Obsidian CLI
Atmosphere/atmosphere
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more.
Conducty's context engine lives in an Obsidian vault. An agent skill from robertbarclayy/conducty.
$ npx skills add robertbarclayy/conducty --skill conducty-obsidian -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install robertbarclayy/conducty conducty-obsidian --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/robertbarclayy/conducty.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/conducty-obsidian .claude/skills/conducty-obsidian && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "conducty-obsidian" agent skill from https://github.com/robertbarclayy/conducty/tree/main/skills/conducty-obsidian into .claude/skills/conducty-obsidian/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conducty-obsidian", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/robertbarclayy/conducty/tree/main/skills/conducty-obsidianType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add robertbarclayy/conducty --skill conducty-obsidian -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install robertbarclayy/conducty conducty-obsidian --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/robertbarclayy/conducty.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/conducty-obsidian .agents/skills/conducty-obsidian && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "conducty-obsidian" agent skill from https://github.com/robertbarclayy/conducty/tree/main/skills/conducty-obsidian into .agents/skills/conducty-obsidian/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conducty-obsidian", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add robertbarclayy/conducty --skill conducty-obsidian -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install robertbarclayy/conducty conducty-obsidian --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/robertbarclayy/conducty.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/conducty-obsidian .cursor/skills/conducty-obsidian && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "conducty-obsidian" agent skill from https://github.com/robertbarclayy/conducty/tree/main/skills/conducty-obsidian into .cursor/skills/conducty-obsidian/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conducty-obsidian", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/robertbarclayy/conducty.git --path skills/conducty-obsidian--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add robertbarclayy/conducty --skill conducty-obsidian -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install robertbarclayy/conducty conducty-obsidian --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/robertbarclayy/conducty.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/conducty-obsidian .gemini/skills/conducty-obsidian && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "conducty-obsidian" agent skill from https://github.com/robertbarclayy/conducty/tree/main/skills/conducty-obsidian into .gemini/skills/conducty-obsidian/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conducty-obsidian", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install robertbarclayy/conducty conducty-obsidianInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add robertbarclayy/conducty --skill conducty-obsidian -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/robertbarclayy/conducty.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/conducty-obsidian .github/skills/conducty-obsidian && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "conducty-obsidian" agent skill from https://github.com/robertbarclayy/conducty/tree/main/skills/conducty-obsidian into .github/skills/conducty-obsidian/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conducty-obsidian", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add robertbarclayy/conducty --skill conducty-obsidian -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install robertbarclayy/conducty conducty-obsidian --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/robertbarclayy/conducty.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/conducty-obsidian .opencode/skills/conducty-obsidian && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "conducty-obsidian" agent skill from https://github.com/robertbarclayy/conducty/tree/main/skills/conducty-obsidian into .opencode/skills/conducty-obsidian/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conducty-obsidian", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
conducty-obsidianConducty's context engine lives in an Obsidian vault. An agent skill from robertbarclayy/conducty.
Conducty Obsidian is an agent skill from robertbarclayy/conducty. Conducty's context engine lives in an Obsidian vault. This skill defines the vault layout, naming, linking, and index conventions every other Conducty skill must follow when reading or writing notes. Use when reading/writing any plan, design, context, improvement, failure pattern, metrics, or prompt-log note — or when the user says "vault", "Obsidian", "context engine", "where is X stored".
Its SKILL.md is about 5.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Knowledge Management. It works with Obsidian. The repository describes itself as: Stop context-switching. Start batch-planning. Conducty replaces the fragmented cycle of plan → prompt → wait → get distracted → review → fix → repeat with advanced batch planning. The licence is MIT.
2 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 64aefd5. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown, bash and yaml).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Conducty Obsidian loads about 5.2k tokens when it runs. Until then it costs about 103 tokens; SKILL.md has 2,155 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from robertbarclayy/conducty at commit 64aefd5, republished under its MIT licence (© robertbarclayy). 2,155 words, ~5,196 tokens.
