doctor
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…
Skill by Roflochinsky
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-doctor
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/doctor
What's inside
- Skill name
doctor- Description
- 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 project for these skills, or when the user asks to check that the skill stack is healthy.
- License
- MIT
- Instructions
- 56 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Doctor ## Overview Composite workflow skills depend on other skills and tools being installed and wired. Doctor verifies the stack, reports what's missing, and — with the user's consent — installs and wires it. Never install or edit anything without asking first. ## 1. Check — run these and build a status table | Component | Check | Healthy when | |---|---|---| | Superpowers plugin | `grep -o 'superpowers' ~/.claude/plugins/installed_plugins.json` or `ls ~/.claude/plugins/cache/*/superpowers/*/skills/` (the Skill tool listing is not shell-checkable) | Plugin installed; skills dir contains brainstorming, writing-plans, subagent-driven-development, verification-before-completion | | This collection's skills | Diff the source repo against installed: `comm -23 <(ls <repo>/skills/) <(ls ~/.claude/skills/)` where `<repo>` is your clone of this collection | Empty output — every `skills/<name>` from the repo present in `~/.claude/skills/` (symlink or copy), each with SKILL.md. grill-me/handoff count if you use them | | beads (tracker) | `command -v bd && bd version` | Installed | | beads in project | `test -d <project-root>/.beads` — do NOT use `bd ready` as the check: it walks up parent dirs and exits 0 against `~/.beads`, a false positive | Dir exists (only if a project is open) | | Project CLAUDE.md routing | Project CLAUDE.md mentions task tiers / routes heavy tasks to a pipeline skill | Routing line exists; it must NAME the skill, not retell its process | | Name collisions | `sort <(ls ~/.claude/skills/) <(ls .claude/skills/ 2>/dev/null) <(ls ~/.claude/plugins/cache/*/*/*/skills/ 2>/dev/null) \| uniq -d` | Empty — no skill name duplicated across personal / project / plugin namespaces (collisions resolve unreliably — rename) | | Description budget | Startup warnings about skill descriptions exceeding the listing budget (session start output; `claude doctor` is an interactive TUI and does not report this) | No overflow warnings | Report the table to the user: OK / MISSING / MISCONFIGURED per row, one line each. ## 2. Ask — before changing anything Use one batched question round: 1. **Install missing skills + beads?** (Recommended: yes.) 2. **Wire this project's CLAUDE.md?** (Add the routing block below.) Show the exact diff before writing. If the user declines a component, note which workflows degrade (e.g. without beads, decomposition falls back to markdown plans — worse persistence) and proceed with the rest. ## 3. Fix — only what was approved - **Superpowers**: `claude plugin marketplace add obra/superpowers-marketplace && claude plugin install superpowers@superpowers-marketplace` - **This collection**: clone the repo, then symlink each `skills/<name>` into `~/.claude/skills/<name>` (symlinks keep one source of truth; `cp -r` if the filesystem can't symlink). - **beads**: install per https://github.com/steveyegge/beads#installation (check README for the current command — do not guess one). Then `bd init` in the project if the user wants project tracking. - **CLAUDE.md routing block** (adapt tiers to the project; keep it to routing — the process lives in the skills): ```markdown # Task dispatcher Classify every request with the classifying-tasks skill before acting. Heavy tasks → delivering-heavy-features skill. Shipping → shipping-a-release skill (explicit ask only). <Project-specific gates and verification commands go here.> ``` ## 4. Re-check Re-run the checks after fixing; report the final table. Done = all approved rows healthy, not "commands executed". ## Red flags | Thought | Reality | |---|---| | "I'll just install it, the user obviously wants it" | Installs and config edits get a yes first. Always. | | "The routing text can summarize the pipeline" | Summaries get followed INSTEAD of the skill. Route by name only. | | "Check passed last week" | Plugins update, machines change. Re-check before each heavy run is cheap. |
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
delivering-heavy-features
Roflochinsky
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…
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
delivering-heavy-features
Roflochinsky
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…
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
Cite this page
doctor skill. Agent Mart. https://agentmart.dev/skills/roflochinsky-doctor (last updated 2026-10-24)