Przejdź do treści
Biblioteka skilli
AI i agenci · Research

context-gather

/context-gather

Zbiera kontekst z pamięci Serena, dokumentacji Context7, DeepWiki i internetu przed planowaniem lub wdrożeniem i zwraca zwięzłe podsumowanie.

Repozytorium
ai-agents ↗
Licencja
MIT
Ostatnia zmiana repozytorium
25.10.2026

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
2
Skrypty
0
Komentarze HTML
0
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 25.10.2026, bez odwołań do wycofanych modeli i API.

Licencja

MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.

Co robi i kiedy

Zbiera kontekst z pamięci Serena, dokumentacji Context7, DeepWiki i internetu przed planowaniem lub wdrożeniem i zwraca zwięzłe podsumowanie.

Wyzwalacze z opisu

gather context before planningwhat do we know before I start
Oryginalny opis (EN)

Gather comprehensive context from Serena memory, Context7 docs, DeepWiki, and web sources before planning or implementation. Searches across all knowledge tiers and returns a focused summary ending in a CONTEXT_LOADED marker that this skill scans to skip a repeat fetch in the same conversation. Use when you say "gather context before planning", "what do we know before I start". Do NOT use for compressing or placing skill text (use context-optimizer).

Jak działa

  1. Triggers
  2. Quick Reference
  3. When to Use
  4. When to Skip
  5. Process
  6. Extension Points
  7. Tools
  8. Anti-Patterns
  9. Verification
  10. References
Sekcje z nagłówków SKILL.md, w oryginale · 128 linii, 945 słów
Podgląd SKILL.md
---
name: context-gather
version: 1.1.1
description: Gather comprehensive context from Serena memory, Context7 docs, DeepWiki, and web sources before planning or implementation. Searches across all knowledge tiers and returns a focused summary ending in a CONTEXT_LOADED marker that this skill scans to skip a repeat fetch in the same conversation. Use when you say "gather context before planning", "what do we know before I start". Do NOT use for compressing or placing skill text (use context-optimizer).
license: MIT
---

# Context Gather

Collect multi-source context before planning or implementation. Searches Serena, Context7, DeepWiki, and web sources, then returns a focused summary. The closing `CONTEXT_LOADED:` marker is read only by this skill's own Phase 1 scan, which skips a repeat fetch for the same topic in one conversation.

> **Model choice (behavior change from prior `/context-gather` slash command)**: this skill's frontmatter carries no `model` field, so it inherits the harness default rather than the slash command's pinned `opus`. Context retrieval is search-and-synthesis work, not deep reasoning. Skill behavior is otherwise unchanged.

## Triggers

| Phrase | Context |
|--------|---------|
| `gather context for` | User requests pre-work context collection |
| `context-gather` | Direct skill invocation, or autoplan routing an unfamiliar topic here before research (SPEC-005) |
| `what do we know about` | Exploratory context retrieval |

## Quick Reference

| Field | Value |
|-------|-------|
| Input | Task description or technology topic (free text) |
| Output | Focused summary with code snippets, architectural insights, and `CONTEXT_LOADED: <topic>` marker |
| Quality Gate | Summary addresses the stated topic; at least one queried tier reconciled (short-circuit and early-stop exempt); marker line present |

## When to Use

Use this skill when:

- Starting a complex task that needs multi-source context before planning or implementation.
- autoplan routes an unfamiliar-topic request here before `research`.
- You need to pull framework-specific guidance from Context7 alongside project memory.
- Exploring what the memory tiers already record about a topic before committing to an approach.

## When to Skip

Skip this skill when:

- A `CONTEXT_LOADED: <topic>` marker for the same topic already exists in the current conversation. Do not re-fetch.
- The task is trivial and single-step (no external context needed).
- You already have sufficient context from a prior skill invocation or manual research.
- The topic is purely internal to the current file (no cross-cutting concerns).

## Process

### Phase 1: Check for Prior Invocation

1. Scan the current conversation for an existing `CONTEXT_LOADED:` marker line.
2. If a marker exists whose topic matches the current request, report "Context already loaded for <topic>" and stop. Do not re-fetch.

### Phase 2: Search Across Knowledge Tiers

Follow [references/context-retrieval.md](references/context-retrieval.md) for
the source-priority strategy, the untrusted-content guard, and the synthesis and
citation discipline.

1. Search the following tiers, in parallel where possible:
   - **Serena Memory**: Always first. Read this project's memories for prior decisions, patterns, and ADRs on the topic.
   - **Context7**: Query framework-specific documentation if the topic involves a known library or SDK.
   - **DeepWiki**: Read repository-level documentation for relevant GitHub repos.
   - **Web Search**: Fall back to web sources only when memory and docs are insufficient.
2. Stop early once the queried tiers give sufficient coverage for the request.
3. For each tier actually queried, emit a marker line:

```text
TIER_QUERIED: <tier>
```

Where `<tier>` is one of: `serena`, `context7`, `deepwiki`, `web`. Emit one `TIER_QUERIED:` line per tier actually queried.

### Phase 3: Synthesize, Emit Marker, and Return

1. Combine findings into a focused summary. Include:
   - Relevant code snippets and file paths.
   - Architectural insights and ADR references.
   - Framework-specific guidance (if applicable).
   - Gaps or unknowns that remain.
2. Emit the marker line at the end of the summary output:

```text
CONTEXT_LOADED: <topic>
```

Where `<topic>` is a short, normalized label for the subject (e.g., `pytest-fixtures`, `session-protocol`, `react-server-components`).

3. Return the summary and marker to the calling skill or user. Only this skill's Phase 1 scan reads the marker; no other skill checks it.

## Extension Points

1. **Additional knowledge tiers**: new MCP servers (e.g., a future code-search server) slot into Phase 2 without changing the skill structure.
2. **Marker protocol**: the `CONTEXT_LOADED:` format can be extended with metadata (e.g., `CONTEXT_LOADED: <topic> [tier=serena,context7]`) to convey which sources were queried.

## Tools

This skill searches the knowledge tiers using:

- `mcp__serena__read_memory`, `mcp__serena__list_memories`
- `mcp__context7__resolve-library-id`, `mcp__context7__get-library-docs`
- `mcp__deepwiki__read_wiki_structure`, `mcp__deepwiki__read_wiki_contents`, `mcp__deepwiki__ask_question`
- `WebSearch`, `WebFetch`

## Anti-Patterns

| Avoid | Why | Instead |
|-------|-----|---------|
| Re-fetching when marker exists | Wastes tokens and time; duplicates context | Check for `CONTEXT_LOADED:` marker first |
| Querying all sources sequentially | Slow; unnecessary when early sources suffice | Query in parallel; stop early if coverage is sufficient |
| Returning raw tool output | Floods context window; not actionable | Synthesize into a focused summary with citations |
| Skipping the marker emission | A repeat invocation in the same conversation cannot detect the prior fetch | Always emit `CONTEXT_LOADED: <topic>` at the end |
| Using opus model for retrieval | Context gathering is search and synthesis, not deep reasoning | Use sonnet (cost-appropriate) |

## Verification

After execution, confirm:

- [ ] Reconciliation (fetch path only): `grep -c '^TIER_QUERIED:' <output>` >= 1, with one `TIER_QUERIED: <tier>` line per source actually queried. Exempt when the skill short-circuited on a prior `CONTEXT_LOADED:` marker (no tiers queried) or early-stopped after one source gave sufficient coverage.
- [ ] Summary addresses the stated topic with specific findings, not generic advice.
- [ ] `CONTEXT_LOADED: <topic>` marker line is present at the end of output.
- [ ] No raw tool output was returned; findings are synthesized.
- [ ] If a prior marker existed for the same topic, the skill short-circuited without re-fetching.

## References

| Artifact | Relationship |
|----------|-------------|
| SPEC-005 REQ-005 | Acceptance criteria AC-12 defines runtime-conditional skip via `CONTEXT_LOADED:` marker |
| SPEC-005 DESIGN-005 | Historical design for per-command preflight wiring; ADR-064 retired the commands, so no current skill checks the marker |
| `.claude/skills/steering-matcher/SKILL.md` | Sibling preflight skill in the `/build` chain |
| `.claude/skills/chestertons-fence/SKILL.md` | Sibling preflight skill in the `/build` chain |
Pliki w paczce (2)
  • SKILL.md 7 KB
  • references/context-retrieval.md 5 KB

Wersje

W bazie nie ma innych skilli o nazwie context-gather.

Identyczna treść występuje jeszcze w 4 innych folderach na GitHubie. Tu pokazujemy jedną, najlepiej ocenioną kopię.

Migawka bazy z 13.11.2026 · wersja paczki 9aaa27995a72 (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

  • 100context-hub-setup
    Sprawdza, czy zainstalowano wtyczki Serena i Context7, i raportuje braki wraz z poleceniem instalacji każdej z nich.
  • 100context-hub-setup
    Sprawdza, czy działają wtyczki Serena i Context7, i podaje polecenia instalacji dla brakujących elementów, gdy łączność MCP szwankuje.
  • 93serena-usage
    Używa Serena MCP do pamięci projektu i nawigacji po kodzie: zarządza zapisami pamięci, symbolami, refaktoryzacją i ciągłością kontekstu między sesjami agentów.
  • 100get-context
    Zbiera kontekst kodu dla repozytorium, biblioteki lub pytania o technologię przez DeepWiki, Context7, Exa, klonowanie git i wyszukiwanie w sieci.
  • 100gather-context
    Ustala intencję zadania, wykorzystuje zweryfikowane dowody i pozyskuje brakujący kontekst planowania, tworząc Context Map bez ładowania surowych dokumentów do głównej rozmowy.
  • 100gather-business-context
    Zbiera kontekst biznesowy z podłączonych lub podanych źródeł, zanim analiza ruszy, np. co oznacza metryka i co się ostatnio zmieniło.

Uwagi i zgłoszenia

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