Keep project knowledge in plain Markdown while a deterministic CLI maintains folder indexes, cross-links, structure checks, and scoped map, search, and read commands for agents.
Open the source and read safety notes before installing.
Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.
Decision playbook
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
0
71
—
No baseline selected
No major trust-signal divergence detected in the current selection.
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Source provenance statusRequired
Marked as source-backed.
Metadata reviewed
No reviewed flag detected in metadata.
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Trust level risk gateRequired
Trust level does not block evaluation.
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Package verification flag
No package verification flag provided.
Checksum metadata
No checksum provided for downloaded artifact.
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
Baseline comparison available
No baseline peer selected yet.
Diverging trust signals identified
No major trust-signal divergence found.
Setup at a glance
Copy-ready — paste the snippet to get started.
Adoption plan
Current risk score 24/100. Use staged verification before broader rollout.
Validate source and review signals before any execution.
Confirm source provenanceRequired
Source URL/provenance metadata is present.
Confirm metadata review state
No review metadata found; increase manual validation.
Verify install payload
Install/config payload exists and can be inspected.
Confirm safety, privacy, and package integrity signals.
Review safety notesRequired
Safety notes are present.
Review privacy notesRequired
Privacy notes are present.
Verify package integrity metadata
No package verification/checksum metadata.
Adopt in controlled steps based on the selected plan.
Run in isolated sandbox firstRequired
Use a constrained sandbox and observe behavior across multiple tasks.
Roll out graduallyRequired
Roll out to a small cohort before wider usage.
Set monitoring and fallback
Define rollback path and monitor errors after adoption.
Evidence readiness
Missing required evidence: Metadata review. Risk score 31.
Source repository/provenance is listed.
Required in this preset
Review metadata is missing.
Required in this preset
Safety notes are present.
Required in this preset
Privacy notes are present.
Optional in this preset
Package integrity metadata is missing.
Optional in this preset
Install payload is available.
Required in this preset
Required gaps: Metadata review
Decision timeline
Blocking gaps: Check metadata review status. Risk 28.
triage
Source/provenance metadata is available.
triage
Review metadata is missing.
verify
Safety notes are available.
verify
Privacy notes are available.
verify
Package integrity metadata is missing.
rollout
Install payload is available.
Blockers: Check metadata review status
Prerequisite readiness
3 prerequisites to line up before setup.
Safety & privacy surface
4 safety and 3 privacy notes across 4 risk areas. Review closely: permissions & scopes, network access.
| Platform | Support | Install path |
|---|---|---|
| claude-code | Native | .claude/skills/<skill-name>/SKILL.md |
| codex | Native | .agents/skills/<skill-name>/SKILL.md |
| windsurf | Native | .windsurf/skills/<skill-name>/SKILL.md |
| gemini | Native | .gemini/skills/<skill-name>/SKILL.md or .agents/skills/<skill-name>/SKILL.md |
| cursor | Adapter | .cursor/rules/<skill-name>.mdc |
| cli | Manual | AGENTS.md or tool-specific context file |
wiki init
wiki update
wiki lint
wiki map
wiki search "authentication"
wiki read authPlasma Wiki turns a folder of Markdown files into an indexed knowledge base for
people and agents. A deterministic CLI maintains _index.md pages,
cross-links, frontmatter, structure checks, and the generated region of index
merges. People and agents remain responsible for the content.
The agent workflow is intentionally small: map the tree, search for the topic, then read only the pages the task needs. The knowledge base stays in plain files that users can edit and review through Git.
This listing was verified on 2026-07-24 against the public repository,
canonical SKILL.md, documentation, and the published plasma-wiki 1.1.0
package. The source is Apache-2.0 licensed.
Install the CLI in an isolated Python environment, then copy the bundled skill into the supported agent skill directories:
pipx install plasma-wiki
wiki install
The documented plugin marketplace routes are also available:
# Claude Code
/plugin marketplace add plasma-ai/plugins
/plugin install wiki@plasma
# Codex
codex plugin marketplace add plasma-ai/plugins
codex plugin add wiki@plasma
Run wiki install again after upgrading a copied skill. Editable installs can
use wiki install --link.
Initialize a wiki and keep its generated structure current:
wiki init
wiki update
wiki lint
Agents retrieve context through three commands:
wiki map
wiki search "authentication"
wiki read auth
wiki map prints the indexed tree and word counts. wiki search performs text
search using Python regular expressions. wiki read loads one named entry and
can slice it by words, lines, or characters.
_index.md navigation._index.md files
while leaving authored conflicts visible..wiki/settings.json.wiki trust before a repository hook can execute.wiki install.wiki install.wiki CLI.Other Agent Skills hosts can load the canonical
wiki/skills/wiki/SKILL.md file if they support the standard SKILL.md
format.
Wiki maintenance commands write files. Review wiki update --check, use Git
diffs, and keep authored pages under the repository's normal review policy.
After cloning a repository, run wiki config to restore the clone-local merge
driver before relying on generated-index merge handling.
A wiki may include .wiki/wiki.py to customize indexing or formatting.
wiki refuses to load that hook until the user runs wiki trust. Inspect the
hook first because trust allows it to execute with the user's privileges.
The retrieval commands operate on local Markdown, but any page handed to an agent can enter that agent's model context, transcript, or provider logs. Keep secrets, customer data, credentials, and regulated information out of the wiki unless the selected agent environment is approved for them.
Issue: A formatter changes *** to --- or escapes [[wikilinks]]
Fix: Install mdformat-wiki, remove a conflicting
mdformat-frontmatter plugin, or exclude the wiki root from that formatter.
Issue: Generated _index.md sections conflict after a fresh clone
Fix: Run wiki config in that clone to register the local Git merge
driver.
Issue: The installed agent skill does not reflect a package upgrade
Fix: Run wiki install again, or use wiki install --link from an
editable install.
HeyClaude already lists Markdown Knowledge Base Composer, which consolidates Markdown folders and exports combined documents. Plasma Wiki instead maintains an indexed source tree for selective agent navigation and retrieval. The Obsidian Agent Skills entry covers Obsidian-specific authoring and development workflows; Plasma Wiki can use Obsidian as an optional editor but owns its indexing and CLI workflow independently.
Submitted by a contributor affiliated with Plasma AI. This is a source-backed community listing for the Apache-2.0 project.
Show that Plasma Wiki is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/skills/plasma-wiki)Plasma Wiki side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
1 trust signal differ across this comparison (Submitter).
| Field | Keep project knowledge in plain Markdown while a deterministic CLI maintains folder indexes, cross-links, structure checks, and scoped map, search, and read commands for agents. Open dossier | MIT-licensed BrowserAct Agent Skill pack for installing and operating the `browser-act` browser automation CLI from Claude Code, Codex, OpenClaw, Cursor, OpenCode, Windsurf, Gemini CLI, and other skills-compatible agents. Open dossier | MIT-licensed Agent Skills collection for context engineering, harness engineering, multi-agent architectures, filesystem context, memory systems, tool design, evaluation, hosted agents, and production agent operating loops for Claude Code, Cursor, Codex, and Open Plugins-compatible agent tools. Open dossier | Agent Skills for Obsidian by Steph Ango, teaching Claude Code, Codex, OpenCode, and skills-compatible agents to work with Obsidian Flavored Markdown, Bases, JSON Canvas, Obsidian CLI, vaults, plugins, themes, and Defuddle-powered web-to-markdown extraction. Open dossier |
|---|---|---|---|---|
| Next steps | ||||
| Trust | ||||
| Review status | Not reviewed | Not reviewed | Not reviewed | Not reviewed |
| Package trust | Package not verified | Package not verified | Package not verified | Package not verified |
| Source provenance | Source-backed | Source-backed | Source-backed | Source-backed |
| SubmitterDiffers | ryanpettry | — | — | — |
| Install risk | Review first | Review first | Review first | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Brand | — | — | ||
| Category | skills | skills | skills | skills |
| Source | Source-backed | Source-backed | Source-backed | Source-backed |
| Author | Plasma AI | BrowserAct | Muratcan Koylan | Steph Ango |
| Added | 2026-07-24 | 2026-06-18 | 2026-06-18 | 2026-06-18 |
| Platforms | ||||
| Harness | ||||
| Source repo | — | — | — | — |
| Safety notes | ✓`wiki init`, `wiki config`, and `wiki update` write local Markdown structure, settings, frontmatter, headings, `.gitattributes`, and clone-local Git merge-driver configuration. Review the diff before committing it. `wiki trust` authorizes the selected wiki's `.wiki/wiki.py` hook to execute with the user's privileges. Read that file before trusting a cloned or third-party wiki. `wiki init` and `wiki config` can download the pinned Front Matter Title Obsidian plugin from GitHub. Obsidian itself remains optional. The `***` delimiter and `[[wikilinks]]` are load-bearing syntax. Use `mdformat-wiki` or exclude the wiki root from formatters that rewrite them. | ✓BrowserAct can open pages, click, type, upload files, inspect state, capture screenshots, read page text, handle dialogs, export cookies, capture network requests, and operate logged-in browser sessions. Use BrowserAct only on sites, accounts, and data sources where the user has authorization. Do not use it to evade access controls, violate site terms, scrape disallowed data, or bypass rate limits. The entry skill declares confirmation gates for browser creation, deletion, local Chrome profile import, proxy/security changes, logins, form submissions, file uploads, and other sensitive operations; preserve those gates in agent workflows. `solve-captcha` may send the challenge image to BrowserAct's verification-assistance service according to the skill metadata; do not use it with sensitive or unauthorized pages. `remote-assist` can generate a live handoff URL for a human to take over. Treat that URL as access to the active browser session. Skill Forge can generate reusable automation skills from explored sites. Review generated scripts, selectors, network assumptions, output schemas, and site authorization before reusing them at scale. | ✓These skills alter how agents select context, delegate work, persist state, design tools, evaluate outputs, and operate autonomous loops; use them as engineering guidance, not as automatic authority to change a production agent system. Filesystem-context and memory-system patterns can cause agents to write durable plans, scratchpads, logs, summaries, preferences, or shared handoff files. Keep cleanup, ownership, and review rules explicit. Harness-engineering, hosted-agent, and evaluation workflows can launch long-running loops, background agents, benchmark suites, paid model calls, or remote sandbox work. Require budgets, kill switches, rollback rules, and approval gates. Tool-design guidance can change MCP schemas, tool descriptions, return formats, and error contracts. Test routing and compatibility before deploying changes to users. Benchmark results are source evidence for this repository's claims, but they are workload-specific. Re-run or adapt benchmarks before relying on the reported routing numbers in a different agent stack. | ✓Obsidian vaults often contain personal notes, private research, customer context, credentials in notes, meeting records, and unpublished plans; scope agent access carefully. The Obsidian CLI skill can guide vault operations, plugin work, and theme development, so review commands before running them against a real vault. JSON Canvas and Bases edits can alter knowledge organization, saved views, formulas, and linked note structures; review generated files before syncing or publishing. Defuddle-powered extraction can bring third-party web content into a vault; check source attribution, copyright, and cleanup before sharing extracted notes. |
| Privacy notes | ✓`wiki map`, `wiki search`, and `wiki read` inspect local project documentation. Pages supplied to an active agent can become part of that agent's model context and logs. Wiki content, `.wiki/settings.json`, and generated indexes remain ordinary local files, but Git remotes, backups, and collaboration tools can copy them according to the user's repository policy. Package installation contacts the selected Python package index, while optional Obsidian setup contacts GitHub to download the pinned plugin release. | ✓BrowserAct workflows can expose page content, screenshots, URLs, credentials typed into forms, cookies, browser profiles, uploaded files, downloaded files, network requests, HAR data, session names, browser descriptions, and logs. The BrowserAct skill metadata states that cookies, login sessions, page content, credentials, and browser profile data stay local, except the CAPTCHA challenge image when `solve-captcha` is invoked. Chrome-direct and profile import workflows can connect agents to existing local browser state. Treat those modes as account access, not a blank test browser. Log reports, feedback, Discord support, generated Skill Forge packages, and shared screenshots can leak private browsing or account context if submitted without review. Managed proxy, stealth browser, and API-key features create additional BrowserAct service dependencies beyond local CLI execution. | ✓Context-engineering work often touches prompts, system instructions, tool definitions, retrieved documents, message history, tool outputs, logs, scratch files, memory stores, benchmark prompts, and model responses. Do not persist secrets, customer data, private source code, incident data, unpublished strategy, or regulated records into scratchpads, skill examples, benchmark fixtures, or shared agent workspaces. If benchmark runners or hosted-agent examples call external models or remote sandboxes, review what prompts, traces, files, and logs are sent outside the local workspace. Agent memory and filesystem-context patterns should include deletion, redaction, retention, and access-control rules before being used with private projects. | ✓Using the skills can expose note contents, backlinks, properties, canvases, Base queries, plugin code, theme files, vault paths, web extracts, and personal knowledge workflows to the configured model provider. Do not share private journals, client notes, regulated data, secret recovery phrases, API keys, unreleased plans, or internal knowledge bases unless the agent environment is approved for that data. When committing or publishing generated vault files, review embedded links, frontmatter properties, canvas text, extracted quotes, and metadata for private information. |
| Prerequisites |
|
|
|
|
| Install | | | | |
| Config | — | — | — | — |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
BrowserAct entry skill for agent-safe browser automation, indexed page interaction, session isolation, remote assist, and reusable Skill Forge flows.
Agent Skills pack for context windows, multi-agent systems, filesystem memory, tool design, evaluation, harness engineering, and production agents.
Obsidian skill pack for Markdown, Bases, JSON Canvas, Obsidian CLI vault workflows, plugin/theme development, and clean web-to-markdown extraction.
Source-backed guides for putting this to work.
Write a claude-code-hint tag to stderr under CLAUDECODE, and Claude Code prompts users once to install your official-marketplace plugin.
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.