds@latest add talhamah56/setup-ci in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Setup CI safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Setup CI?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Setup CI free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Setup CI?

talhaMah56 (@talhamah56) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Setup CI by talhamah56 — Agent Skill

Name: Setup CI
Rating: 4.666666666666667 (3 reviews)
Author: talhaMah56

Setup CI

Use to create or adjust the CI/CD pipeline that materializes the SDD gates — lint, static analysis (type-check/complexity/SAST), tests (unit/integration/acceptance) and coverage from docs/engineering/TESTING.md, with coverage and static analysis published as artifacts, plus the "PR fails without an approved spec" rule. Detects GitHub Actions / GitLab CI / other. Generates the file only with approval. Trigger with /setup-ci.

talhaMah56 Updated Sep 22, 2026

File contents

Translation note: Originally authored in Portuguese (pt-BR) by Igor Uehara (igoruehara/spec-driven, MIT). Translated to English by this hub to keep the repository language consistent. Original content unchanged in meaning; see the upstream repo for the pt-BR source.

Skill: CI/CD setup (SDD gates in the pipeline)

Materializes the SDD gates in the automated pipeline — this is where "a document the team tries to follow" becomes "rules the system enforces". Idempotent: re-running adjusts the existing pipeline.

Discover the target

Detect the provider (GitHub Actions / GitLab CI / Bitbucket / other) from the repo and from integrations.md.
Read docs/engineering/TESTING.md (gate commands) and the quality gate from CLAUDE.md (minimum coverage).

Propose the pipeline (confirm before generating)

Stages in order; failing blocks the merge:

Lint/format → 2. Static analysis (type-check + complexity + SAST) → 3. Unit →
1. Integration → 5. Acceptance (one per AC-N) → 6. Coverage (min. from CLAUDE.md).
SDD rule: a PR that changes code without an approved spec in specs/ → fails (a job that checks the presence/status of the spec corresponding to the change).

Traceable evidence: publish coverage and static analysis as artifacts of the run (and, if the provider allows, as a check/comment on the PR). The quality result gets attached to the change and feeds the delivery-trend data you choose to track.

Generate

The pipeline file (.github/workflows/*.yml / .gitlab-ci.yml) using the commands from docs/engineering/TESTING.md — do not invent commands; reuse the ones there.
⚠️ No secrets in the file — use the provider's secrets. Confirm before writing.
Record the pipeline choice as an ADR if it is structural; reference it in docs/engineering/agentic-layer.md.

Next step

Pair CI automation with a human/agent review gate: CI enforces tests/coverage, while review enforces the judgement calls CI cannot check.

---name: setup-cidescription: Use to create or adjust the CI/CD pipeline that materializes the SDD gates — lint, static analysis (type-check/complexity/SAST), tests (unit/integration/acceptance) and coverage from docs/engineering/TESTING.md, with coverage and static analysis published as artifacts, plus the "PR fails without an approved spec" rule. Detects GitHub Actions / GitLab CI / other. Generates the file only with approval. Trigger with /setup-ci.---> **Translation note:** Originally authored in Portuguese (pt-BR) by Igor Uehara ([igoruehara/spec-driven](https://github.com/igoruehara/spec-driven), MIT). Translated to English by this hub to keep the repository language consistent. Original content unchanged in meaning; see the upstream repo for the pt-BR source.# Skill: CI/CD setup (SDD gates in the pipeline)Materializes the SDD gates in the automated pipeline — this is where "a document the team tries to follow" becomes"rules the system enforces". **Idempotent**: re-running adjusts the existing pipeline.## Discover the target- Detect the provider (GitHub Actions / GitLab CI / Bitbucket / other) from the repo and from `integrations.md`.- Read `docs/engineering/TESTING.md` (gate commands) and the quality gate from `CLAUDE.md` (minimum coverage).## Propose the pipeline (confirm before generating)Stages in order; failing **blocks the merge**:1. **Lint/format** → 2. **Static analysis** (type-check + complexity + SAST) → 3. **Unit** → 4. **Integration** → 5. **Acceptance** (one per `AC-N`) → 6. **Coverage** (min. from `CLAUDE.md`).7. **SDD rule:** a PR that changes code **without an approved spec** in `specs/` → fails (a job that checks the presence/status of the spec corresponding to the change).**Traceable evidence:** publish **coverage and static analysis as artifacts** of the run (and, if theprovider allows, as a check/comment on the PR). The quality result gets attached to the change andfeeds the delivery-trend data you choose to track.## Generate- The pipeline file (`.github/workflows/*.yml` / `.gitlab-ci.yml`) using the commands from `docs/engineering/TESTING.md` — do not invent commands; reuse the ones there.- ⚠️ **No secrets in the file** — use the provider's secrets. Confirm before writing.- Record the pipeline choice as an **ADR** if it is structural; reference it in `docs/engineering/agentic-layer.md`.## Next stepPair CI automation with a human/agent review gate: CI enforces tests/coverage, while reviewenforces the judgement calls CI cannot check.

Frequently asked questions