Analyze Logs
activepieces/activepieces
Analyze application logs from the .evlog/logs/ directory. An agent skill from activepieces/activepieces.
Review and maintain the technical instructions Roam gives coding agents: shipped skills, tool descriptions, preset guidance and generated instruction blocks.
Install Roam Agent Guidance
$ npx skills add Cranot/roam-code --skill roam-agent-guidance -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Cranot/roam-code roam-agent-guidance --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/Cranot/roam-code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/roam-agent-guidance .claude/skills/roam-agent-guidance && 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 "roam-agent-guidance" agent skill from https://github.com/Cranot/roam-code/tree/main/.agents/skills/roam-agent-guidance into .claude/skills/roam-agent-guidance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "roam-agent-guidance", 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/Cranot/roam-code/tree/main/.agents/skills/roam-agent-guidanceType 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 Cranot/roam-code --skill roam-agent-guidance -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Cranot/roam-code roam-agent-guidance --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Cranot/roam-code.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/roam-agent-guidance .agents/skills/roam-agent-guidance && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "roam-agent-guidance" agent skill from https://github.com/Cranot/roam-code/tree/main/.agents/skills/roam-agent-guidance into .agents/skills/roam-agent-guidance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "roam-agent-guidance", 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 Cranot/roam-code --skill roam-agent-guidance -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Cranot/roam-code roam-agent-guidance --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Cranot/roam-code.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/roam-agent-guidance .cursor/skills/roam-agent-guidance && 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 "roam-agent-guidance" agent skill from https://github.com/Cranot/roam-code/tree/main/.agents/skills/roam-agent-guidance into .cursor/skills/roam-agent-guidance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "roam-agent-guidance", 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/Cranot/roam-code.git --path .agents/skills/roam-agent-guidance--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 Cranot/roam-code --skill roam-agent-guidance -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Cranot/roam-code roam-agent-guidance --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Cranot/roam-code.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/roam-agent-guidance .gemini/skills/roam-agent-guidance && 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 "roam-agent-guidance" agent skill from https://github.com/Cranot/roam-code/tree/main/.agents/skills/roam-agent-guidance into .gemini/skills/roam-agent-guidance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "roam-agent-guidance", 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 Cranot/roam-code roam-agent-guidanceInstalls 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 Cranot/roam-code --skill roam-agent-guidance -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Cranot/roam-code.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/roam-agent-guidance .github/skills/roam-agent-guidance && 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 "roam-agent-guidance" agent skill from https://github.com/Cranot/roam-code/tree/main/.agents/skills/roam-agent-guidance into .github/skills/roam-agent-guidance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "roam-agent-guidance", 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 Cranot/roam-code --skill roam-agent-guidance -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Cranot/roam-code roam-agent-guidance --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Cranot/roam-code.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/roam-agent-guidance .opencode/skills/roam-agent-guidance && 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 "roam-agent-guidance" agent skill from https://github.com/Cranot/roam-code/tree/main/.agents/skills/roam-agent-guidance into .opencode/skills/roam-agent-guidance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "roam-agent-guidance", 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.
Facts
- Skill name
roam-agent-guidance- GitHub stars
- 517
- Token cost
- ~1.3k tokens
- SKILL.md length
- 692 words
- Files
- 2
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Review and maintain the technical instructions Roam gives coding agents: shipped skills, tool descriptions, preset guidance and generated instruction blocks.
- Misleading usage guidance
- SKILL.md covers Find the instruction and its…, Make the next action usable and Check the instruction, not…
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Not product persuasion
What it does
Roam Agent Guidance is an agent skill from Cranot/roam-code. Review and maintain the technical instructions Roam gives coding agents: shipped skills, tool descriptions, preset guidance and generated instruction blocks. Use for stale, unreachable or misleading usage guidance, not product persuasion, general repo exploration or runtime defect repair.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Development, covering MCP servers. It works with Model Context Protocol. The repository describes itself as: Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 commands, 246 MCP tools, change-safety gates, audit evidence, zero API keys. The licence is Apache-2.0.
When your agent uses it
- Misleading usage guidance
- Not product persuasion
- General repo exploration
- Runtime defect repair
Example prompts
- “/roam-agent-guidance”
What it can do on your machine
Read from SKILL.md and the folder at commit f0bdb63. 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
No URLs in SKILL.md.
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
Roam Agent Guidance loads about 1.3k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 692 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.
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 Cranot/roam-code at commit f0bdb63, republished under its Apache-2.0 licence (© Cranot). 692 words, ~1,315 tokens.
Download SKILL.mdSave it as
.claude/skills/roam-agent-guidance/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- roam-agent-guidance
- description
- Review and maintain the technical instructions Roam gives coding agents: shipped skills, tool descriptions, preset guidance and generated instruction blocks. Use for stale, unreachable or misleading usage guidance, not product persuasion, general repo exploration or runtime defect repair.
Roam agent guidance
Make an instruction lead an agent to an available operation and a conclusion the returned evidence can support. This is instruction maintenance, not a new agent interface or another general hardening pass. A mixed document can contain both a human adoption explanation and technical operating instructions; review each for its own job rather than rewriting both as a pitch or a gate checklist.
Find the instruction and its owner
Resolve the Roam checkout and read current AGENTS.md. Use
docs/understanding-roam.md for product and evidence meaning,
docs/agent-cli.md for invocation guidance and docs/mcp-tools.md for MCP
presets and inventory ownership. Read the relevant sections of
docs/concepts/verification-evidence.md and docs/concepts/detector-evidence.md
when the instruction asks an agent to act on findings. A frozen packet can
supply these authorities for a trial; missing sources remain missing.
Trace each changed instruction to its source: handwritten guidance, tool
docstring, maintained generator, or user-owned annotation. Inspect generated
markers and the current generator before editing. For example, the MCP inventory
names its owner in docs/mcp-tools.md; minimap's command documents its sentinel
block and durable notes input. Preserve unrelated notes and regenerate the owned
output when authorized. Do not invent a new universal surface map or hand-edit
generated copies because they are the first matching file.
Bind syntax and availability to the intended version, client, preset and shell. Use the checkout's verified venv, preserving an explicitly requested launcher; inspect actual help/tool schemas and save full JSON where acted on. A CLI flag is not necessarily an MCP argument. A registered tool may be absent from the connected preset; expansion guidance may require a server restart. Do not change the user's configuration merely to make an example work. Help proves syntax, not execution, coverage or supported behavior on another release.
Exercise disputed examples from the reader's intended state, not just Roam's checkout. A clean committed CI checkout differs from an unstaged working diff; a repository-relative rules directory or optional dependency may not exist after the stated install. Use a small representative fixture to verify selection and prerequisites, and disclose any stubbed boundary. Keep simple verified examples short rather than adding every possible environment caveat.
Show full SKILL.md (340 more words)Show less
Make the next action usable
State a concrete operation and what its result is for. A discovery example can remain short; an instruction approving a change needs the evidence conditions for that decision. Indexed callers are not a census of every possible caller, and a suggested test list is not executed coverage. Remove unsupported savings or completeness claims without making correct instructions timid or unusable.
For evidence-consuming guidance, state which observations support the requested decision. Follow the verification guide's command-specific distinctions between completed zeros, violations, partial computation and delivery-only elision; preserve useful findings without calling them complete clearance. Required scope, freshness and detail still matter. Resolve conflicting prose against the actual contract and consumer requirements; do not silently choose the easier rule.
Keep imperative tool text and executable follow-ups aligned with the actual contract. Consult AGENTS.md for current facts/verdict conventions; do not copy its changing vocabulary lists. Counts belong to maintained generators; a performance comparison needs qualified measurement, not intuition or old prose. Instruction-only corrections do not require inventing a runtime defect. A producer/consumer defect discovered here needs its own authorized repair and evidence qualification; a wording change cannot repair that behavior.
Check the instruction, not just the sentence
Record revised and retained surfaces with their owners and unresolved claims. Check the command/configuration promise against actual read-only help or inventory. When a change alters which result states a reader accepts, or a disputed reading matters to a decision, test a fresh reader with only the proposed instructions and representative valid, partial and failed results. Include a correct no-change case and withhold the desired answer. Routine syntax or spelling repairs need their relevant checks, not a new model trial. A simulated reading is not a live-client witness or a publication gate.
Keep a correct section when no change improves its use. Reconcile affected
siblings without copying the same paragraph everywhere. Keep private trial
records under internal/; distinguish draft, locally checked, released and
observed client behavior. Installation or a schema-valid tool description does
not establish that an agent actually uses the instruction.
© Cranot, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .agents/skills/roam-agent-guidance of Cranot/roam-code.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit f0bdb63
Compare with similar skills
Roam Agent Guidance 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 |
|---|---|---|---|---|---|---|
| Roam Agent Guidance this skillCranot/roam-code | 517 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Analyze Logsactivepieces/activepieces | 25k | 1 repos | ~1.6k | Automated safety check: Pass | MIT | |
| ReleasePrefectHQ/fastmcp | 28k | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | |
| Review PRPrefectHQ/fastmcp | 28k | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| ObservalObserval/Observal | 4.3k | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| Ue Code AuthoringJasonMa0012/MooaToon | 750 | — | ~1.9k | Automated safety check: Notes | Custom licence |
Similar skills
Release
PrefectHQ/fastmcp
Cut a FastMCP release end to end. An agent skill from PrefectHQ/fastmcp.
Review PR
PrefectHQ/fastmcp
Assess a FastMCP pull request for justified behavior, compatibility, and correctness, then follow CI and review feedback to a revision-specific verdict.
Observal
Observal/Observal
A skill your agent uses when starting any task the organization may already have an approved skill, prompt, MCP server, or Agent for: reviewing code, a commit, a diff, or a pull request; writing…
Ue Code Authoring
JasonMa0012/MooaToon
A skill your agent uses when writing or modifying UE C++ (classes, actors, components, subsystems, interfaces, function libraries) with Rider MCP available.
Misakanet Failure Memory
Ikalus1988/MisakaNet
Search and record failure-recovery lessons from real engineering sessions; submit and verify debugging lessons across the MisakaNet network.
More from Cranot/roam-code
All 9 skills in this repoRoam
Cranot/roam-code
Codebase comprehension via roam-code CLI. An agent skill from Cranot/roam-code.
Roam Evidence Hardening
Cranot/roam-code
Investigate and harden Roam detectors, CLI/MCP result contracts, and evidence consumers when dogfooding or correcting incomplete, misleading, or inconsistent analysis.
Roam Lesson Maintenance
Cranot/roam-code
Turn a reproduced or recurring Roam failure into a durable correction, regression control or narrowly scoped project skill, and reconcile conflicting lessons.
Roam Measurement Design
Cranot/roam-code
Design or interpret a comparison of Roam performance, detector accuracy, retrieval or workflow value.
Roam Milestone Planning
Cranot/roam-code
Define or revise a Roam product milestone and its engineering, adoption and offer-readiness sequence.
Roam Release Readiness
Cranot/roam-code
Qualify a Roam commit or accumulated batch for package, website, or server publication; reconcile source, tests, review, CI and deployed identities, and identify the next authorized release step.
Related
Works with
Categories
Questions about Roam Agent Guidance
What does Roam Agent Guidance do?
Review and maintain the technical instructions Roam gives coding agents: shipped skills, tool descriptions, preset guidance and generated instruction blocks. Roam Agent Guidance is an agent skill from Cranot/roam-code. Review and maintain the technical instructions Roam gives coding agents: shipped skills, tool descriptions, preset guidance and generated instruction blocks.
When should I use Roam Agent Guidance?
Roam Agent Guidance fits situations like: misleading usage guidance; not product persuasion; general repo exploration; runtime defect repair.
How do I install Roam Agent Guidance in Claude Code?
Run `npx skills add Cranot/roam-code --skill roam-agent-guidance -a claude-code`. Or copy the skill folder (.agents/skills/roam-agent-guidance in Cranot/roam-code) into .claude/skills/roam-agent-guidance in your project. Claude Code loads it when a task matches its description.
How do I install Roam Agent Guidance in Codex?
Run `npx skills add Cranot/roam-code --skill roam-agent-guidance -a codex`. Or copy the skill folder (.agents/skills/roam-agent-guidance in Cranot/roam-code) into .agents/skills/roam-agent-guidance in your project. Codex loads it when a task matches its description.
Can I use Roam Agent Guidance 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 Cranot/roam-code --skill roam-agent-guidance -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/roam-agent-guidance, .gemini/skills/roam-agent-guidance, .github/skills/roam-agent-guidance and .opencode/skills/roam-agent-guidance in your project.
What does Roam Agent Guidance need to run?
SKILL.md names no scripts, command-line tools or credentials: Roam Agent Guidance is instructions for the agent only.
Does Roam Agent Guidance access the network?
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.
Is Roam Agent Guidance 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 Roam Agent Guidance use?
Roam Agent Guidance is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Roam Agent Guidance use?
About 1.3k tokens (SKILL.md is roughly 5.3k 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 Roam Agent Guidance?
Skills that share tags, products or a category with Roam Agent Guidance: Analyze Logs (activepieces/activepieces, 25k stars), Release (PrefectHQ/fastmcp, 28k stars), Review PR (PrefectHQ/fastmcp, 28k stars) and Observal (Observal/Observal, 4.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Roam Agent Guidance?
Cranot (a GitHub user) maintains it in Cranot/roam-code, which has 517 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 10, 2026.
Source: Cranot/roam-code on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.