Skip to content

Explore Cloud Local Providers API keys Developers Docs

Explore

MCP servers and skills: search, filter by where they run, and compare.

Conduit

The open directory of tools for AI agents. Free to browse, honest about what runs where.

Catalog

Explore
Cloud tools
Local tools
Skills
Categories

Developers

List your project
Documentation
Public API
llms.txt

Account

Sign in
Dashboard

Conduit lists open-source projects by their authors. Listing is not an endorsement or a security review.

Privacy Termsv2026.10.14-98

No tools match “”.

↑↓ navigate openesc close

Explore tools · Conduit

Explore Cloud Local Providers API keys Developers Docs

Filters2ShowHide

More filters

More filters

Search the catalog

All17
Local17
Local + Cloud0
Hosted0
Cloud only0

1–17 of 17 tools for “merge-split”

Skills Databases Clear all

Nothing matches every word exactly, so these are the closest matches.

markdown-no-artificial-line-wrapsprisma
Local
Writes and edits Markdown without inserting manual hard line breaks at a fixed column (e.g. 72 or 80). GitHub, docs sites, and editors soft-wrap prose; artificial breaks make diffs noisy and reflow aw
in the skill textexplicit breaks where semantics require them. 3. **Links and emphasis** — Prefer not splitting a paragraph so that a ` text ` link is alone on a continuation line
OfficialSkillApache-2.0★ 48k in collectionNo key

Local runs on your computer · Local + Cloud also runs on Conduit’s servers · Hosted is run by its author, you connect by URL

qdrant-indexing-performance-optimizationgithub

Local

Diagnoses and fixes slow Qdrant indexing and data ingestion. Use when someone reports 'uploads are slow', 'indexing takes forever', 'optimizer is stuck', 'HNSW build time too long', or 'data uploaded

in the skill textbad'. Also use when optimizer status shows errors, segments won't merge, or indexing threshold questions arise. # What to Do When Qdrant Indexing Is Too Slow

OfficialSkillMIT★ 40k in collectionNo key

qdrant-indexing-performance-optimizationqdrant

Local

Diagnoses and fixes slow Qdrant indexing and data ingestion. Use when someone reports 'uploads are slow', 'indexing takes forever', 'optimizer is stuck', 'HNSW build time too long', or 'data uploaded

in the skill textbad'. Also use when optimizer status shows errors, segments won't merge, or indexing threshold questions arise. # What to Do When Qdrant Indexing Is Too Slow

OfficialSkillApache-2.0★ 256 in collectionNo key

langchain-raglangchain-ai

Local

INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecon

in the skill textfetching relevant context from external knowledge sources. **Pipeline:** 1. **Index**: Load → Split → Embed → Store 2. **Retrieve**: Query → Embed → Search → Return docs 3. **Generate**: Docs + Query → LLM

OfficialSkillMIT★ 1.3k in collectionNo key

audit-flowArunJRK

Local

Claude Code skill for interactive system flow tracing across CODE, API, AUTH, DATA, NETWORK layers. SQLite persistence, Mermaid export, git merge driver.

SkillMIT★ 15No key

publish-npm-versionprisma

Local

Cuts the next release of Prisma 8: bumps the root package.json version (on the v8 RC line: 8.0.0-rc.N → rc.N+1), propagates it to every workspace package, and opens a PR titled "chore(release): bump t

in the skill textthe matching prisma/web docs-site PR from the same release notes, to merge once the release is published. Use when a maintainer asks to "cut the

OfficialSkillApache-2.0★ 48k in collectionNo key

qdrant-search-qualitygithub

Local

Diagnoses and improves Qdrant search relevance. Use when someone reports 'search results are bad', 'wrong results', 'low precision', 'low recall', 'irrelevant matches', 'missing expected results', or

in the skill textinspect how chunks are being passed to Qdrant before tuning any parameters. Splitting mid-sentence can drop quality 30-40%. - Start by testing with exact search

OfficialSkillMIT★ 40k in collectionNo key

qdrant-scaling-query-volumegithub

Local

Guides Qdrant query volume scaling. Use when someone asks 'query returns too many results', 'scroll performance', 'large limit values', 'paginating search results', 'fetching many vectors', or 'high c

in the skill texteach shard for a smaller limit computed via Poisson distribution statistics, then merge. This is safe because auto-sharding guarantees random, independent data distribution. ## When

OfficialSkillMIT★ 40k in collectionNo key

create-prprisma

Local

Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for revie

in the skill textTML-2375: 5 new pgvector operator descriptors + HNSW index support` - `TML-2456: split contract emission into two phases` ### Step 4: Compose the PR Description The

OfficialSkillApache-2.0★ 48k in collectionNo key

contrib-prprisma

Local

Open a high-quality external contributor PR against prisma/orm. Use when the user is an outside contributor (not a Prisma maintainer) and wants to submit a change as a pull request from a fork. Encode

in the skill textcleanup or "while I was here" fixes, ask the user whether to split them into separate PRs. Mixed-scope PRs almost always trigger a "please split

OfficialSkillApache-2.0★ 48k in collectionNo key

bigquery-expertjustvinhhere

Local

BigQuery Skills - Claude Code plugin that makes Claude a BigQuery expert. 5 skills covering query optimization, SQL generation, schema design, cost optimization, and BigQuery-specific features. Detect

in the skill textviews, query caching, storage management, and dry-run estimation. | | **BigQuery Features** | STRUCT/ARRAY/UNNEST, MERGE DML, scripting, JSON functions, approximate aggregation, geography, BigQuery ML, search indexes, and vector

