agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Auto-populate SDLC artifact metadata headers across all templates using team profile configuration
$ npx -y skills add jmagly/aiwg --skill prefill-cards --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/prefill-cardsContext preview
The summary Claude sees to decide when to auto-load this skill.
Auto-populate SDLC artifact metadata headers across all templates using team profile configuration
namespace: aiwg name: prefill-cards platforms: [all] description: Auto-populate SDLC artifact metadata headers across all templates using team profile configuration
<!-- AIWG-SKILL-CALLOUT --> > **Skill access pattern (post-kernel-pivot, 2026.5+)** > > Skill names referenced in this document are AIWG skills, **not slash commands**. Most are not kernel-listed and cannot be invoked as `/skill-name` by the platform. Reach them via: > > ```bash > aiwg discover "<capability>" > aiwg show skill <name> > ``` > > Only kernel-listed skills (`aiwg-doctor`, `aiwg-refresh`, `aiwg-status`, `aiwg-help`, `use`, `steward`) are directly invokable as slash commands. See [skill-discovery rule](../../../addons/aiwg-utils/rules/skill-discovery.md).
You auto-populate SDLC artifact metadata headers across all templates in the current project using team configuration from `.aiwg/team/team-profile.md`.
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
| Pattern | Example | Action | |---------|---------|--------| | Prefill request | "prefill cards" | Run `aiwg prefill-cards` | | Populate request | "populate metadata" | Run `aiwg prefill-cards` | | Fill templates | "fill sdlc cards" | Run `aiwg prefill-cards` | | Auto-populate | "auto-populate artifacts" | Run `aiwg prefill-cards` | | Dry run | "show what prefill would change" | Run `aiwg prefill-cards --dry-run` | | Specific type | "prefill just the use case cards" | Run `aiwg prefill-cards --type use-cases` |
When triggered:
1. **Extract intent**:
2. **Run the appropriate command**:
# Default: prefill all artifact templates aiwg prefill-cards # Preview only — show what would change aiwg prefill-cards --dry-run # Limit to a specific artifact type aiwg prefill-cards --type use-cases aiwg prefill-cards --type adrs aiwg prefill-cards --type test-plans # Override author (useful when project lead differs from default) aiwg prefill-cards --author "Jane Smith"
3. **Report the result** — summarize how many files were updated and which fields were populated.
Fields populated from `.aiwg/team/team-profile.md`:
| Field | Source | |-------|--------| | `author` | Team lead or assigned role member | | `created` | Current date (ISO 8601) | | `project` | Project name from team profile | | `organization` | Org name from team profile | | `status` | Set to `draft` for new artifacts | | `version` | Set to `0.1` for new artifacts |
Fields that are NOT overwritten if already set (idempotent behavior).
**User**: "We just finished onboarding — go ahead and prefill the cards"
**Extraction**: Full prefill, no overrides
**Action**:
aiwg prefill-cards
**Response**: "Prefilled metadata in 14 artifact templates — use cases (6), ADRs (4), test plans (3), deployment plan (1). Author set to 'Alex Rivera', project set to 'Ingest Pipeline v2', date 2026-04-01."
**User**: "Show me what prefill-cards would do without changing anything"
**Extraction**: Dry-run requested
**Action**:
aiwg prefill-cards --dry-run
**Response**: "Dry run: would update 14 files. Fields to be written: author, created, project, organization, status (draft), version (0.1). No changes made."
**User**: "Just prefill the ADR cards for now"
**Extraction**: Limit to ADR type
**Action**:
aiwg prefill-cards --type adrs
**Response**: "Prefilled metadata in 4 ADR templates. Author set to 'Alex Rivera'."
Reusable project context and specialist workflows for the AI tools you already use. Plan software, coordinate specialist reviews, prepare campaigns, investigate incidents, organize research, curate media, and maintain operational knowledge.
Repo: jmagly/aiwg
Crash-resilient external agent loop with state persistence and CI/CD integration
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern
Enable agent loops to learn from similar past tasks and share patterns across loops
Query and manage the executable feedback debug memory
Execute tests on generated code and iterate until passing