Skills that help your agent track research hypotheses and experimental results on the Chronicle platform, with role-filtered search over past experimental results and uploaded research documents. Via the methodic-research SDK: research surveys, hypothesis-driven experiment + variation generation, history/lineage search, prep/fork variations, dataset upload, report write-ups with figures, bulk research-PDF import into org libraries (server-side math OCR + role-filtered indexing), lifecycle (delete open drafts, retract committed work, purge orphaned assets, move into an org), status.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Use this skill when the user wants a new variation whose config the AGENT writes by applying a requested change — phrases like "make a variation that doubles the width", "author a variation with lr 1e-3", "create a variation that swaps the dataset to X". This is the LLM-authoring counterpart to `chronicle-prep-variation`: same git flow (mint token, clone, agent branch), but instead of copying the parent config verbatim, the agent reads the parent `config.yaml`, edits it in-context to apply the user's change, then commits/pushes/registers it. Use `chronicle-prep-variation` when the user just wants a scaffold to edit by hand, and `chronicle-fork-variation` when forking a committed variation into a user-owned branch.
Use this skill when the user (or an agent flow) wants to upload a dataset / training data / reference field to a Chronicle experiment, or to load one back. Phrases like "upload this dataset", "register the training data", "attach this .npz as an input to the variation", "add the reference field", "load the dataset for experiment X", "download the dataset". A dataset is a binary asset (e.g. an `.npz`) uploaded via the presigned-PUT flow with a recorded provenance record (per-component sha256 + size), then linked as an experiment- or variation-level **input**. A directory uploads as one component per file — the way to shard GB-scale data. For *reports* / write-ups use chronicle-write-report; for authoring a variation's *config* use chronicle-author-variation. This is the data counterpart to those.
Use this skill when an agent/runner that brought its OWN training code wants to EXECUTE a committed Chronicle variation and record the run — phrases like "run this variation", "train variation 2 and report it", "execute the committed variation and log to W&B". It is training-AGNOSTIC: it drives the Chronicle run lifecycle (start → succeed/fail, with heartbeats) and, when W&B is available, links the run's W&B run so distillation can pull the metrics. The training itself — a tiny CPU fit or a huge multi-GPU architecture — is the caller's; this skill never writes or contains it. Create + commit the variation first with chronicle-author-variation, and distill the results afterward with chronicle-write-report. This is the BYO-agent (self-run) counterpart to Chronicle's managed Menlo Park workers: the agent runs the training, Chronicle records the run.
Use this skill when the user (or a cleanup flow) wants to permanently delete Chronicle **assets that are not linked to any experiment** — orphaned uploads: phrases like "delete these datasets", "clean up the assets I uploaded by mistake", "purge the orphaned uploads", "remove that abandoned pending upload". Hard delete is refused (409) while an asset is linked as any experiment/variation input or output — linked assets are part of an experiment's record and are taken out of use with deprecate/invalidate instead (`chronicle.assets.deprecate` / `chronicle.assets.invalidate`). For deleting a whole draft experiment (which unlinks its assets), use chronicle-delete-experiment.
Use this skill when the user wants to permanently delete one or more **open (uncommitted)** Chronicle experiments — phrases like "delete this experiment", "remove that draft", "I/the agent created too many experiments, clean them up", "consolidate these experiments", "throw away the experiments I'm not using". The skill resolves the target experiment(s), shows the user exactly what will be removed, requires an explicit confirmation (delete is irreversible), then hard-deletes each open one via the SDK. Committed or concluded experiments are NOT deleted — the skill reports them and points the user at retraction (`chronicle-retract-experiment` / `chronicle.experiments.retract`) instead. Do not invoke this to undo results on a committed experiment (that's retraction) or to remove a single variation (that's a variation operation).
Claude Code plugin: skills for working with the Chronicle experiment platform.
These skills help your agent track research hypotheses and experimental results, and provide role-filtered search over past experimental results and uploaded research documents. Hypotheses become first-class experiments; variations and runs record what was tried and what it produced — metrics, datasets, figures, write-ups, always including what didn't work. Search respects your role's access: you find everything you're allowed to see and nothing you aren't. And lineage travels with the record — parents, retractions, invalidated outputs — so new work builds on results whose provenance and current standing are explicit.
This repo is a Claude Code marketplace containing one plugin (methodic).
Quick start (TL;DR). The default path is UI first, then the plugin: create an account + API key in the Methodic UI, paste its one-line setup command (plus one
pip install) in your terminal, install the plugin from the marketplace — and you're working.# 1. UI: sign up at https://methodiclabs.ai/chronicle/signup, open # "API keys" in the sidebar, create a key, and paste the one-line # setup command the UI shows. It looks like: mkdir -p ~/.methodic && echo 'api_key: sk_user_...' > ~/.methodic/credentials.yaml && chmod 600 ~/.methodic/credentials.yaml # …and install the SDK the skills orchestrate: pip install methodic-research# 2. Claude Code: install the plugin from the marketplace. /plugin marketplace add methodic-research/skills /plugin install methodicThat's the whole default path — once the plugin is installed you can start immediately ("survey the literature on …", "propose an experiment for …"). The easy-to-miss line is the
pip install: the skills orchestrate themethodicSDK and never make raw HTTP calls, so withoutmethodic-researchimportable in the Python environment Claude Code shells out to, every skill ImportErrors onfrom methodic import Chronicleand does nothing. Details below.
Heads-up for agents (initial bootstrap). Creating the account and API key happens in the Methodic UI, logged in as the user — there is no API an agent can call to bootstrap credentials it doesn't yet have (no key, no JWT → no access). If
~/.methodic/credentials.yamlis missing, ask the user to do step 1 below — create a key in the UI and run the one-line setup command it shows in their terminal — then retry. Don't ask for the raw key in chat. The files that command writes are the same credentials everything here reads: the skills/SDK, the MCPAuthorizationheader, and direct REST calls.
Everything starts in the Methodic UI — the one step only you can do (initial bootstrap — an agent can't do it for you; see the note above):
Create an account at methodiclabs.ai/chronicle/signup (or sign in if you already have one).
Create an API key: open API keys in the sidebar and create one. If you work in an organization, create the key in that organization's context — the setup command then records the org as your default; create it in your personal context otherwise.
Paste the one-line setup command the UI shows into your terminal —
one paste, no environment variables. It writes the standard ~/.methodic
client config that Chronicle.from_env() reads, and everything here uses
the same files: skills/SDK, the MCP Authorization header, and direct
REST calls. It looks like:
# Key created in your personal context:
mkdir -p ~/.methodic && echo 'api_key: sk_user_...' > ~/.methodic/credentials.yaml && chmod 600 ~/.methodic/credentials.yaml
# Key created in an organization context — additionally records that org:
mkdir -p ~/.methodic && echo 'organization_id: <org-principal-id>' > ~/.methodic/config.yaml && echo 'api_key: sk_user_...' > ~/.methodic/credentials.yaml && chmod 600 ~/.methodic/credentials.yaml
Install the SDK in the same terminal — the skills orchestrate it (they never make raw HTTP calls), so it must be importable in the Python environment Claude Code shells out to:
pip install methodic-research
What the setup command wrote:
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub methodic-research/skills --plugin methodicComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Payload Development plugin - covers collections, fields, hooks, access control, plugins, and database adapters.