aminet-browser
Aminet search and browse: full-text search, category tree navigation, architecture filtering, package detail, and curated collections. Use when searching,…
Unit Circle Laboratory + sc-dev-team autonomous mission control. Provides human-in-the-loop automation layer, pipeline management, context lifecycle, stuck-state prevention. UC re-execution series and dev branch milestones. Adapted from uc-lab pattern for code
$ npx -y skills add Tibsfox/gsd-skill-creator --skill team-control --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/team-controlContext preview
The summary Claude sees to decide when to auto-load this skill.
Unit Circle Laboratory + sc-dev-team autonomous mission control. Provides human-in-the-loop automation layer, pipeline management, context lifecycle, stuck-state prevention. UC re-execution series and dev branch milestones. Adapted from uc-lab pattern for code
name: team-control description: "Unit Circle Laboratory + sc-dev-team autonomous mission control. Provides human-in-the-loop automation layer, pipeline management, context lifecycle, stuck-state prevention. UC re-execution series and dev branch milestones. Adapted from uc-lab pattern for code plan/execute/verify/complete. Auto-activates during UC milestone work; trigger: user says 'bring up the dev team'." format: 2025-10-02 version: 1.0.0 status: ACTIVE updated: 2026-04-15 triggers: - during UC milestone work - user says 'bring up the dev team'
Autonomous mission-control skill with two parameterized modes for the two team branches:
Both modes share the same four-agent architecture, autonomy principles, context management, and stuck-state prevention. The mode is selected by the active branch (UC on `v1.50`, Dev on `dev`) or by explicit invocation. Either way, the team acts as the human-in-the-loop layer so the pipeline never stalls waiting for decisions.
| Agent | Model | Role | Key Responsibility | |-------|-------|------|-------------------| | **lab-director** | Opus | Authority | Go/no-go, plan approval, quality rubric, strategic direction | | **flight-ops** | Opus | Operations | Pipeline management, milestone/phase spawning, error handling | | **capcom** | Sonnet | Communications | Context lifecycle, handoffs, warm starts, continuity | | **watchdog** | Haiku | Monitor | Stuck detection, health checks, overload alerts |
Agent definitions: `.claude/agents/lab-director.md`, `flight-ops.md`, `capcom.md`, `watchdog.md`.
**Team pre-flight (topology check).** Before launching the team — spawning the four agents, or any larger fan-out flight-ops sizes up — run the `spectral-topology-preflight` skill on the proposed communication graph. It builds the row-stochastic operator from the team graph and emits a (ρ, Δ, κ) coordination signature plus a pass/fail verdict against per-task-class thresholds, so coordination defects are caught **pre-dispatch** rather than mid-run. Honor a fail verdict (adjust the topology) before flight-ops spawns work.
1. **lab-director IS the human** — no waiting for external approval 2. **Auto-approve** plans that pass quality gates (TDD, tests, NASA SE or clean commits) 3. **Auto-close** milestones when enforcement checks pass 4. **Auto-handoff** context when pressure detected (>80%) 5. **Auto-scale** parallelism based on observed metrics (UC Mode) 6. **Auto-heal** stuck states via watchdog detection + flight-ops resolution
| Pattern | Detection | Resolution | |---------|-----------|------------| | Waiting for user | Watchdog | lab-director decides | | Context full | Capcom | Handoff protocol | | Agent idle | Watchdog | flight-ops reassigns | | Repeated failure | Watchdog | flight-ops escalates | | Lost state | Capcom | Restore from handoff |
---
Autonomous mission control for the Unit Circle re-execution series (v1.50.14+). Branch-bound to `v1.50`.
QUEUE → PRE-FLIGHT → INIT → PLAN → APPROVE → EXECUTE → VERIFY → ANALYZE → RETRO → CLOSE → HANDOFF → NEXT ↑ | +----------------------------------------------------------------------------------------------------+
| Dimension | Weight | Min Score | |-----------|--------|-----------| | Completeness | 25% | 3.0 | | Depth | 30% | 3.0 | | Connections | 25% | 3.0 | | Honesty | 20% | 3.0 |
Weighted average must be >= 3.0 for auto-approval.
The lab team coordinates with `uc-observatory` agents:
---
Autonomous execution team for dev branch milestones. Adapted from the UC pattern for code execution (plan/execute/verify/complete). Trigger: user says "bring up the dev team" or "sc-dev-team". Branch-bound to `dev`.
1. Read `.planning/STATE.md` for current position 2. Read `~/.claude/teams/sc-dev-team/config.json` for team state 3. Check `TaskList` for pending work 4. Create team if not exists: `TeamCreate(team_name: "sc-dev-team")` 5. Spawn agents into team:
6. Assign first pending task to flight-ops
STATE.md → PLAN PHASE → EXECUTE PHASE → VERIFY → NEXT PHASE → ... → COMPLETE MILESTONE
An adaptive learning and coprocessor architecture for Claude Code, built as an extension to GSD (open-gsd)
Repo: Tibsfox/gsd-skill-creator
Aminet search and browse: full-text search, category tree navigation, architecture filtering, package detail, and curated collections. Use when searching,…
FS-UAE emulator configuration and launch: hardware profiles, ROM management, WHDLoad integration, config generation, and state snapshots. Use when configuring…
Manages Aminet INDEX infrastructure: fetch, parse, cache, and incremental update of ~84,000-entry package database. Use when managing INDEX data, checking…
Aminet package installation: LhA/LZX extraction, Amiga filesystem mapping, dependency detection, install tracking, and scan gate enforcement. Use when…
Selective Aminet package mirroring: single-package fetch, integrity verification, mirror state tracking, bulk download, and sync detection. Use when…
Multi-layer virus scanning for Aminet packages. Signature-based detection, heuristic hunk analysis, boot block scanning, quarantine management, and scan…