armelhbobdad/bmad-module-ultracode-goal / skills/ultracode-goal
ultracode-goal
FlaggedRuns a BMAD Epic autonomously to a machine-checked Definition-of-Done. Use when the user requests to 'run an epic autonomously', 'execute this epic', 'ultracode goal', or 'autonomously deliver the epic'.
assets/ucg-awareness/bmad-testarch-test-design.toml
View on GitHub# UCG awareness fragment for bmad-testarch-test-design.
# Additive guardrail facts landing in the one universal sanctioned append channel
# (persistent_facts, authored top-level here; merge_customization.py re-homes them
# into the target's nested [workflow].persistent_facts). The gate, not this shaping,
# is load-bearing; a plain run is unaffected or strictly improved.
# Idempotent strip-then-reappend is merge_customization.py's concern, matched by the
# per-directive [ucg:{skill}-NN] id marker each entry carries.
#
# WIRING: authored, not auto-enrolled. The installer's Step 6b enrolls only the four
# planning-workflow fragments (bmad-prd, bmad-architecture, bmad-create-epics-and-stories,
# ucg-create-story); the TEA fragments are deliberately excluded there, so a stock install
# never merges this file. It applies only when an operator runs it explicitly:
# merge_customization.py --target _bmad/custom/bmad-testarch-test-design.toml \
# --fragment <this file> (--remove to uninstall)
# Until then this shaping is inert and the gate alone is load-bearing, as above.
persistent_facts = [
"Extract every NFR threshold (latency, size, count, rate, timeout) from the PRD, architecture, ADRs, epics, or stories and cite the source artifact it came from; never guess a number — a genuinely-unknown threshold is marked UNKNOWN and converted into a risk, assumption, or deferral rather than an invented value. [ucg:bmad-testarch-test-design-01]",
"Populate the risk matrix with genuine risks (not features), each carrying a unique id, a category (TECH/SEC/PERF/DATA/BUS/OPS), and probability x impact scores (1-3 each); any risk scoring 6 or higher must carry a stated mitigation. [ucg:bmad-testarch-test-design-02]",
"When a risk row states both probability and impact, fill its score cell with the probability x impact product; if a stated score disagrees with the stated probability and impact, reconcile it rather than leaving the conflict — the score is arithmetic from the two factors, not a free number. [ucg:bmad-testarch-test-design-03]",
"Assign P0-P3 priorities honestly (P0 = blocks a core flow, high risk, no workaround); TEA owns the coverage percentages, so state the priorities truthfully and do not restate or recompute the threshold percentages here. [ucg:bmad-testarch-test-design-04]",
"Run in Create mode at Epic-Level so the plan is a fresh deterministic artifact, never a stalled interactive resume; a legal sprint-status makes the Epic-Level selection automatic. [ucg:bmad-testarch-test-design-05]",
"Write every test-design artifact under the configured trace_output / test_artifacts root; never leave a test-design plan, risk matrix, or any TEA artifact in the source or implementation tree. [ucg:bmad-testarch-test-design-06]",
"These are run-scoped guardrail facts that shape test-design to be ready-by-construction; they are narrower than per-AC directives and are not the verdict. A story is ready only when the gate says so, and these facts are additive guidance a plain run can ignore with no harm. [ucg:bmad-testarch-test-design-07]",
]
[ucg]
managed = true
version = "0.3.0"
block = "ucg-awareness"
installed_at = "2026-06-26T00:00:00Z"
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |