New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Adopt

by evloghq in evloghq/evlog

Work on a repository's use of evlog with the evlog CLI. An agent skill from evloghq/evlog.

MITAuto-check passedDevelopment

Install Adopt

skills CLI
$ npx skills add evloghq/evlog --skill adopt -a claude-code

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

GitHub CLI
$ gh skill install evloghq/evlog adopt --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/evloghq/evlog.git skills-src && mkdir -p .claude/skills && cp -r skills-src/apps/evi/agent/skills/adopt .claude/skills/adopt && 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
adopt
GitHub stars
1.9k
Token cost
~1.2k tokens
SKILL.md length
686 words
Files
1
Skills in repo
22
Repo updated
First seen
Licence
MIT

At a glance

Work on a repository's use of evlog with the evlog CLI. An agent skill from evloghq/evlog.

  • Works in 5 steps: evlog init --dry-run --yes to see what… → Take the entry points from map, worst… → evlog agents --yes --no-skills writes… → …
  • Tasks that involve Observability
  • SKILL.md covers Before anything: where you are, Instrument, Review and Verify, plus 3 more sections
  • Calls npx

What it does

Adopt is an agent skill from evloghq/evlog. Work on a repository's use of evlog with the evlog CLI. Load this when asked to instrument an app or server, add or improve observability, review logging in code or a pull request, verify an evlog setup or a coverage score, analyze what an app logged, or add an audit trail. It routes to the CLI command that grounds the task and the published skill that carries the procedure.

Its SKILL.md is about 1.2k 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 Development, covering Observability and Pull requests. The repository describes itself as: Digging through logs is not observability. It's hope — wide events, structured errors, TypeScript-first, every runtime. The licence is MIT.

When your agent uses it

  • Tasks that involve Observability
  • Tasks that involve Pull requests

Example prompts

  • “/adopt”

Requirements

  • Node.js

Workflow steps

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

  1. evlog init --dry-run --yes to see what the CLI would change, then evlog init --yes (add --drain fs for a dev-only file drain). Skip when…
  2. Take the entry points from map, worst score first. Fix by rule weight: wide-event (40), then audit (25), structured-errors (20)…
  3. evlog agents --yes --no-skills writes the evlog block into the repository's own AGENTS.md, so the next agent in that repo follows the same…
  4. Run the repository's own checks, then evlog map --json --no-write again.
  5. One pull request. The body carries the score before and after, the entry points changed, the commands run, and the revision. A drain that…

What it can do on your machine

Read from SKILL.md and the folder at commit 59a105f. 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

    Shell commands in SKILL.md call:

    • npx

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

  • Network

    No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

    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

Adopt loads about 1.2k tokens when it runs. Until then it costs about 96 tokens; SKILL.md has 686 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~96
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 evloghq/evlog at commit 59a105f, republished under its MIT licence (© evloghq). 686 words, ~1,225 tokens.

Download SKILL.mdSave it as .claude/skills/adopt/SKILL.md (or your agent's skills folder).
name
adopt
description
Work on a repository's use of evlog with the evlog CLI. Load this when asked to instrument an app or server, add or improve observability, review logging in code or a pull request, verify an evlog setup or a coverage score, analyze what an app logged, or add an audit trail. It routes to the CLI command that grounds the task and the published skill that carries the procedure.

Adopt evlog in a repository

Five verbs, one loop. Every task here starts by measuring the repository, does its work, and ends by measuring again. The number is what makes the result reviewable.

Before anything: where you are

  • On the home repository the checkout is /workspace/repo, dependencies installed. On any other repository, git__checkout then git__install, and work in /workspace/<owner>/<repo>; that checkout is cold, so say so when you report its checks.
  • evlog is on PATH: the CLI built from the current main. Run it from the target repository's root, never npx @evlog/cli.
  • Two commands ground every verb. Run both first, together:
    • evlog doctor --json: the stack, whether evlog is installed, which drains exist.
    • evlog map --json --no-write: the global score and every entry point with its rule findings. It covers Nuxt, Nitro, Next.js, TanStack Start and Hono. On another framework it refuses; then there is no score, and the framework section of review-logging-patterns is the procedure.
  • Load review-logging-patterns before touching code. Its framework sections, drain and enricher tables, and references/code-review.md are the rules. Do not instrument from memory.