.claude/skills/conducty-obsidian/SKILL.md (or your agent's skills folder).Conducty's plans, designs, context, improvements, failure patterns, metrics, and prompt logs all live in an Obsidian vault. The vault is not a backup or export target — it IS the context engine. Every Conducty note is written there, linked to its peers, and re-read on future sessions to inform planning.
[!important] Read this first Before writing or reading any state file (plan, design, context, etc.), check this skill for naming and linking conventions. Other Conducty skills assume you've internalized these rules.
Resolve the vault root in this order:
$CONDUCTY_VAULT environment variable, if set~/Obsidian/Conducty/ fallbackWhen this skill says "the vault" or {vault}/..., substitute the resolved path. Always use absolute paths when invoking Bash/Read/Write/Edit.
# Resolve in shell:
VAULT="${CONDUCTY_VAULT:-$HOME/Obsidian/Conducty}"If the vault directory doesn't exist, create it (and the seed index notes — see Bootstrap) before writing anything.
Earlier Conducty stored state under ~/.conducty/{plans,designs,history,context}/ as flat folders. That worked but produced a write-only log: each file was an island. The vault model fixes this:
Context My-App and Obsidian shows every plan and design that referenced it.The vault is the memory of the orchestrator. Treat every note as a node in a graph, not a row in a log.
Nested by category, flat-within-category. Subfolders organize by note type and scope; basenames stay unique and descriptive so wikilinks (which resolve by basename across all subfolders) are unaffected by directory placement.
Title Case filenames. Wikilinks resolve by basename, so the filename is the canonical title — never rely on the directory path to disambiguate a wikilink target.
{vault}/
├── Conducty Index.md # root hub
│
├── Indexes/
│ ├── Plans Index.md # links every plan note
│ ├── Designs Index.md # links every design doc
│ ├── Context Index.md # links every project context hub
│ └── Improvements Index.md # links every improvement entry
│
├── Accumulators/
│ ├── Failure Patterns.md # accumulating, append-prepend
│ ├── Metrics.md # one row per plan run
│ └── Prompt Log.md # one entry per prompt outcome
│
├── Plans/
│ ├── Plan 2026-04-27 0930 Auth Cleanup.md
│ └── Plan 2026-04-27 1430 Bug Triage.md
│
├── Designs/
│ └── Design 2026-04-27 0930 Auth Cleanup.md
│
├── Improvements/
│ └── Improvement 2026-04-27 1830.md
│
├── Code Reviews/
│ └── Code Review 2026-04-27 1900.md
│
├── Ship Reports/
│ └── Ship Report 2026-04-27 1915.md
│
└── Context/
└── My App/ # one folder per project
├── Context My App.md # hub
├── Context My App Architecture.md
├── Context My App Conventions.md
├── Context My App Invariants.md
├── Context My App Hotspots.md
├── Context My App Tests.md
├── Context My App Glossary.md
├── Modules/
│ └── Context My App Auth.md # per bounded-context deep note
└── Refreshes/
└── Context Refresh My App 2026-04-27 1830.mdWhy nested: flat root broke at scale — a vault with 50+ plans + multi-project context becomes a wall of files. Nesting by category makes Obsidian's file tree navigable. Wikilinks are unaffected because Obsidian resolves them by basename across the whole vault, not by path.
Why long unique basenames inside Context/{Project}/ (e.g. Context My App Architecture.md, not just Architecture.md): wikilinks like [[Architecture]] would collide across projects. Keeping Context {Project} {Slice} as the basename makes every wikilink unambiguous forever.
Two note categories:
| Note type | Directory | Filename pattern | Example |
|---|---|---|---|
| Plan | Plans/ | Plan YYYY-MM-DD HHmm [{Topic Title Case}].md | Plans/Plan 2026-04-27 0930 Auth Cleanup.md |
| Design | Designs/ | Design YYYY-MM-DD HHmm {Topic Title Case}.md | Designs/Design 2026-04-27 0930 Auth Cleanup.md |
| Improvement | Improvements/ | Improvement YYYY-MM-DD HHmm.md | Improvements/Improvement 2026-04-27 1830.md |
| Code review | Code Reviews/ | Code Review YYYY-MM-DD HHmm.md | Code Reviews/Code Review 2026-04-27 1900.md |
| Ship report | Ship Reports/ | Ship Report YYYY-MM-DD HHmm.md | Ship Reports/Ship Report 2026-04-27 1915.md |
| Index | Indexes/ | {Topic} Index.md | Indexes/Plans Index.md |
All per-project notes live under Context/{Project}/. Optional bounded-context deep notes go under Context/{Project}/Modules/. Refresh delta notes go under Context/{Project}/Refreshes/.
| Note | Path | Purpose |
|---|---|---|
| Hub | Context/{Project}/Context {Project}.md | Project identity, links to slices, last-refreshed |
| Architecture | Context/{Project}/Context {Project} Architecture.md | Bounded contexts, module map, Mermaid dep graph, seams |
| Conventions | Context/{Project}/Context {Project} Conventions.md | Naming, style, lint/format commands |
| Invariants | Context/{Project}/Context {Project} Invariants.md | Public APIs, schemas, contracts |
| Hotspots | Context/{Project}/Context {Project} Hotspots.md | Frequently changed files, recent activity |
| Tests | Context/{Project}/Context {Project} Tests.md | Test/typecheck/lint/vuln commands; characterization data. Read by [[conducty-ship]]. |
| Glossary | Context/{Project}/Context {Project} Glossary.md | Domain terms, ubiquitous language |
| Module deep note | Context/{Project}/Modules/Context {Project} {Module}.md | Optional, for non-trivial bounded contexts |
| Refresh delta | Context/{Project}/Refreshes/Context Refresh {Project} YYYY-MM-DD HHmm.md | Diff vs prior refresh — temporal record |
Multiple plans per day are expected — that's why plans (and the artifacts derived from them) carry an HHmm timestamp. The topic suffix on plans is optional but encouraged when more than one plan runs in a day, so the filename alone tells you which plan is which.
All accumulating notes live under Accumulators/.
| Note type | Path | Behavior |
|---|---|---|
| Failure Patterns | Accumulators/Failure Patterns.md | Append-prepend: newest pattern at top |
| Metrics | Accumulators/Metrics.md | Append-prepend: one row per plan run, newest at top |
| Prompt Log | Accumulators/Prompt Log.md | Append-prepend: one entry per prompt outcome, newest at top |
Accumulating notes never get a timestamp in their filename — they hold every entry across all plan runs and serve as the cross-time learning corpus.
Always Title Case. Always full ISO date for any dated note.
Every Conducty note carries frontmatter. Minimum required fields:
---
type: plan | design | context | improvement | failure-patterns | metrics | prompt-log | index
date: YYYY-MM-DD # for per-instance notes
time: HHmm # for plan / design / improvement
project: {project-name} # for context, and for plans/designs scoped to one project
topic: {short topic} # for plan / design (optional but recommended)
tags: [conducty, conducty/<type>]
---Add type-specific fields as the skill requires (e.g., plans add appetite, metrics rows add pass_rate).
Every per-instance note links its peers and at least one index. A note with no outgoing links has been written into a void.
Standard link patterns:
[[Plans Index]], the design(s) it decomposed ([[Design 2026-04-27 0930 Auth Cleanup]]), the context note(s) it loaded ([[Context My App]]), the prior improvement entry whose experiments it's testing ([[Improvement 2026-04-26 1830]]), and any prior plan whose work carries forward ([[Plan 2026-04-26 0930]]). Plans also link the accumulating notes they will append to: [[Failure Patterns]], [[Metrics]], [[Prompt Log]].[[Designs Index]], the plan(s) that consume it, the context note(s) for relevant projects, related dialectic decisions.[[Context Index]] and any plan/design that depends on the project. Backlinks accumulate naturally as plans reference it.[[Improvements Index]], the plan it reflects on, [[Failure Patterns]], prior improvements being evaluated.[[Plan 2026-04-27 0930 Auth Cleanup]]) and the prompt entry in [[Prompt Log]].[[Failure Patterns]].Place links in two zones:
## Related
- Index: [[Plans Index]]
- Built from: [[Design 2026-04-27 0930 Auth Cleanup]], [[Context My App]]
- Tests experiments from: [[Improvement 2026-04-26 1830]]
- Carries forward from: [[Plan 2026-04-26 0930]]
- Accumulates into: [[Failure Patterns]], [[Metrics]], [[Prompt Log]]Index notes are flat lists with frontmatter. They serve two purposes:
Each index follows this shape:
---
type: index
tags: [conducty, conducty/index]
---
# Plans Index
Conducty plans. Newest first.
- [[Plan 2026-04-27 1430 Bug Triage]]
- [[Plan 2026-04-27 0930 Auth Cleanup]]
- [[Plan 2026-04-26 0930]]
## Related
- Root: [[Conducty Index]]
- See also: [[Designs Index]], [[Improvements Index]], [[Failure Patterns]], [[Metrics]], [[Prompt Log]]When you create a new per-instance note, always prepend its wikilink to the matching index in the same operation.
Conducty Index is the root and links every index plus the accumulating notes:
---
type: index
tags: [conducty, conducty/index, conducty/root]
---
# Conducty Index
The Conducty cycle: Shape → Plan → Trace → Execute → Verify → Improve.
## Indexes
- [[Plans Index]]
- [[Designs Index]]
- [[Context Index]]
- [[Improvements Index]]
## Accumulating
- [[Failure Patterns]]
- [[Metrics]]
- [[Prompt Log]]If the vault root doesn't exist, create it (with the standard subdirectories) before any other note write:
VAULT="${CONDUCTY_VAULT:-$HOME/Obsidian/Conducty}"
mkdir -p "$VAULT"/{Indexes,Accumulators,Plans,Designs,Improvements,"Code Reviews","Ship Reports",Context}Context/{Project}/ and its Modules/ + Refreshes/ subfolders are created lazily by [[conducty-context]] when ingesting a project.
Seed these notes if missing:
Conducty Index.md (vault root)Indexes/): Plans Index, Designs Index, Context Index, Improvements IndexAccumulators/): Failure Patterns, Metrics, Prompt Log (each with its frontmatter and an empty body)The installer (install-claude-code.sh) does this on first run. This skill creates them lazily if a write would otherwise create an orphan.
Plans, code reviews, and ship reports must find each other reliably. The rules:
The "active plan" is the most recent Plans/Plan *.md whose ## End-of-Plan Summary is not yet filled (i.e., [[conducty-review]] hasn't closed it). Resolve by:
# List all plans, newest first
ls -t "$VAULT"/Plans/Plan*.mdRead the newest first. If its End-of-Plan Summary is filled, walk backward until one is found that isn't, OR conclude no active plan exists. [[conducty-plan]] starting a new plan creates a fresh active plan; [[conducty-review]] closes the prior one.
[[conducty-code-review]] reads:
[[conducty-code-review]] writes:
Code Review YYYY-MM-DD HHmm.md note with ## Related linking each plan## Review Notes section to add the wikilink to the code-review note[[conducty-ship]] reads:
Code Reviews/Code Review *.md note. Its verdict field gates the ship battery.Context {Project} Tests for the command set.[[conducty-ship]] writes:
Ship Report YYYY-MM-DD HHmm.md## Related section: add the ship report wikilink## Review Notes section: add the ship report wikilinkWhen a branch accumulates work from multiple plans before merging:
Improvement note via [[conducty-improve]] at plan-closeCode Review runs against the cumulative branch diff at the end (not per-plan)Ship Report runs after the code review## Related lists every plan that contributed to the branchStandard globs every skill can rely on. All globs are relative to the resolved $VAULT root.