SkillApache-2.0★ 16No key

apify-google-maps-leadsapify

Local

Build a local-business lead database from Google Maps in one Apify pipeline: search by target audience + geography, enrich each place with company contacts from its website, leads enrichment (names, e

in the skill texttext. Examples: `"dentists"`, `"vegan restaurants"`, `"boutique hotels"`, `"dog groomers, pet stores"` (comma-splittable → array). 2. **Target geography** — one location per run. City + country reads best (`"Berlin

OfficialSkillApache-2.0★ 275 in collectionNo key

dbckitcanforge

Local

Parse, edit, validate, diff, and encode/decode DBC (CAN database) files in Python

in the skill textDBC content - apply deterministic edits and write the result back out - diff, merge, extract, and search databases - decode CAN log files (`.asc` built in, extensible readers

SkillMITFew starsNo key

triage-contributor-prprisma

Local

Triage open pull requests from external contributors to prisma/orm and produce a per-PR verdict with evidence. Use when a maintainer asks to triage, evaluate, assess, or review the queue of incoming c

in the skill textSigned-off-by:\\s*(? .+)").v) // "MISSING") \(.messageHeadline)"' wip/pr-triage/pr- .json ``` The app skips merge commits, so a merge commit made in GitHub's web UI ("Merge branch

OfficialSkillApache-2.0★ 48k in collectionNo key

bigquery-pipeline-auditgithub

Local

Audits Python + BigQuery pipelines for cost safety, idempotency, and production readiness. Returns a structured report with exact patch locations.

in the skill text/append with no dedup logic. Each write should use one of: 1. `MERGE` on a deterministic key (e.g., `entity_id + date + model_version`) 2. Write

OfficialSkillMIT★ 40k in collectionNo key

gke-backup-drgoogle

Local

Configures Backup for GKE: the BackupRestore cluster addon, BackupPlan and RestorePlan resources, restore workflows, and CMEK-encrypted backups. Use for backup policies, disaster recovery, or GKE clus

in the skill textresource-restore-mode=fail-on-conflict` aborts on any conflict (safe default); `merge-skip-on-conflict` skips conflicting resources; `merge-replace-on-conflict` and `merge-replace

OfficialSkillApache-2.0★ 21k in collectionNo key

oracle-apex-ai-skillsandre-simplifica

Local

Vibe coding for Oracle APEX 24.2. Stop hand-building pages; let AI agents inspect, generate, validate, and follow your project standards.

in the skill textthis kit | | APEX 24.2 through releases before 26.1 | Supported; standard SQL split + readable YAML + monolithic SQL export | | APEX 26.1 or later | Supported; 26.1 public APIs are

SkillMIT★ 20No key

API key

Either17
No key needed17
Needs a key0

API key

Either17
No key needed17
Needs a key0

What it is

Any17
Skills (SKILL.md)17
Subagents0
Commands0
Rules0
Instructions0

What it is

Any17
Skills (SKILL.md)17
Subagents0
Commands0
Rules0
Instructions0

Written in

Any17
Node.js (npx)0
Python (uvx / pip)1
Go0
Docker0

Written in

Any17
Node.js (npx)0
Python (uvx / pip)1
Go0
Docker0

Who stands behind it

Anyone17
Official13
Verified owner0
Community4

Who stands behind it

Anyone17
Official13
Verified owner0
Community4

License type

Any type17
Open source · permissive17
Open source · weak copyleft0
Open source · copyleft0
Source-available0
No licence0
Proprietary0
Hosted service0
Licence not read yet0

License type

Any type17
Open source · permissive17
Open source · weak copyleft0
Open source · copyleft0
Source-available0
No licence0
Proprietary0
Hosted service0
Licence not read yet0

License

Any license17
0BSD0
AGPL-3.00
Apache-2.09
Apache-2.0 AND CC-BY-4.00
BSD-2-Clause0
BSD-2-Clause-Patent0
BSD-3-Clause0
BSD-3-Clause-Clear0
BSL-1.00
BlueOak-1.0.00
CC-BY-4.00
CC-BY-4.0 AND Apache-2.00
CC-BY-SA-4.00
CC0-1.00
No license0

License

Any license17
0BSD0
AGPL-3.00
Apache-2.09
Apache-2.0 AND CC-BY-4.00
BSD-2-Clause0
BSD-2-Clause-Patent0
BSD-3-Clause0
BSD-3-Clause-Clear0
BSL-1.00
BlueOak-1.0.00
CC-BY-4.00
CC-BY-4.0 AND Apache-2.00
CC-BY-SA-4.00
CC0-1.00
No license0

Type

Everything88
MCP servers71
Skills17

Type

Everything88
MCP servers71
Skills17

Category

All categories13
Developer tools8
Databases17
Browser & web33
Search21
Files & documents67
Productivity21
Communication13
Cloud & infrastructure47
Data & analytics51
Design & media87
Memory & knowledge47
Utilities0
Writing92

Category

All categories13
Developer tools8
Databases17
Browser & web33
Search21
Files & documents67
Productivity21
Communication13
Cloud & infrastructure47
Data & analytics51
Design & media87
Memory & knowledge47
Utilities0
Writing92

Newer or easy to miss

Everything17
Created in the last 30 days0
Added to Conduit this week17
Few stars, complete information3

Newer or easy to miss

Everything17
Created in the last 30 days0
Added to Conduit this week17
Few stars, complete information3