Instrument

The request: add evlog, or make an app observable.

  1. evlog init --dry-run --yes to see what the CLI would change, then evlog init --yes (add --drain fs for a dev-only file drain). Skip when doctor says evlog is already wired.
  2. Take the entry points from map, worst score first. Fix by rule weight: wide-event (40), then audit (25), structured-errors (20), page-error-handling (20), context (15), error-handling (15). evlog map <file> --no-write prints the suggested shape for one entry point.
  3. evlog agents --yes --no-skills writes the evlog block into the repository's own AGENTS.md, so the next agent in that repo follows the same conventions. Skip --no-skills only when the person asked for the skills installed there.
  4. Run the repository's own checks, then evlog map --json --no-write again.
  5. One pull request. The body carries the score before and after, the entry points changed, the commands run, and the revision. A drain that needs credentials is wired with the env var name and nothing else; never invent a token.

Review

The request: look at logging in a diff, a file, or a pull request.

  • evlog map <file> --no-write for each entry point the diff touches; the findings are the comments, in the words of references/code-review.md.
  • With an evlog.map.json in the repository, evlog map --baseline evlog.map.json --no-write says whether the diff regressed coverage.
  • Comment on what the diff does to observability, not on style. Requirements are defects; opportunities (error-catalog, audit-coverage) are suggestions.
Show full SKILL.md (265 more words)Show less

Verify

The request: does this setup work, is the score real, is this claim true.

  • evlog doctor --json for configuration claims. A green doctor is a claim about wiring, not about events.
  • For a claim about emitted events, run the code: start the app or call the handler in the sandbox with the fs drain, then read .evlog/logs/ as analyze-logs describes. Report the event you saw, or that nothing was written.
  • To lock a score, propose evlog map --min-score <n> or --baseline in the repository's CI, with the number the current tree earns.

Monitor

The request: what happened, what is slow, what failed.

  • Load analyze-logs. It reads .evlog/logs/*.jsonl (NDJSON or pretty) and the memory drain endpoint, with readFsLogs() from evlog/fs for anything beyond a grep.
  • The sandbox sees local drains only. A production drain (Axiom, Datadog, PostHog, and the others) is not reachable from here; say so and point at the drain's own UI. The telemetry skill is about the CLI's own usage data, not the person's application.

Audit

The request: track who did what, denials, retention, a compliance review.

  • Load build-audit-logs. It carries the call sites, withAudit, denials, catalogs, and the review checklist. map's audit rule (25) and audit-coverage opportunity tell you which handlers are missing one.

Report

Lead with the number: the score before and after, or the count of entry points fixed, or the events read. Then the commands, their observed results, and the revision. A check you could not run is stated as not run. Nothing here is verified by reading source alone; the CLI and the logs are the evidence.

© evloghq, 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 apps/evi/agent/skills/adopt of evloghq/evlog.

Open the folder on GitHubat commit 59a105f

Compare with similar skills

Adopt 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.

Adopt compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Adopt this skillevloghq/evlog1.9k—~1.2kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Babysit PR To Pass CIsgl-project/sglang37k2 repos~3kAutomated safety check: PassApache-2.0
Ansible Development Contextansible/ansible71k—~427Automated safety check: PassGPL-3.0
Ansible Backport Creatoransible/ansible71k—~1.2kAutomated safety check: PassGPL-3.0
Cap Feature Building WorkflowCapSoftware/Cap23k—~2.5kAutomated safety check: WarnCustom licence

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Babysit PR To Pass CI

    sgl-project/sglang

    Start and persistently pursue a goal to babysit an SGLang pull request until selected GitHub Actions workflows pass on the latest PR head.

    37k GitHub starsUsed in 2 repos~3k tokens
    DevelopmentAuto-check passed

  • Ansible Development Context

    ansible/ansible

    Load Ansible project development guidelines, testing conventions, PR review processes, and code structure reference into context

    71k GitHub stars~427 tokensUpdated today
    DevelopmentAuto-check passed

  • Ansible Backport Creator

    ansible/ansible

    Creates backports of a merged Ansible devel pull request onto the right stable branches by cherry-picking its merge commit onto new backport branches.