| To find | Glob |
|---|---|
| Plans | Plans/Plan *.md |
| Designs | Designs/Design *.md |
| Improvements | Improvements/Improvement *.md |
| Code reviews | Code Reviews/Code Review *.md |
| Ship reports | Ship Reports/Ship Report *.md |
| Project hubs | Context/*/Context *.md (filter to depth-2 — the hub sits directly under each project folder) |
| Project slices | Context/*/Context * Architecture.md, Context/*/Context * Conventions.md, etc. |
| Module deep notes | Context/*/Modules/Context *.md |
| Refresh deltas | Context/*/Refreshes/Context Refresh *.md |
| Indexes | Indexes/* Index.md |
| Accumulators | Accumulators/Failure Patterns.md, Accumulators/Metrics.md, Accumulators/Prompt Log.md |
Skills doing discovery should use these patterns, not improvise.
When [[conducty-plan]] starts a new plan, it reads:
Plans/Plan *.md, sort by date then time frontmatter, pick newest — that's the prior planImprovements/Improvement *.md, pick newestContext/*/Context *.md (the hub sits at the top of each project folder)Accumulators/Failure Patterns.md — the accumulating learning corpus, especially recent entriesAccumulators/Metrics.md — last 7-14 rows for trend dataUse Glob with patterns like Plans/Plan *.md against the resolved vault root. Read the resulting notes, follow their wikilinks via Read on the targets, and the orchestrator inherits the full context graph.
## Related section, and an index update in the same Conducty action.`~/.conducty/...` or `./skills/foo/SKILL.md`) are still appropriate for shell paths or external state. Use wikilinks only for vault-resident notes.Failure Patterns, Metrics, and Prompt Log are append-mostly but written by multiple skills (sometimes within the same plan). The contract:
### YYYY-MM-DD HHmm — {short label}. Newest entry is at the top; chronological order descends.old_string is the anchor (H1 + intro), the new_string is anchor + new entry.Example anchor for Accumulators/Failure Patterns.md:
# Failure Patterns
Accumulating failure-pattern entries from [[conducty-debug]] and [[conducty-review]]. Newest first.
### 2026-04-27 1830 — P3 vague acceptance criteria
- **Plan**: [[Plan 2026-04-27 0930 Auth Cleanup]]
- ...To prepend, Edit replaces the intro line with intro line\n\n### {new entry}. The H1 + intro stay constant — they're the anchor.
If two plans run in parallel, each appends through Edit on the same anchor. Edit is line-precise so collisions surface as Edit failures (the second one finds the prior one's text and stops). Resolve by re-reading and re-editing.
Conducty assumes one orchestrator per vault at a time. Running two conducty-execute sessions against the same vault concurrently is supported only when:
When two orchestrators must append to the same accumulating note, serialize: finish one, then the other.
Old Conducty stored state at:
~/.conducty/plans/, ~/.conducty/designs/, ~/.conducty/context/, ~/.conducty/history/The vault replaces all of it. If you find a Conducty skill that still references the old path, treat the vault path as authoritative and update the skill (or flag the inconsistency). The legacy ~/.conducty/ directory is not used.
Plan YYYY-MM-DD HHmm [Topic].mdDesign YYYY-MM-DD HHmm {Topic}.mdContext {Project} hub + Architecture/Conventions/Invariants/Hotspots/Tests/Glossary slices, optional module deep notes, refresh deltas)Improvement YYYY-MM-DD HHmm.mdFailure PatternsMetrics and entries to Prompt LogCode Review YYYY-MM-DD HHmm.mdShip Report YYYY-MM-DD HHmm.md© robertbarclayy, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/conducty-obsidian of robertbarclayy/conducty.
