Agent skill

Anarlog Workflow

by fastrepl in fastrepl/anarlog

Execute Anarlog work immediately while preserving useful decisions and non-obvious lessons in Linear.

MITAuto-check passedAgent Workflows

Install Anarlog Workflow

skills CLI
$ npx skills add fastrepl/anarlog --skill anarlog-workflow -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install fastrepl/anarlog anarlog-workflow --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/fastrepl/anarlog.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/anarlog-workflow .claude/skills/anarlog-workflow && rm -rf skills-src

Use ~/.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/

Facts

Skill name
anarlog-workflow
GitHub stars
9.4k
Token cost
~1.5k tokens
SKILL.md length
798 words
Files
1
Skills in repo
32
Repo updated
First seen
Licence
MIT

At a glance

Execute Anarlog work immediately while preserving useful decisions and non-obvious lessons in Linear.

  • Works in 5 steps: Default to execution. When the user… → Only use a discussion-first workflow… → Search Linear issues, documents, and… → …
  • Anarlog repository
  • SKILL.md covers Start work immediately, Record facts worth remembering, Put knowledge where it belongs and Keep Slack updates selective
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Anarlog Workflow is an agent skill from fastrepl/anarlog. Execute Anarlog work immediately while preserving useful decisions and non-obvious lessons in Linear. Use for Anarlog repository or Anarlog desktop, web, mobile, and API work, including related worktrees and ANLG issues. Explicit brainstorming stays discussion-first. Do not use for unrelated repositories or meeting-data queries.

Its SKILL.md is about 1.5k 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 Agent Workflows, covering Git worktrees and Brainstorming. The repository describes itself as: Open source Granola AI Alternative. The licence is MIT.

When your agent uses it

  • Anarlog repository
  • Anarlog desktop
  • Including related worktrees and ANLG issues
  • Unrelated repositories

Example prompts

  • “/anarlog-workflow”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Default to execution. When the user requests a change, reports a bug, or scopes work, start investigating and implementing immediately and…
  2. Only use a discussion-first workflow when the user explicitly asks for brainstorming, exploration of ideas, or planning without…
  3. Search Linear issues, documents, and comments for the topic, IDs (ANLG-123), and nearby decisions alongside execution. Read matching…
  4. Reuse an existing issue when one fits. Create one for work that needs tracking, such as a feature, substantial behavior change, or…
  5. If Linear is unavailable, continue authorized work and report a recording gap only when there is useful context to preserve. Existing…

What it can do on your machine

Read from SKILL.md and the folder at commit 259a04e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • linear.app

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Anarlog Workflow loads about 1.5k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 798 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~87
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from fastrepl/anarlog at commit 259a04e, republished under its MIT licence (© fastrepl). 798 words, ~1,472 tokens.

Download SKILL.mdSave it as .claude/skills/anarlog-workflow/SKILL.md (or your agent's skills folder).
name
anarlog-workflow
description
Execute Anarlog work immediately while preserving useful decisions and non-obvious lessons in Linear. Use for Anarlog repository or Anarlog desktop, web, mobile, and API work, including related worktrees and ANLG issues. Explicit brainstorming stays discussion-first. Do not use for unrelated repositories or meeting-data queries.

Anarlog workflow

Apply to Anarlog repository or Anarlog desktop, web, mobile, and API work. Apply the same workflow in other checkouts and worktrees.

Use Linear for work tracking and facts worth remembering. Keep implementation and verification details in commits, PRs, and CI.

Write everything you log or edit in English, even when the conversation is in another language: Linear issues, comments, and documents; Slack updates; commits, PRs, and review replies; code comments and docs. Only replies to the user in the conversation follow the user's language, and localized product content such as translation catalogs keeps its target language.

Do not read, create, edit, or comment in Notion for Anarlog work. Anarlog does not use Notion; keep its decisions and durable context in Linear.

Start work immediately

  1. Default to execution. When the user requests a change, reports a bug, or scopes work, start investigating and implementing immediately and carry it through to completion. Document only when the criteria below are met; documentation is not a prerequisite or the deliverable.
  2. Only use a discussion-first workflow when the user explicitly asks for brainstorming, exploration of ideas, or planning without implementation. Answer informational questions directly.
  3. Search Linear issues, documents, and comments for the topic, IDs (ANLG-123), and nearby decisions alongside execution. Read matching issues/docs and the team's Agent lessons early enough to inform relevant implementation decisions. Do not make this pass a prerequisite for starting useful work.
  4. Reuse an existing issue when one fits. Create one for work that needs tracking, such as a feature, substantial behavior change, or unresolved bug; do not create an issue just to log a small completed edit. Use the right team and existing project. Update status when it changes without adding a routine progress comment.
  5. If Linear is unavailable, continue authorized work and report a recording gap only when there is useful context to preserve. Existing approval requirements for external actions and shared history still apply.