    71k GitHub stars~1.2k tokensUpdated today
    DevelopmentAuto-check passed

  • Cap Feature Building Workflow

    CapSoftware/Cap

    Builds a Cap feature in an isolated Git worktree with disposable dev resources, verification, a recorded demo and a neutral pull request, started with /building.

    23k GitHub stars~2.5k tokensUpdated today
    DevelopmentAuto-check: warnings

  • CI Act Run

    chewiebug/GCViewer

    Run the full build-and-deploy.yaml workflow locally via act + Docker.

    4.6k GitHub stars~2.4k tokensUpdated 3 mo ago
    DevelopmentAuto-check: notes

More from evloghq/evlog

All 22 skills in this repo

  • evlog Adapter Creator

    evloghq/evlog

    Walks through adding a new built-in evlog drain adapter for an observability platform: source, build config, exports, tests, docs and PR scope.

    1.9k GitHub stars~2.9k tokensUpdated today
    Auto-check passed

  • evlog Enricher Creator

    evloghq/evlog

    Guides adding a new built-in enricher to the evlog package, covering the source, tests, docs, README, a related skill and a changeset.

    1.9k GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Evlog Log Analyzer

    evloghq/evlog

    Reads the structured wide-event logs that evlog writes to .evlog/logs/ so the agent can debug errors, find slow requests and explain what the app did.

    1.9k GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • evlog Framework Integration

    evloghq/evlog

    Walks a contributor through adding a new HTTP framework integration to the evlog logging package: middleware source, build entry, exports, tests, example app and docs.

    1.9k GitHub stars~5k tokensUpdated today
    Auto-check: notes

  • evlog Map Rule Creator

    evloghq/evlog

    Walks through adding a new rule or framework adapter to `evlog map` in @evlog/cli, from the rule source and registry to types, tests, docs and the published skill.

    1.9k GitHub stars~2.9k tokensUpdated today
    Auto-check passed

  • evlog Content Writing

    evloghq/evlog

    Rules for writing and reviewing evlog docs, blog posts, READMEs, skills and AGENTS.md files, with separate review and rewrite roles, a house voice and a catalog of AI-sounding tells.

    1.9k GitHub stars~2.9k tokensUpdated today
    Auto-check passed

Categories

Questions about Adopt

What does Adopt do?

Work on a repository's use of evlog with the evlog CLI. An agent skill from evloghq/evlog. Adopt is an agent skill from evloghq/evlog. Work on a repository's use of evlog with the evlog CLI.

When should I use Adopt?

Adopt fits situations like: tasks that involve Observability; tasks that involve Pull requests.

How do I install Adopt in Claude Code?

Run `npx skills add evloghq/evlog --skill adopt -a claude-code`. Or copy the skill folder (apps/evi/agent/skills/adopt in evloghq/evlog) into .claude/skills/adopt in your project. Claude Code loads it when a task matches its description.

How do I install Adopt in Codex?

Run `npx skills add evloghq/evlog --skill adopt -a codex`. Or copy the skill folder (apps/evi/agent/skills/adopt in evloghq/evlog) into .agents/skills/adopt in your project. Codex loads it when a task matches its description.

Can I use Adopt 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 evloghq/evlog --skill adopt -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/adopt, .gemini/skills/adopt, .github/skills/adopt and .opencode/skills/adopt in your project.

What does Adopt need to run?

Going by SKILL.md and its folder, Adopt needs the command-line tools its instructions call (npx). Our summary lists: Node.js.

Does Adopt access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Adopt 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 Adopt use?

Adopt 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 Adopt use?

About 1.2k tokens (SKILL.md is roughly 4.9k 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 Adopt?

Skills that share tags, products or a category with Adopt: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Babysit PR To Pass CI (sgl-project/sglang, 37k stars), Ansible Development Context (ansible/ansible, 71k stars) and Ansible Backport Creator (ansible/ansible, 71k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Adopt?

evloghq (a GitHub organization) maintains it in evloghq/evlog, which has 1,885 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 6, 2026.

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