conductor
Multi-phase delivery framework that MUST preserve session continuity and SHOULD support SHA-based rollback.
Skill by gc-victor
Chalk Labs
Need help deploying conductor?
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/gc-victor-conductor
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/conductor
What's inside
- Skill name
conductor- Description
- Multi-phase delivery framework that MUST preserve session continuity and SHOULD support SHA-based rollback.
- License
- MIT
- Instructions
- 90 lines in SKILL.md · view on GitHub
Files (6)
- SKILL.md
- codebase-analysis-integration.md · references/
- contracts.md · references/
- planning-protocol.md · references/
- state-integrity.md · references/
- workflow-governance.md · references/
SKILL.md (first lines)
# Conductor ## Core Responsibilities 1. Validate the Conductor environment and load the target track. 2. Coordinate task execution across the right skills and agents. 3. Keep task and track state current. 4. Record commit SHAs in `log.md`. 5. Enforce the double-review gate: review approval plus human confirmation. 6. Run codebase health checks after each phase and at track completion. 7. Sync documentation when needed. 8. Help close, pause, or archive tracks. ## Orchestration Rules - Prefer skills over agents when possible. - Do not implement code directly. - Use implementation skills for code changes. - Use review skills for code review. - Use writing skills for documentation. - Manage track state directly only in tracking files. ## Execution Workflow ### Phase 1: Setup and Track Selection 1. Verify `.conductor/` exists. 2. Read the global context files: - `meta.json` - `guidelines.md` - `stack.md` - `style.md` - `workflow.md` 3. Verify that `.conductor/tracks/` exists. 4. Load the target track files. 5. Treat `workflow.md` as the source of truth. ### Phase 2: Task Execution Loop For each task: 1. Prepare - Load the task details and dependencies. - Read the matching Task Content entry from `spec.md`. - Block execution if the Task Content entry is missing. 2. Implement - Follow TDD: RED, GREEN, REFACTOR. 3. Verify - Check atomicity. - Run tests. - Run diagnostics. - Run review. - Wait for human approval. 4. Mark complete - Update `plan.md`. - Update progress. - Record the commit SHA in `log.md`. - Update `metadata.json`. 5. Continue or pause - Present the result and ask what to do next. ### Phase 3: Phase Completion 1. Mark the phase complete. 2. Run full verification. 3. Run mandatory codebase health analysis. 4. Present findings and user choices. 5. Document the result in `log.md`. After each track: update relevant docs if needed, and check whether `guidelines.md`, `stack.md`, `style.md`, or `workflow.md` need updates. ### Phase 4: Track Completion 1. Run final verification. 2. Run a full codebase health check. 3. Document overall health impact. 4. Mark the track complete. 5. Offer retrospective and archival actions. See `references/contracts.md` for agent contracts. ## Resources - `references/contracts.md` - `references/planning-protocol.md` (canonical planning ownership) - `references/state-integrity.md` - `references/workflow-governance.md` - `references/codebase-analysis-integration.md`
From gc-victor/supersimple, MIT.
More from gc-victor/supersimple
- 0.562score
security
gc-victor
Hardens code against vulnerabilities.
SkillCFreshness: C★ 33Claude Code +9 - 0.556score
debug
gc-victor
Debugging workflow that MUST reproduce, investigate, fix, and verify unexpected behavior.
SkillCFreshness: C★ 33Claude Code +9 - 0.556score
code-quality
gc-victor
Code-quality review that MUST assess five quality axes and SHOULD apply the ReAct checklist with prioritized fixes.
SkillCFreshness: C★ 33Claude Code +9 - 0.556score
simplify
gc-victor
Refinement pass that MUST preserve behavior and SHOULD make recent changes clearer and more consistent.
SkillCFreshness: C★ 33Claude Code +9 - 0.551score
deslop
gc-victor
Cleanup pass that MUST remove filler and SHOULD tighten code, docs, and Markdown.
SkillCFreshness: C★ 33Claude Code +9
Signals
- Stars
- 33
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 30, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/gc-victor/supersimple
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from gc-victor
- 0.562score
security
gc-victor
Hardens code against vulnerabilities.
SkillCFreshness: C★ 33Claude Code +9 - 0.556score
debug
gc-victor
Debugging workflow that MUST reproduce, investigate, fix, and verify unexpected behavior.
SkillCFreshness: C★ 33Claude Code +9 - 0.556score
code-quality
gc-victor
Code-quality review that MUST assess five quality axes and SHOULD apply the ReAct checklist with prioritized fixes.
SkillCFreshness: C★ 33Claude Code +9 - 0.556score
simplify
gc-victor
Refinement pass that MUST preserve behavior and SHOULD make recent changes clearer and more consistent.
SkillCFreshness: C★ 33Claude Code +9 - 0.551score
deslop
gc-victor
Cleanup pass that MUST remove filler and SHOULD tighten code, docs, and Markdown.
SkillCFreshness: C★ 33Claude 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 conductor 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
conductor skill. Agent Mart. https://agentmart.dev/skills/gc-victor-conductor (last updated 2026-10-24)