feature
Start feature workflow — analyze, spec v1.0, plan, TDD, comprehension, verification.
Skill by alec-c4
Chalk Labs
Need help deploying feature?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/alec-c4-feature
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
Use cases: testing, productivity
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/feature
What's inside
- Skill name
feature- Description
- Start feature workflow — analyze, spec v1.0, plan, TDD, comprehension, verification. Use when user runs /feature or asks to add or build a new capability.
- License
- MIT
- Instructions
- 35 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Feature workflow
**Explicit invoke** — skip [intent-router](../intent-router/SKILL.md) classification. Same pipeline as natural-language feature intent ([INTENT-ROUTING.md](../../docs/guidelines/INTENT-ROUTING.md)).
## Intent
**Feature (new or update)** — create or bump spec, plan, implement with TDD.
## Steps
Follow [WORKFLOW.md](../../docs/guidelines/WORKFLOW.md) standard feature flow:
1. **Analyze** — read ticket or request; set **work_ref** and **spec_key** ([TRACKER.md](../../docs/guidelines/TRACKER.md)); paste into `.ai/work/{work_ref}-analysis.md` if needed; run `./scripts/kit detect-stack --write-profile`. Load `.ai/work/{work_ref}-findings.md` and treat open/regressed **block** rows as constraints.
2. **Spec** — new task: `.ai/specs/{spec_key}-spec.md` at **v1.0**; update: bump version, changelog, archive ([SPECS.md](../../docs/guidelines/SPECS.md)). **Wait for human approval** before plan or code.
3. **Plan** — `.ai/work/{work_ref}-plan.md` with Detail level (minimal | standard | detailed). **Wait for approval** before production code.
4. **Branch** — `feature/<short-name>` per [GIT.md](../../docs/guidelines/GIT.md).
5. **Implement** — TDD per [TESTING.md](../../docs/guidelines/TESTING.md) and stack profile.
6. **Comprehension** — [comprehension-check](../comprehension-check/SKILL.md): handoff + Q&A + human sign-off ([COMPREHENSION.md](../../docs/guidelines/COMPREHENSION.md)) when tier ≥ standard.
7. **Verification** — **new agent session** ([VERIFICATION.md](../../docs/guidelines/VERIFICATION.md)); save `.ai/work/{work_ref}-verification.md`.
8. **Review** — [REVIEW.md](../../docs/guidelines/REVIEW.md).
9. **PR** — draft `.ai/pr-summary.md`; open PR with test plan.
## First message
Announce in one line: **Following feature workflow** (spec → plan → TDD → comprehension → verification → review → PR).
If scope is unclear, ask **one** clarifying question before spec — do not skip spec gates.
## Do not
- Commit before spec approval (non-trivial work).
- Skip comprehension or verification when DoD requires them.
- Deploy or merge without explicit human confirm.From alec-c4/agent_dev_kit, MIT.
More from alec-c4/agent_dev_kit
- 0.547score
fix
alec-c4
Start bug-fix workflow — analyze, spec bump, TDD fix, verification.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
comprehension-check
alec-c4
Generate comprehension Q&A from spec and handoff; grade human answers and teach on errors before verification.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
docker-patterns
alec-c4
Docker and container patterns — images, compose, multi-stage builds, CI.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
intent-router
alec-c4
Classify user intent before acting — feature, bug, refactor, audit, or question.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
changelog
alec-c4
Draft user-facing changelog entries from spec changelog and merged PRs.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
elixir-phoenix-patterns
alec-c4
Elixir and Phoenix patterns — contexts, Ecto, LiveView.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
fastapi-patterns
alec-c4
FastAPI patterns — routers, dependency injection, Pydantic v2.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
flutter-patterns
alec-c4
Flutter patterns — widgets, state, navigation, async, and platform integration.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
go-service-patterns
alec-c4
Go service patterns — packages, context, errors, HTTP handlers.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
inertia
alec-c4
Inertia.js patterns with Rails or Node backends.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
kotlin-patterns
alec-c4
Kotlin patterns — Gradle, coroutines, null safety, Android and Ktor.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
kubernetes-patterns
alec-c4
Kubernetes (k8s) patterns — workloads, networking, config, GitOps.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 2, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/alec-c4/agent_dev_kit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from alec-c4
- 0.547score
fix
alec-c4
Start bug-fix workflow — analyze, spec bump, TDD fix, verification.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
docker-patterns
alec-c4
Docker and container patterns — images, compose, multi-stage builds, CI.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
intent-router
alec-c4
Classify user intent before acting — feature, bug, refactor, audit, or question.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
comprehension-check
alec-c4
Generate comprehension Q&A from spec and handoff; grade human answers and teach on errors before verification.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
changelog
alec-c4
Draft user-facing changelog entries from spec changelog and merged PRs.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
hotwire
alec-c4
Hotwire Turbo and Stimulus patterns for Rails.
SkillBFreshness: B★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get feature running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
feature skill. Agent Mart. https://agentmart.dev/skills/alec-c4-feature (last updated 2026-10-24)