Record facts worth remembering

Before writing a comment or document, ask: will this help someone make a future decision or avoid rediscovering something non-obvious, and is it missing from the existing record? If not, do not post.

  • Preserve consequential decisions and their rationale, surprising findings, non-obvious constraints, corrected assumptions, and failed approaches with a reusable lesson.
  • Record a blocker or handoff only when someone needs to act, including the missing context and required next step.
  • Skip investigation-start announcements, step-by-step progress, change summaries, commit/push notices, test counts, formatting results, and routine verification caveats. These belong in the task response, PR, or CI, not another Linear comment.
  • Do not copy information already captured in an issue, document, or PR. Link to the source when it supports a new fact; include only the context needed to understand that fact.
  • Keep each note short: what we learned, why it matters, and what it changes next time. No required headings or per-turn documentation quota. If nothing worth remembering emerged, write nothing.
  • Link the issue in commits/PRs when one exists (ANLG-123).
Show full SKILL.md (293 more words)Show less

Put knowledge where it belongs

  • Ticket-specific findings or decisions: a concise comment on the existing issue.
  • Lessons reusable across tickets: the team's Agent lessons document (create it if missing). Check for an existing entry and update it rather than repeating it. Use a date, short title, lesson, and future action; newest first.
  • Durable specs, research conclusions, and product context: the relevant Linear team or project document, only when there is substantive context to preserve.
  • Use one appropriate home for each fact. Do not duplicate it across an issue comment and a lessons document, or post a separate announcement that it was documented.

Keep Slack updates selective

  • Post only when the user has requested a Slack update or an explicitly invoked workflow authorizes it. This skill does not authorize unsolicited messages.
  • For authorized updates, ask whether the channel's audience needs to know or act now: a consequential outcome, a decision needing input, or a blocker requiring help. A fact worth storing is not automatically worth broadcasting.
  • Skip routine progress, test results, commit/PR notices already covered by integrations, and announcements that a Linear note or document was updated. If nothing warrants the audience's attention, stay quiet unless the user explicitly requested that specific update.
  • Consolidate related outcomes into one short message: what changed for the audience, any action needed, and a source link. Continue an existing thread for follow-ups; avoid repeated top-level posts or cross-posting without a distinct audience need.
  • Account for indirect noise: Linear comments may already appear in Slack through an integration. Apply the same documentation threshold before writing them, and do not send a second Slack copy.
  • Notification routing and subscription settings are separate from agent writing behavior. Do not claim notifications are suppressed unless those settings were actually changed and verified.

© fastrepl, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/anarlog-workflow of fastrepl/anarlog.

Open the folder on GitHubat commit 259a04e

Compare with similar skills

Anarlog Workflow 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.

Anarlog Workflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Anarlog Workflow this skillfastrepl/anarlog9.4k—~1.5kAutomated safety check: PassMIT
Superpowers Feature WorkflowSYZ-Coder/superpowers-openspec-team-skills196—~891Automated safety check: PassMIT
Orca CLIstablyai/orca87k2 repos~593Automated safety check: PassMIT
Using Git Worktreesjulianromli/opencode-template14427 repos~1.4kAutomated safety check: PassNone
Chatgpt App Builderalpic-ai/skybridge2.1k—~1kAutomated safety check: PassMIT
Using Git Worktreesfarm-fe/farm5.6k13 repos~2kAutomated safety check: PassMIT

Similar skills

  • Superpowers Feature Workflow

    SYZ-Coder/superpowers-openspec-team-skills

    A skill your agent uses when feature work needs the Superpowers stages before or during implementation: brainstorming, design confirmation, implementation planning, worktree setup, test-driven…

    196 GitHub stars~891 tokensUpdated 3 mo ago
    Testing & QAAuto-check passed
  • Orca CLI

    stablyai/orca

    Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser…

    87k GitHub starsUsed in 2 repos~593 tokens
    Agent WorkflowsAuto-check passed
  • Using Git Worktrees

    julianromli/opencode-template

    A skill your agent uses when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory…

    144 GitHub starsUsed in 27 repos~1.4k tokens
    Agent WorkflowsAuto-check passed
  • Chatgpt App Builder

    alpic-ai/skybridge

    Guide developers through creating and updating ChatGPT plugins.

