Skip to content

jeremylongshore/tons-of-skills-marketplace / plugins/mcp/governed-second-brain/skills/brain

Search and analyze governed notes, decisions, runbooks, and conventions, returning a qmd:// citation for every supported claim. Use when checking what the brain has captured about architecture, infrastructure, decisions, or operating practices. Trigger with "/brain", "ask the brain", or "check my knowledge base".

FileKindSize
SKILL.mdskill md7.8 KB
references/runtime-contract.mdmarkdown2.3 KB

references/runtime-contract.md

View on GitHub
# Brain runtime contract

This reference records the public `brain_search` contract implemented by the
`governed-second-brain` plugin. The skill body owns the answer workflow; this file owns exact runtime
details.

## Contents

- [Tool input](#tool-input)
- [Successful result](#successful-result)
- [Mode and authentication](#mode-and-authentication)
- [Failure semantics](#failure-semantics)

## Tool input

`brain_search` accepts:

- `query`: required non-empty string.
- `scope`: optional `curated`, `all`, `inbox`, or `archived`; default `curated`.
- `limit`: optional integer from 1 through 50; default 10.

Start with 1–4 distinctive keywords. Keep the same keywords when broadening from `curated` to `all`
so the scope change is the only variable.

## Successful result

Both modes return a JSON object containing the query, scope, result count, and `results`. Each result
can contain `citation`, `snippet`, `score`, and `collection`. Cite only `citation` values actually
returned by the tool. Never synthesize a `qmd://` URI.

Local results identify the source as `local-qmd`. Team results come from the configured team service.
Treat snippets as evidence for only the claims they state; provenance does not independently prove a
claim true.

## Mode and authentication

Local mode is selected when no real `TEAMKB_API_URL` is configured. It runs in-process against the
local brain and requires no API credential. A compatible qmd 2.x executable must be on `PATH` for
indexed retrieval.

Team mode is selected when `TEAMKB_API_URL` is set directly or loaded from `~/.teamkb/team.json`.
`TEAMKB_API_TOKEN` supplies the per-user bearer credential and `TEAMKB_TENANT_ID` selects the tenant.
The runtime refuses to start team mode without a token. Never print the token or configuration file
contents.

## Failure semantics

- A successful empty result is not permission to answer from general knowledge. Complete the
  curated-to-all ladder, then state that no governed evidence was found.
- A local result with a note about a missing index means qmd or its index is unavailable; report the
  operational issue.
- A team response with `ok: false`, an authorization error, or an unreachable-service error is a tool
  failure, not an empty knowledge result. Report it distinctly and do not fabricate an answer.
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 323kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall