Przejdź do treści
Biblioteka skilli
Programowanie · Pisanie

knowledge-stinger

/knowledge-stinger

Pisze narracyjne dokumenty wiedzy dla repozytorium: przeglądy architektury, diagramy, przepływy uwierzytelniania, opisy schematów i standardy kodowania.

Licencja
AGPL-3.0
Ostatnia zmiana repozytorium
14.10.2026

Ocena i bezpieczeństwo

100/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść35 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
32
Skrypty
3
Komentarze HTML
0
Adresy URL w SKILL.md
1
Przestarzałość

Brak sygnałów. Repozytorium zmienione 14.10.2026, bez odwołań do wycofanych modeli i API.

Licencja

AGPL-3.0, copyleft: przeróbki udostępniane innym muszą mieć tę samą licencję.

Co sprawdzić przed instalacją
  • 3 skrypty w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.

Skrypty: references/examples/diagram-authority/fixtures/flows.py, references/examples/novice-explanation/fixtures/repo/src/data/invoices.ts, references/examples/novice-explanation/fixtures/repo/src/routes/invoices.ts

Co robi i kiedy

Pisze narracyjne dokumenty wiedzy dla repozytorium: przeglądy architektury, diagramy, przepływy uwierzytelniania, opisy schematów i standardy kodowania.

Oryginalny opis (EN)

Write narrative knowledge docs for a repository. Use for architecture overviews, diagrams, auth flows, schema references, or coding standards. Read README.md for the guide map.

Jak działa

  1. What This Skill Produces
  2. Source Material (Always Read First)
  3. The Document Format
  4. Domain taxonomy (choose folders for the target repository)
  5. Analysis Workflow
  6. Companion Resources
  7. Source-grounded diagrams
  8. Audience document packets
Sekcje z nagłówków SKILL.md, w oryginale · 152 linii, 1 046 słów
Podgląd SKILL.md
---
name: "knowledge-stinger"
license: AGPL-3.0-or-later
description: "Write narrative knowledge docs for a repository. Use for architecture overviews, diagrams, auth flows, schema references, or coding standards. Read README.md for the guide map."
---

# 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.
Pliki w paczce (32)
  • README.md 4 KB
  • SKILL.md 9 KB
  • examples/actual-build-journey.md 3 KB
  • examples/beginner-invoice-tour.md 3 KB
  • examples/example-auth-architecture.md 3 KB
  • examples/example-system-overview.md 4 KB
  • guides/01-domain-taxonomy.md 7 KB
  • guides/02-document-format.md 7 KB
  • guides/03-analysis-workflow.md 9 KB
  • guides/04-beginner-repository-tour.md 3 KB
  • guides/05-turn-meeting-sources-into-decision-drafts.md 5 KB
  • guides/06-preserve-behavior-in-diagrams.md 6 KB
  • references/examples/diagram-authority/receipts.json 6 KB
  • references/examples/diagram-authority/worked-cases.md 8 KB
  • references/examples/diagram-authority/fixtures/draft-teaching-intention.txt 1 KB
  • references/examples/diagram-authority/fixtures/flows.py 1 KB
  • references/examples/meeting-decisions/receipts.json 5 KB
  • references/examples/meeting-decisions/worked-drafts.md 3 KB
  • references/examples/meeting-decisions/fixtures/teaching-notes.txt 1 KB
  • references/examples/novice-explanation/evidence/actual-build-ledger.json 6 KB
  • references/examples/novice-explanation/evidence/qualification.json 1 KB
  • references/examples/novice-explanation/evidence/source-claims.json 9 KB
  • references/examples/novice-explanation/evidence/source-exercise-review.md 4 KB
  • references/examples/novice-explanation/fixtures/prd/PRD-001-invoice-notes.md 1 KB
  • references/examples/novice-explanation/fixtures/repo/README.md 1 KB
  • references/examples/novice-explanation/fixtures/repo/contracts/invoice-read.md 1 KB
  • references/examples/novice-explanation/fixtures/repo/src/data/invoices.ts 1 KB
  • references/examples/novice-explanation/fixtures/repo/src/routes/invoices.ts 1 KB
  • references/templates/meeting-decision-action-drafts.md 2 KB
  • references/templates/source-grounded-diagram.md 2 KB
  • templates/beginner-repository-tour.md 1 KB
  • templates/knowledge-doc-template.md 2 KB

Wersje

W bazie nie ma innych skilli o nazwie knowledge-stinger.

Migawka bazy z 13.11.2026 · wersja paczki 68836ad7e9a4 (skrót SHA-256 całej paczki)

Pobrania w ostatnich 30 dniach: 0 · ranking

Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.

Podobne skille

  • 95library-stinger
    Utrzymuje dokumenty Library Schema v2 i szablony przepływów pracy: PRD, IRD, dokumenty wiedzy, zmiany cyklu życia, import zgłoszeń i audyty dryfu.
  • 100readme-writing-stinger
    Pisze i audytuje pliki README jako strony docelowe: propozycja wartości, instalacja, badge'e, struktura i kontekst narzędzi wewnętrznych.
  • 85atlas
    Tworzy dokumentację architektury: ADR, diagramy, changelogi, materiały wdrożeniowe i raporty o tym, co zmieniło się w projekcie.
  • 90update-docs
    Sprawdza i aktualizuje dokumentację repozytorium przed utworzeniem PR lub MR: nieaktualne dokumenty, diagramy mermaid, README i API.
  • 100write-architecture-docs
    Pisze i przegląda dokumenty architektury podsystemów oraz ADR-y dla zespołu inżynierskiego w katalogu docs.
  • 100coding-standards
    Pisze, aktualizuje i sprawdza plik CODING_STANDARDS.md i zamienia błędy z sesji lub przeglądu w reguły kodowania.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.