Agent skill

Community Guides

by magnus919 in magnus919/agent-skills

Create, adapt, or revise practical community guides with locally grounded activities, participant worksheets, facilitator instructions, and maintenance plans.

MITAuto-check passedEducation

Install Community Guides

skills CLI
$ npx skills add magnus919/agent-skills --skill community-guides -a claude-code

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

GitHub CLI
$ gh skill install magnus919/agent-skills community-guides --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/magnus919/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/community-guides .claude/skills/community-guides && 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
community-guides
GitHub stars
115
Token cost
~3k tokens
SKILL.md length
1,494 words
Files
103 (incl. scripts, references)
Skills in repo
131
Repo updated
First seen
Licence
MIT

At a glance

Create, adapt, or revise practical community guides with locally grounded activities, participant worksheets, facilitator instructions, and maintenance plans.

  • Works in 5 steps: Establish the community brief → Establish outcomes and dependencies → Write coordinated materials → …
  • Neighborhood preparedness
  • SKILL.md covers When not to use, Choose the entry point, Workflow and Worked example and provenance
  • Calls python3

What it does

Community Guides is an agent skill from magnus919/agent-skills. Create, adapt, or revise practical community guides with locally grounded activities, participant worksheets, facilitator instructions, and maintenance plans. Use for neighborhood preparedness, mutual support, shared projects, and community learning programs. Do not use for travel guides, promotional brochures, standalone policies, simple document formatting, or live incident response.

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 106 other files, including scripts and reference files (for example `README.md`, `evals/evals.json` and `evals/files/absent-residents.json`).

It sits in Education, covering Educational content and Incident response. The repository describes itself as: Curated collection of AI agent skills for Hermes and other agent frameworks. The licence is MIT.

When your agent uses it

  • Neighborhood preparedness
  • Shared projects
  • Community learning programs
  • Promotional brochures

Example prompts

  • “/community-guides”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Establish the community brief
  2. Establish outcomes and dependencies
  3. Write coordinated materials
  4. Check and revise
  5. Hand off and maintain

What it can do on your machine

Read from SKILL.md and the folder at commit 22b4723. 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

    Ships 1 file in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    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

Community Guides loads about 3k tokens when it runs, and up to ~6.3k if it reads all its reference files. Until then it costs about 101 tokens; SKILL.md has 1,494 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~101
When it runs · the whole SKILL.md, loaded when a task matches
~3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.3k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from magnus919/agent-skills at commit 22b4723, republished under its MIT licence (© magnus919). 1,494 words, ~2,952 tokens.

Download SKILL.mdSave it as .claude/skills/community-guides/SKILL.md (or your agent's skills folder). This skill also uses 102 other files; get the full folder from GitHub.
name
community-guides
description
Create, adapt, or revise practical community guides with locally grounded activities, participant worksheets, facilitator instructions, and maintenance plans. Use for neighborhood preparedness, mutual support, shared projects, and community learning programs. Do not use for travel guides, promotional brochures, standalone policies, simple document formatting, or live incident response.
license
MIT
metadata.source
Original method informed by Ready Together; attribution and adaptation boundaries in references/source-pattern.md

Community Guides

Help a community turn a shared concern into feasible actions and a program that another facilitator can run. Success means usable materials, clear dependencies, and an honest account of what has been checked and what still needs participants.

When not to use

Use travel-guide for destination research and visitor itineraries, documents for document rendering or formatting alone, and product-discovery for product requirements research. This skill owns community program design. It does not replace specialist technical advice or direct an unfolding emergency.

Choose the entry point

  • Create: build from a community brief and evidence.
  • Adapt: inspect the supplied guide, retain useful activities, and explain changes caused by the new community's circumstances.
  • Revise: map feedback and changed facts to specific activities, worksheets, and facilitator instructions. Preserve useful material and show the revisions.

Default to editable Markdown. Honor the requested medium and scope: one workshop may need a single document; a series may need a workbook and separate host notes. Seven sessions is an example, not a requirement. Do not collect every possible artifact or impose a structured plan on a short prose-only request.

