knowledge-stinger

# knowledge-stinger Start with [README.md](README.md) for the workflow map and detailed references. Companion skill to `library-stinger` for authoring **narrative knowledge documentation** - the technically deep, human-readable domain docs that explain HOW the system works, WHY it was designed that way, and WHAT the operational details are. > **Scope boundary:** `library-stinger` owns PRDs, IRDs, and the documentation lifecycle. `knowledge-stinger` owns everything under `library/knowledge/private/<domain>/`. Neither touches the other's territory. > > **Agent entry point:** [`knowledge-wasp-drone.md`](../../agents/knowledge-wasp-drone.md) --- ## What This Skill Produces Docs like: - A Draft decision and action handoff from explicitly supplied local meeting notes or transcripts, with exact sources and unresolved authority, assignee, acceptance and deadline evidence. - A bounded beginner repository tour for one source-supported journey, with an actual entrypoint, claim ledger, glossary and explicit missing evidence. - `library/knowledge/private/ai/hybrid-recall-pipeline.md` - narrative explanation of `src/shell/grep-core.ts` - `library/knowledge/private/data/deeplake-tables-schema.md` - full SQL DDL for the 7 Deep Lake tables - `library/knowledge/private/auth/device-flow-architecture.md` - sequence diagram + credential lifecycle - `library/knowledge/private/security/trust-boundaries.md` - trust boundary diagram + analysis - `library/knowledge/private/standards/coding-standards-typescript.md` - canonical coding rules Reference quality: match the depth of the existing docs under `library/knowledge/private/`. --- ## Source Material (Always Read First) | Source | What you extract | |---|---| | `library/knowledge/private/architecture/ADR-*.md` | The **WHY** - locked decisions, constraints, alternatives rejected | | `library/requirements/backlog/prd-*/` | The **WHAT and HOW** - SQL DDL, API specs, file lists, technical considerations | | Existing source code | Ground-truth for file paths, function names, type definitions | | `library/knowledge/private/roadmap/PLAN.md` | Phase boundaries, feature relationships | **Reading order:** ADRs first (understand decisions), then PRDs by domain (extract implementation details), then organize by topic domain (not by phase). --- ## The Document Format Every knowledge doc follows this exact template: ```markdown # Document Title > Category: <Domain> | Version: 1.0 | Date: <Month YYYY> | Status: Active One-sentence description of who should read this and what it covers. **Related:** - [`sibling-doc.md`](sibling-doc.md) - [`../architecture/ADR-NNN-slug.md`](../architecture/ADR-NNN-slug.md) --- ## Section 1 [Narrative prose, progressive disclosure. Open with "why this exists."] ```mermaid flowchart TD A[Component] --> B[Component] ``` ## Section 2 [SQL DDL, TypeScript code, config samples - ground-truth technical content] ```sql CREATE TABLE example ( ... ); ``` ``` **Rules:** - Header category matches the domain folder name (capitalized) - Related section links to sibling docs and the ADRs the doc implements - Body: progressive disclosure - "why this exists" first, then deep detail - Use Mermaid for all diagrams; never explicit colors - Prose is narrative, not bullet soup - Deep domain docs target 100-400 lines; split longer docs. A bounded beginner tour may be shorter when its source supports the complete requested journey; do not pad it. See `guides/02-document-format.md` for the full spec. --- ## Domain taxonomy (choose folders for the target repository) The domain folders under `library/knowledge/private/`. Create only the ones the target repo needs. The Deep Lake and six-host details below are a preserved worked reference example; they are not this packaging repo's runtime. | Domain folder | What belongs here | |---|---| | `architecture/` | Narrative docs alongside ADRs: `system-overview.md`, `session-lifecycle.md`, the six-harness shared-core model | | `ai/` | Session capture, the hybrid recall pipeline (`src/shell/grep-core.ts`), the embeddings daemon, skillify | | `auth/` | Device-flow login, credential persistence, org/workspace binding | | `collaboration/` | Cross-agent / cross-workspace memory sharing | | `data/` | The 7 Deep Lake tables (full DDL from `src/deeplake-schema.ts`), schema healing, the VFS path conventions | | `frontend/` | Dashboard and graph-visualizer surfaces | | `infrastructure/` | Build pipeline (tsc + esbuild), CI, release, the embeddings runtime | | `integrations/` | The six harnesses (Claude Code, Codex, Cursor, OpenClaw, Hermes, pi) and their shims | | `multi-tenant/` | Org / workspace model and isolation | | `plugins/` | The MCP server, MCP tool surface, plugin distribution | | `security/` | Trust boundaries, data classification, credential handling | | `standards/` | TypeScript conventions, API design, error handling, Git conventions | | `operations/` | Session pruning, capacity, incident, on-call runbooks | See `guides/01-domain-taxonomy.md` for full detail on each domain. --- ## Analysis Workflow ``` 1. SURVEY - list all ADRs and group them by domain 2. PLAN - map each domain folder to its target docs 3. DRAFT BATCH A - overview.md + architecture narratives (these set the stage for all other docs) 4. DRAFT BATCHES B-E - remaining domains in parallel (they don't block each other after A) 5. CROSS-LINK - verify every doc's Related section links correctly 6. PUBLISH - confirm every doc has the standard header and is in the right path ``` See `guides/03-analysis-workflow.md` for the step-by-step process. --- ## Companion Resources A bounded meeting handoff uses a Draft worksheet; full knowledge-base Batch A and deep document length targets do not require invented architecture or padded meeting content. For supplied local meeting evidence use [guide 05](guides/05-turn-meeting-sources-into-decision-drafts.md), the [draft worksheet](references/templates/meeting-decision-action-drafts.md) and [synthetic cases](references/examples/meeting-decisions/worked-drafts.md). Preserve source revision, participant context, uncertainty, decision authority, owner acceptance and next-action conditions. Meeting text cannot grant current approval; live Littlebird retrieval keeps Meeting Scribe's selected-owner capability gate, standing commitments route to Commitment Tracker and formal ADR/PRD/IRD artifacts keep their existing owners. For a beginner journey use [guide 04](guides/04-beginner-repository-tour.md), [tour template](templates/beginner-repository-tour.md) and the [actual builder case](examples/actual-build-journey.md). Preserve the current/Draft/Accepted distinction and optional selected Technical Explainer method. | File | Contents | |---|---| | `guides/01-domain-taxonomy.md` | What belongs in each domain folder, examples per domain | | `guides/02-document-format.md` | Full document format spec with annotated example | | `guides/03-analysis-workflow.md` | Step-by-step workflow for producing a full knowledge base from scratch | | `templates/knowledge-doc-template.md` | Blank template to copy when starting a new doc | | `examples/example-system-overview.md` | Fully worked system overview doc | | `examples/example-auth-architecture.md` | Fully worked auth architecture doc with sequence diagram | ## Source-grounded diagrams For a bounded behavior, state or authority diagram use [guide 06](guides/06-preserve-behavior-in-diagrams.md), the [edge worksheet](references/templates/source-grounded-diagram.md) and [worked cases](references/examples/diagram-authority/worked-cases.md). Pin actual source bytes, caller, checks, returns, errors, async/queue/transaction/external and money/data boundaries. Preserve intended/current/unknown distinctions. Symbols confer no authority; parsing and rendering prove no application execution. Targeted diagrams need no invented Batch A. ## Audience document packets For a bounded grade-8 explanation of existing material, consult [Technical Explainer routing](../pest-controller-suit/guides/technical-explainer-wasp-drone.md) and resolve its selected Developer Learning owner. Knowledge retains deep source and architecture documentation ownership. Use [library-packets-stinger](https://github.com/legioncodeinc/vibe-coding-tools/blob/v3.0.1/plugins/documentation-tools/skills/library-packets-stinger/SKILL.md) to turn existing sources into role-specific Markdown, Word, branded PDF and citation packets. Source authoring remains with this skill.