delivering-heavy-features
Use when a task is classified heavy — a new feature with its own business logic, work spanning several layers with a new or changed contract, or anything…
Skill by Roflochinsky
Chalk Labs
Need help deploying delivering-heavy-features?
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/roflochinsky-delivering-heavy-features
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: documents, backend, security, 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/delivering-heavy-features
What's inside
- Skill name
delivering-heavy-features- Description
- Use when a task is classified heavy — a new feature with its own business logic, work spanning several layers with a new or changed contract, or anything touching a gated decision (auth, schema, money, metric semantics, public API).
- License
- MIT
- Instructions
- 59 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Delivering Heavy Features ## Overview Heavy features fail in predictable ways: built on guessed requirements, no durable spec/plan artifacts, the author approving their own work. This pipeline prevents all three. Phases run in order; the design sign-off is the **only** user approval gate — after it, run to completion. **Dependencies:** superpowers (brainstorming, writing-plans, subagent-driven-development, requesting-code-review, verification-before-completion), grill-me, an issue tracker (beads `bd` recommended). If anything is missing, run the **doctor** skill first. ## Phase 0 — Project conventions Read the project's CLAUDE.md / AGENTS.md for: approval gates (e.g. ADR triggers), layer list, where specs/plans live, mandatory verification commands, tracker conventions. If the project defines its own heavy pipeline — use that one instead. If conventions are missing, use defaults below and offer to record them in the project CLAUDE.md at the end. ## Phase 1 — Discuss (main session, with the user — never a sub-agent) - Invoke **grill-me**: one question at a time until every branch of the design tree is resolved; recommend an answer with each question. If the codebase can answer a question, explore instead of asking. - If the project has approval gates (ADR etc.) and one is touched: write/update the decision record and get the user's sign-off **before any code**. **If the user is unreachable:** unavailability defers the gate, it does not remove it. - Write every assumption down in the spec, marked ASSUMPTION. - Build only the **safe, reversible subset**; leave hard-to-undo decisions (real sends to users, destructive migrations, public contract finalization) behind explicit "needs your yes" items. - Send the batched questions through whatever channel exists; present them prominently when the user returns. ## Phase 2 — Spec (durable artifact) Persist to `docs/specs/<slug>.md` (create dir on first use) or the project's convention: problem, decisions with the why, scope, non-goals, acceptance criteria, affected layers, assumptions. The spec must survive compaction and session changes — chat history is not an artifact. ## Phase 3 — Decompose into tracked issues Epic + child issues in the tracker (`bd create --type=epic`, children wired with `bd dep add`). Each child = one vertical slice independently executable by a fresh agent, carrying its verification command(s) in the description. Use the **decomposing-to-issues** skill. ## Phase 4 — Research (read-only sub-agents, parallel) One Explore-type sub-agent per affected layer. Research agents read only — no edits. Each returns: current state, integration points, patterns to reuse, risks. Append findings to the spec under `## Research`. ## Phase 5 — Plan superpowers:writing-plans over spec + research: steps with a verify criterion per step. Persist to `docs/plans/<slug>.md` or project convention. Sync plan steps with the tracker issues. ## Phase 6 — Execute superpowers:subagent-driven-development: one issue = one executor sub-agent with a **fresh context** — pass spec/plan/issue paths, not a retelling of the conversation. TDD where it fits. Close issues as they complete. ## Phase 7 — Verify (never the author) - Per issue: independent reviewer sub-agent (superpowers:requesting-code-review) checks the diff against spec + plan; loop fix → review until clean. Reviewers get different lenses (correctness / simplicity / conventions), not N identical passes. - Epic level: project's mandatory verification for every touched layer + run the actual app and observe the feature working (superpowers:verification-before-completion). - Record verification notes in the spec/plan. Close the epic. Ship via **shipping-a-release** only on the user's explicit ask. ## Red flags — you are rationalizing | Thought | Reality | |---|---| | "Deadline tomorrow → compressed pipeline" | Compress SCOPE (smaller vertical slice at full discipline), never phases. | | "User is in meetings, so no approval gate" | Deferred ≠ removed. Safe subset + queued decisions. | | "The spec is the tracker issue / chat history" | Issues fragment, chat compacts. One durable spec file. | | "I'll review my own diff carefully" | Same context = same blind spots. Fresh-context reviewer, always. | | "Research slows me down, I know this codebase" | Each layer gets 10 minutes of reading and saves a rejected PR. |
From Roflochinsky/workshopskills, MIT.