    2.1k GitHub stars~1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • A skill your agent uses when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git…

    5.6k GitHub starsUsed in 13 repos~2k tokens
    Agent WorkflowsAuto-check passed
  • Agent of Empires Session Manager

    agent-of-empires/agent-of-empires

    Starts, monitors and organizes coding agent sessions that run in tmux through the aoe command, including groups, profiles and worktree-based parallel work.

    3.3k GitHub stars~2.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from fastrepl/anarlog

All 32 skills in this repo
  • But

    fastrepl/anarlog

    Use only in the Anarlog repository when the active checkout branch is exactly gitbutler/workspace.

    9.4k GitHub stars~5.8k tokensUpdated today
    Auto-check passed
  • Create PRs

    fastrepl/anarlog

    Use only in the Anarlog repository when the active checkout branch is exactly gitbutler/workspace.

    9.4k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Fix Ready PRs

    fastrepl/anarlog

    Inspect every open non-draft PR for CI failures and unresolved Cursor Bugbot findings, then fix them on the existing PR branches.

    9.4k GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • No Use Effect

    fastrepl/anarlog

    Avoid direct React useEffect usage when writing or reviewing React components and hooks.

    9.4k GitHub stars~825 tokensUpdated today
    Auto-check passed
  • QA Critical UX

    fastrepl/anarlog

    QA Anarlog's critical Pro user journey on a signed staging candidate — onboarding, responsive launch, microphone and system-audio capture, automated summaries, and cloud sync.

    9.4k GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Reactive Sqlite UI

    fastrepl/anarlog

    Build SQLite-backed reactive UI in apps/desktop using stable patterns for reads, selection, forms, writes, and loading states.

    9.4k GitHub stars~699 tokensUpdated today
    Auto-check passed

Questions about Anarlog Workflow

What does Anarlog Workflow do?

Execute Anarlog work immediately while preserving useful decisions and non-obvious lessons in Linear. Anarlog Workflow is an agent skill from fastrepl/anarlog. Execute Anarlog work immediately while preserving useful decisions and non-obvious lessons in Linear.

When should I use Anarlog Workflow?

Anarlog Workflow fits situations like: anarlog repository; anarlog desktop; including related worktrees and ANLG issues; unrelated repositories.

How do I install Anarlog Workflow in Claude Code?

Run `npx skills add fastrepl/anarlog --skill anarlog-workflow -a claude-code`. Or copy the skill folder (.agents/skills/anarlog-workflow in fastrepl/anarlog) into .claude/skills/anarlog-workflow in your project. Claude Code loads it when a task matches its description.

How do I install Anarlog Workflow in Codex?

Run `npx skills add fastrepl/anarlog --skill anarlog-workflow -a codex`. Or copy the skill folder (.agents/skills/anarlog-workflow in fastrepl/anarlog) into .agents/skills/anarlog-workflow in your project. Codex loads it when a task matches its description.

Can I use Anarlog Workflow in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add fastrepl/anarlog --skill anarlog-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/anarlog-workflow, .gemini/skills/anarlog-workflow, .github/skills/anarlog-workflow and .opencode/skills/anarlog-workflow in your project.

What does Anarlog Workflow need to run?

SKILL.md names no scripts, command-line tools or credentials: Anarlog Workflow is instructions for the agent only.

Does Anarlog Workflow access the network?

SKILL.md names 1 domain. As links in the text: linear.app. This is read from the text; nothing was executed.

Is Anarlog Workflow safe to install?

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.

What licence does Anarlog Workflow use?

Anarlog Workflow is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Anarlog Workflow use?

About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Anarlog Workflow?

Skills that share tags, products or a category with Anarlog Workflow: Superpowers Feature Workflow (SYZ-Coder/superpowers-openspec-team-skills, 196 stars), Orca CLI (stablyai/orca, 87k stars), Using Git Worktrees (julianromli/opencode-template, 144 stars) and Chatgpt App Builder (alpic-ai/skybridge, 2.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Anarlog Workflow?

fastrepl (a GitHub organization) maintains it in fastrepl/anarlog, which has 9,445 GitHub stars. The repository holds 32 skills in this directory. The repository was last updated on October 7, 2026.

Source: fastrepl/anarlog on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.