Scale the process to what can be decided now. When even the topic or community boundary is unknown, stop before module design: return a brief discovery draft (roughly one screen, normally under 300 words), at most three essential questions, and one optional next step. Do not expand that first response into a workbook, facilitation manual, repeated unknowns tables, or a publication approval process. Use a longer intake only when requested or needed to resolve known complexity. For bounded workshops, keep the participant handout short and put research notes and operational detail in a clearly separate facilitator section. For a narrow revision or unresolved source conflict, deliver the requested edited card or decision brief plus concise change/verification notes. Do not add a workshop, new worksheets, or multiple pilots unless they advance an explicitly requested learning outcome. A blocked local fact needs a targeted verification step, not a larger program. For a bounded revision, use the revision checklist. Its source-to-action audit and language/version preflight are required before handoff; an unsupported resident imperative must be removed, not merely flagged.

Workflow

1. Establish the community brief

Extract known facts before asking questions. Use the brief template. Identify who the guide serves, the desired capability, local setting, existing assets, participation constraints, available time, delivery medium, and guide owner. Ask only about missing facts that materially change the program. Continue useful drafting with explicit assumptions when possible; leave location-dependent advice unresolved when the location or evidence is missing.

An organizer's account is one perspective. Record whose experience is represented and whose input is still needed. Never invent consultation, consensus, accepted volunteer roles, or a local service's willingness to help.

Read localization and evidence when researching or adapting local content. Public research supports factual claims; residents' accounts support lived constraints and priorities. Both need attribution and appropriate limits.

When the user restricts research to supplied sources, honor that boundary for technical advice too. If feedback exposes an unsupported safety instruction, remove or quarantine it and mark the replacement for qualified verification; do not invent a new procedure from general knowledge. A provisional draft must not describe proposed verification or services as work already underway. Keep unsupported safety prose out of resident-facing copy; state that the replacement is unresolved until an authoritative source is supplied. Any editorial placeholder belongs in verification notes, not in instructions residents might act on.

2. Establish outcomes and dependencies

For each need, trace:

need → capability → activity → usable output → real action → check

Choose only modules that support the requested outcomes. Put prerequisite actions first: inventory before purchasing; agreement about sharing before a directory; accepted roles before reliance on a contact chain. Use low/no-cost entry actions and more involved options where useful, without defining effort solely by money.

Read activity and facilitation design before writing a new program. A brief explanation, reflection, shared exercise, debrief, and feasible next action form the default loop. Adapt it to the available time.

3. Write coordinated materials

Use the module template as the common record for participant and facilitator instructions. Include a completed fictional example and a blank copy of any unfamiliar worksheet. Make each exercise produce a decision, practice, map, plan, or other usable result; discussion alone needs a stated purpose.

Provide timing including introductions, interpretation, transitions, and closing. Name preparation, supplies, instructions, debrief questions, completion checks, and a fallback when prerequisites or helpers are unavailable. Distinguish private household records from voluntary shared information.

Translate constraints into actual alternatives: renters need actions within their control; offline participants need the essential instructions on paper; people who miss meetings need a catch-up route. Do not assume purchasing power, literacy, transportation, home ownership, or comfort disclosing personal needs. Translation needs competent language review; machine translation alone is not evidence of that. When revising an existing multilingual guide, retain its language coverage unless the user changes scope. Provide labeled draft translations where needed and identify the review still required; a promise to translate later does not supply the missing copy. For source-only revisions, translating supported content is allowed: the source boundary forbids adding facts, not expressing those facts in another language. Check the delivered resident copy language by language before handoff. An English card plus a note promising Spanish later is an incomplete bilingual revision.

Use the worksheet template, facilitator template, and maintenance template as needed. Every proposed shared role needs a way to obtain acceptance and a fallback if nobody accepts it.

For multi-module or multi-file guides, maintain one structured plan following the plan contract. Use it to keep module IDs, worksheets, timing, and evidence consistent across materials; do not expose JSON to participants.