Open the folder on GitHubat commit 64aefd5
Conducty Obsidian next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Conducty Obsidian this skillrobertbarclayy/conducty | 176 | — | ~5.2k | Automated safety check: Pass | MIT | |
| Obsidian CLIAtmosphere/atmosphere | 3.8k | 13 repos | ~795 | Automated safety check: Pass | Apache-2.0 | |
| Obsidian Canvas BoardsAgriciDaniel/claude-obsidian | 15k | — | ~1.4k | Automated safety check: Pass | MIT | |
| LLM Wikilewislulu/llm-wiki-skill | 655 | — | ~3.7k | Automated safety check: Pass | None | |
| Second BrainNicholasSpisak/second-brain | 737 | — | ~1.5k | Automated safety check: Notes | None | |
| Codex History IngestAr9av/obsidian-wiki | 3.5k | — | ~2.2k | Automated safety check: Notes | MIT |
Atmosphere/atmosphere
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more.
AgriciDaniel/claude-obsidian
Creates, inspects and updates Obsidian JSON Canvas boards in a vault, with text, file, link, group and edge nodes, using safe recoverable edits.
lewislulu/llm-wiki-skill
Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers…
NicholasSpisak/second-brain
Set up a new Obsidian knowledge base with the LLM Wiki pattern.
Ar9av/obsidian-wiki
Ingest Codex CLI conversation/session history into Obsidian as distilled knowledge.
smixs/agent-second-brain
Schema-as-code enforcement for any Obsidian vault. An agent skill from smixs/agent-second-brain.
robertbarclayy/conducty
Quality gate between parallelization groups. An agent skill from robertbarclayy/conducty.
robertbarclayy/conducty
Standalone post-implementation code review across a whole branch or PR.
robertbarclayy/conducty
Ingest a project directory into the Obsidian vault as a linked context sub-graph — Architecture, Conventions, Invariants, Hotspots, Tests, Glossary, plus per-bounded-context module notes.
robertbarclayy/conducty
Leverage-point analysis for failed prompts. An agent skill from robertbarclayy/conducty.
robertbarclayy/conducty
Dispatches Claude Code Task subagents to run prompts from a vault plan note.
robertbarclayy/conducty
End-of-plan improvement kata. An agent skill from robertbarclayy/conducty.
Works with
Categories
Conducty's context engine lives in an Obsidian vault. An agent skill from robertbarclayy/conducty. Conducty Obsidian is an agent skill from robertbarclayy/conducty. Conducty's context engine lives in an Obsidian vault.
Conducty Obsidian fits situations like: reading/writing any plan; failure pattern; prompt-log note —; the user says vault.
Run `npx skills add robertbarclayy/conducty --skill conducty-obsidian -a claude-code`. Or copy the skill folder (skills/conducty-obsidian in robertbarclayy/conducty) into .claude/skills/conducty-obsidian in your project. Claude Code loads it when a task matches its description.
Run `npx skills add robertbarclayy/conducty --skill conducty-obsidian -a codex`. Or copy the skill folder (skills/conducty-obsidian in robertbarclayy/conducty) into .agents/skills/conducty-obsidian in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add robertbarclayy/conducty --skill conducty-obsidian -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/conducty-obsidian, .gemini/skills/conducty-obsidian, .github/skills/conducty-obsidian and .opencode/skills/conducty-obsidian in your project.
SKILL.md names no scripts, command-line tools or credentials: Conducty Obsidian is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Conducty Obsidian is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.2k tokens (SKILL.md is roughly 21k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Conducty Obsidian: Obsidian CLI (Atmosphere/atmosphere, 3.8k stars), Obsidian Canvas Boards (AgriciDaniel/claude-obsidian, 15k stars), LLM Wiki (lewislulu/llm-wiki-skill, 655 stars) and Second Brain (NicholasSpisak/second-brain, 737 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
robertbarclayy (a GitHub user) maintains it in robertbarclayy/conducty, which has 176 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on June 19, 2026.
Source: robertbarclayy/conducty on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.