dev-playbook
Use when the user types /dev-playbook, asks to start, scaffold, bootstrap, or init a new project/repo/library in rust, python, go, java, cpp, c, php, ts-lib…
Skill by folkengine
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/folkengine-dev-playbook
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/dev-playbook
What's inside
- Skill name
dev-playbook- Description
- Use when the user types /dev-playbook, asks to start, scaffold, bootstrap, or init a new project/repo/library in rust, python, go, java, cpp, c, php, ts-lib, or ts-next, or asks to bump/update an existing playbook repo's toolchain, dependencies, or language version. Replaces forking the devplaybooks GitHub org templates.
- License
- Apache-2.0
- Instructions
- 114 lines in SKILL.md · view on GitHub
Files (20)
- SKILL.md
- AI-BOM.md.tmpl · assets/
- CODE_OF_CONDUCT.md · assets/
- CONTRIBUTING.md.tmpl · assets/
- SECURITY.md.tmpl · assets/
- LICENSE-APACHE · assets/licenses/
- LICENSE-GPLv3 · assets/licenses/
- LICENSE-MIT · assets/licenses/
- 2026-08-01-dev-playbook-skill-design.md · docs/
- 2026-08-01-dev-playbook-skill.md · docs/plans/
- baseline.md · references/
- c.md · references/
- cpp.md · references/
- go.md · references/
- java.md · references/
- php.md · references/
- python.md · references/
- rust.md · references/
- ts-lib.md · references/
- ts-next.md · references/
SKILL.md (first lines)
# Dev Playbook Scaffold repos the devplaybooks way: opinionated supporting files layered on top of the stack's native init — quality gates, CI, security scanning, CLAUDE.md, and an OKF knowledge bundle — no application code beyond hello-world, and a quality gate that is green before the first commit. Also updates an existing playbook repo's toolchain and dependencies to latest or to pinned versions. "Cruel to be kind in the right measure." ## How to read this skill Always read `references/baseline.md` plus exactly ONE stack file from the roster. Never read more than one stack file per run. ## Stack roster | Key | Reference | Stack-specific questions | |---|---|---| | rust | references/rust.md | lib vs bin; edition/MSRV; miri opt-in | | python | references/python.md | lib vs app | | go | references/go.md | module path | | java | references/java.md | maven vs gradle; JDK version (default 21) | | cpp | references/cpp.md | cmake vs bazel; gtest vs catch2 (bazel→gtest only) | | c | references/c.md | — | | php | references/php.md | lib vs app; package name (vendor/name); namespace root | | ts-lib | references/ts-lib.md | package scope; entry points | | ts-next | references/ts-next.md | — (create-next-app runs its own) | ## Flow 1: Scaffold `/dev-playbook [stack] [name] [--<tool> <version> ...]` 1. **Interview** — ask only what wasn't given, one question at a time: stack → project name → stack-specific questions (roster) → license(s) (default: all three of MIT, Apache-2.0, GPLv3) → target directory (default `./<name>`) → version targeting (default: current stable; accept pins like `--python 3.11`). 2. **Preflight** — target dir must not exist or be empty, else STOP and ask. Native tool must be installed, else STOP and report the install command (prefer `mise install`). Resolve every version now (ask the toolchain, e.g. `rustup check`, `uv python list`; never guess from memory). 3. **Native init** — run the stack's init command (stack file, section Init). 4. **Layer** — apply baseline layers (baseline.md) then stack layer (stack file, sections Config/Gate/CI). Order: baseline files → AI files → stack configs. 5. **Knowledge** — seed `.okf/` last (baseline.md, OKF section), so toolchain decisions exist to record. 6. **Verify** — run `make ayce`; iterate on failures until green. If still red after ~3 distinct fix attempts, deliver anyway and state plainly which target fails and why. Never claim green that isn't. 7. **Validate OKF** — run the okf validator (baseline.md, OKF section). If the plugin is absent, say validation was skipped. 8. **Hand off** — print, never run: ``` git init && git add -A && git commit -m "chore: scaffold <name> via dev-playbook (<stack>)" gh repo create <name> --public --source=. --push # optional ``` ## Flow 2: Update `/dev-playbook update [--<tool> <version> ...]` inside an existing repo. 1. **Detect** stack from `.tool-versions` + manifests (Cargo.toml, pyproject.toml, go.mod, pom.xml/build.gradle*, CMakeLists.txt/MODULE.bazel, Makefile-with-cc-rules + Check-based tests/ for c, composer.json, package.json). Read the matching stack file. On a repo that only partially matches playbook conventions, list what was and wasn't recognized and touch only the recognized parts. 2. **Dirty-tree check** — `git status --porcelain`; if dirty, warn and get explicit go-ahead before touching files (reading git state is allowed; changing it is not). 3. **Resolve targets** — latest stable per tool, overridden by explicit pins. 4. **Propagate versions** to every location this stack declares — the baseline set is `.tool-versions`, CI matrix, devcontainer toolchain pin (image tag where the family encodes the language version; otherwise the postCreateCommand/feature pin — see baseline.md § Devcontainer), and manifest pins; the stack file names any it adds (Python adds `.python-version`). Enumerate the set from the stack file rather than assuming a count. Bump GitHub Actions `uses:` versions too. 5. **Update dependencies** — run the stack file's Update-section commands. 6. **Drift check** — for each generated file the stack file defines a drift probe for (its Update section names them), regenerate what the current toolchain would produce and diff against the repo's file. REPORT divergence with the actual diff; never silently rewrite — after the first commit these files belong to the user. Offer to apply the fresh output only if the user asks. 7. **Verify** — `make ayce` to green, security-scan included. If an upgrade breaks the build, report the offender and offer to hold it back pinned so the rest lands. 8. **Record** — append dated `.okf/log.md` entry; update `.okf/decisions/toolchain.md` if a tool (not just a version) changed. 9. **Hand off** — report what changed and why; print git commands, never run. ## Hard rules - Never run state-changing git commands. Print them for the user. - `make ayce` is always the default Makefile target; its meaning never varies. - One security-scan definition (`bin/security-scan`); Makefile and CI call it. - Every version-declaring location agrees. The set is stack-dependent — the baseline four plus whatever the stack file adds — so enumerate it per stack and never assert a fixed count. - GitHub Actions `uses:` majors are resolved at scaffold time like any other version, never copied from a reference file — stack files write them as `@<resolved-major>` for exactly this reason. Refs that name a thing rather than a version (`dtolnay/rust-toolchain@stable`, `taiki-e/install-action@cargo-audit`) are copied verbatim and never resolved. See baseline.md, § CI workflows → Action version pins. - Report failures plainly; never claim a green gate that isn't. - Offline or registry unreachable: do what is possible, then list exactly which steps (version resolution, dependency fetch, advisory databases) need connectivity to finish.
From folkengine/.claude, Apache-2.0.
More from folkengine/.claude
- 0.570score
huxley
folkengine
Use when the user types /huxley <code>, or asks how a function, type, file, or snippet evolved over time, wants its git lineage or "family tree", asks where…
SkillAFreshness: AClaude Code +9 - 0.529score
smimd
folkengine
Evaluate a codebase for parallelism opportunities — SIMD lanes, SWAR bit-tricks, MIMD/thread-level data parallelism, and the algorithm or data-structure…
SkillBFreshness: BClaude Code +9 - 0.529score
untangle
folkengine
Evaluate how entangled a repository is with each of its dependencies and what removing them would take — a standardized audit written to the repo's docs…
SkillBFreshness: BClaude Code +9 - 0.529score
conformance
folkengine
Measure a codebase against an externally-authored ruleset — a standards-body spec, RFC, protocol document, regulation, house rules PDF, or API contract —…
SkillBFreshness: BClaude Code +9 - 0.524score
quality-commitments
folkengine
Facilitates Quality Commitments work — collaborative definition of quality standards, generation of a Quality Commitments Matrix, evidence-based audit of an…
SkillBFreshness: BClaude Code +9 - 0.524score
critique
folkengine
Deliver a harsh, evidence-backed critique of whatever the user points at — a file, directory, codebase, skill, design doc, API, spec, README, or pasted text.
SkillBFreshness: BClaude Code +9 - 0.524score
qanda
folkengine
Generate a paired self-test Q&A study set — <TOPIC>_QUESTIONS.md and <TOPIC>_ANSWERS.md in the repo's docs folder — that helps developers learn how the code…
SkillBFreshness: BClaude Code +9 - 0.519score
debrief
folkengine
Bullet-point summary of what changed on the current branch versus main.
SkillBFreshness: BClaude Code +9 - 0.499score
blooper
folkengine
Use when the user asks for a "blooper report" or wants to dig through a repo's git history to find its most embarrassing early coding mistakes and see which…
SkillBFreshness: BClaude Code +9 - 0.479score
deconstruct
folkengine
Distill an existing codebase into a portable regeneration pack — language-agnostic DECON epics in the /epic house style plus golden test vectors extracted by…
SkillCFreshness: CClaude Code +9 - 0.479score
codebase-kata
folkengine
Turn a real codebase into a TDD-style coding kata that teaches the core technology or algorithm behind it.
SkillCFreshness: CClaude Code +9 - 0.474score
dog
folkengine
Dog mode, aka "walking the dog" — Claude writes no code; it walks the developer through a coding task one step at a time while the developer types everything.
SkillCFreshness: CClaude 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
- Apache-2.0
- Repository
- github.com/folkengine/.claude
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from folkengine
- 0.570score
huxley
folkengine
Use when the user types /huxley <code>, or asks how a function, type, file, or snippet evolved over time, wants its git lineage or "family tree", asks where…
SkillAFreshness: AClaude Code +9 - 0.529score
conformance
folkengine
Measure a codebase against an externally-authored ruleset — a standards-body spec, RFC, protocol document, regulation, house rules PDF, or API contract —…
SkillBFreshness: BClaude Code +9 - 0.529score
smimd
folkengine
Evaluate a codebase for parallelism opportunities — SIMD lanes, SWAR bit-tricks, MIMD/thread-level data parallelism, and the algorithm or data-structure…
SkillBFreshness: BClaude Code +9 - 0.529score
untangle
folkengine
Evaluate how entangled a repository is with each of its dependencies and what removing them would take — a standardized audit written to the repo's docs…
SkillBFreshness: BClaude Code +9 - 0.524score
qanda
folkengine
Generate a paired self-test Q&A study set — <TOPIC>_QUESTIONS.md and <TOPIC>_ANSWERS.md in the repo's docs folder — that helps developers learn how the code…
SkillBFreshness: BClaude Code +9 - 0.524score
quality-commitments
folkengine
Facilitates Quality Commitments work — collaborative definition of quality standards, generation of a Quality Commitments Matrix, evidence-based audit of an…
SkillBFreshness: BClaude Code +9
Cite this page
dev-playbook skill. Agent Mart. https://agentmart.dev/skills/folkengine-dev-playbook (last updated 2026-10-24)