More from Roflochinsky/workshopskills
- 0.474score
shipping-a-release
Roflochinsky
Use when implementation is complete and the user explicitly asks to wrap up, ship, release, merge, or publish the work.
SkillCFreshness: CClaude Code +9 - 0.474score
decomposing-to-issues
Roflochinsky
Use when breaking a spec or plan into tracker issues for execution — especially when different agents or sessions will pick the pieces up independently.
SkillCFreshness: CClaude Code +9 - 0.474score
doctor
Roflochinsky
Use before running heavy composite workflows (delivering-heavy-features etc.), when a required skill or tool is missing, when setting up a new machine or…
SkillCFreshness: CClaude Code +9 - 0.474score
fixing-incidents
Roflochinsky
Use when production is down or degraded, users are reporting errors, or the user demands an urgent fix ("prod is down", "fix it now", "clients are calling") —…
SkillCFreshness: CClaude Code +9 - 0.474score
getting-second-opinion
Roflochinsky
Use when about to approve, merge, or sign off on non-trivial work you authored yourself — especially when feeling confident, when the user says "I trust your…
SkillCFreshness: CClaude Code +9 - 0.474score
upgrading-dependencies
Roflochinsky
Use when asked to update, upgrade, or bump dependencies, fix dependency vulnerabilities, or when CI flags outdated/vulnerable packages — before running any…
SkillCFreshness: CClaude Code +9 - 0.474score
codifying-learnings
Roflochinsky
Use when the user corrects you, repeats an instruction they gave before, or you notice you've made the same mistake or received the same feedback more than…
SkillCFreshness: CClaude Code +9 - 0.474score
classifying-tasks
Roflochinsky
Use when receiving any new work request, before writing code or choosing an approach — especially multi-item requests, vague one-liners, "quick" asks, or work…
SkillCFreshness: CClaude Code +9 - 0.474score
onboarding-codebase
Roflochinsky
Use when working in a repository for the first time, or in an unfamiliar area of a large repo — before making any edit, especially when the task "should be…
SkillCFreshness: CClaude Code +9 - 0.471score
heavy-task-pipeline
Roflochinsky
Use for Tier 2 / heavy Workwatch tasks — a new dashboard section with its own business logic, anything spanning API + DB migrations + UI, or any ADR-gate…
SkillCFreshness: CClaude Code +9 - 0.471score
runtime-sql-review
Roflochinsky
Mandatory write→review loop for runtime-/live-only fixes the test suite cannot catch — raw SQL via SQLAlchemy text() / asyncpg, migrations, queries, any…
SkillCFreshness: CClaude Code +9 - 0.445score
grill-me
Roflochinsky
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 16, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Roflochinsky/workshopskills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Roflochinsky
- 0.474score
shipping-a-release
Roflochinsky
Use when implementation is complete and the user explicitly asks to wrap up, ship, release, merge, or publish the work.
SkillCFreshness: CClaude Code +9 - 0.474score
decomposing-to-issues
Roflochinsky
Use when breaking a spec or plan into tracker issues for execution — especially when different agents or sessions will pick the pieces up independently.
SkillCFreshness: CClaude Code +9 - 0.474score
doctor
Roflochinsky
Use before running heavy composite workflows (delivering-heavy-features etc.), when a required skill or tool is missing, when setting up a new machine or…
SkillCFreshness: CClaude Code +9 - 0.474score
fixing-incidents
Roflochinsky
Use when production is down or degraded, users are reporting errors, or the user demands an urgent fix ("prod is down", "fix it now", "clients are calling") —…
SkillCFreshness: CClaude Code +9 - 0.474score
getting-second-opinion
Roflochinsky
Use when about to approve, merge, or sign off on non-trivial work you authored yourself — especially when feeling confident, when the user says "I trust your…
SkillCFreshness: CClaude Code +9 - 0.474score
upgrading-dependencies
Roflochinsky
Use when asked to update, upgrade, or bump dependencies, fix dependency vulnerabilities, or when CI flags outdated/vulnerable packages — before running any…
SkillCFreshness: CClaude 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 delivering-heavy-features 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
delivering-heavy-features skill. Agent Mart. https://agentmart.dev/skills/roflochinsky-delivering-heavy-features (last updated 2026-10-24)