Show full SKILL.md (548 more words)Show less
4. Check and revise

Perform a cold walkthrough: can a new facilitator prepare and run the session using only these materials? Can a participant complete each worksheet? Check that the guide and host notes agree, every decision has a next step, and necessary information is accessible in the intended medium. Resolve each named or numbered reference against the actual delivered worksheet: do its sections, checkbox counts, and field labels exist as described? Do not infer agreement just because both documents discuss the same activity. For responsibility maps, check for contradictory acceptance claims, overlapping assignments that exceed stated availability, and backups that rely on the same unavailable person. Preserve existing accepted scope; mark additional work proposed.

For source-only revisions, audit each resident-facing imperative against a supplied source. Remove unsupported directions even when they sound prudent (for example, an invented interim reporting route, waiting instruction, or emergency process). Use a factual unresolved-status notice instead. Keep historical unsafe wording only in a clearly labeled retired-source record, never in the active card.

For structured plans, run the read-only checker (Python 3.10+, standard library):

sh
python3 scripts/validate_guide.py /path/to/guide/plan.json

Run from the skill root or resolve the script from its installed location. Read its JSON diagnostics, fix errors, and account for warnings. This checks records, file references, and timing; it does not verify facts, prose agreement, translation, or community usability. Its tests run with:

sh
python3 -m unittest discover -s scripts -p 'test_*.py'

For PDF/Word output, use available documents tooling and inspect rendered pages, especially worksheets, page breaks, and print readability. If unavailable, deliver editable content and name the uncompleted rendering check.

Read review and evaluation for independent walkthroughs, pilot design, or skill evaluation. An agent simulation must be labeled as such.

5. Hand off and maintain

The entry-point scope rules take precedence over this full-program checklist. For discovery or a narrow card/decision-brief revision, supply only the requested artifact and concise verification/change notes. Add maintenance and ownership records only when the requested artifact or existing package calls for them.

For a full program, deliver the requested guide, relevant facilitator material, sources and adaptation notes, and a maintenance record. List unresolved local facts and proposed roles where they affect use. Name an owner or mark ownership unconfirmed, a review date or trigger, and how feedback should produce revisions.

Completion means requested artifacts exist, applicable checks are reported, and open dependencies are visible. Say ready for a community pilot when only agent checks have occurred. Claim participant-tested usability only with actual evidence. If an essential unknown prevents a usable guide, finish independent parts and ask the specific question needed to proceed; do not invent an answer or claim completion.

This skill produces local artifacts. Sending invitations, collecting residents' details, changing shared records, or publishing externally changes external state: Confirm the target, scope, and rollback path before acting. Read-only discovery may proceed without confirmation. Existing explicit authorization can supply that confirmation; guide creation alone does not authorize those actions.

Worked example and provenance

Read the original apartment example when a complete brief-to-guide model would help. Its plan and host notes demonstrate coordination. All people, constraints, and local evidence in it are fictional; it is not a technical outage manual.

Read source pattern and attribution when adapting Ready Together. Retain the participatory method while researching technical content afresh. Do not reproduce the source handbook's text, images, or worksheets without appropriate permission.

© magnus919, MIT. 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 102 other files (scripts, references) in community-guides of magnus919/agent-skills.

  • SKILL.md
  • README.md
  • evals/evals.json
  • evals/files/absent-residents.json
  • evals/files/conflicting-sources.json
  • evals/files/garden-seasonal-care.json
  • evals/files/multilingual-renters-outage.json
  • evals/files/participant-feedback.json
  • evals/files/rural-offline.json
  • evals/files/sparse-brief.json
  • evals/files/workshop-45-minute.json
  • evals/runs/README.md
  • evals/runs/REPORT.md
  • evals/runs/code-review-followup.md
  • evals/runs/final-regression/review.md
  • evals/runs/final-regression/revision.md
  • evals/runs/final-regression/run-metadata.json
  • … and 86 more

Open the folder on GitHubat commit 22b4723

Compare with similar skills

Community Guides 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.

Community Guides compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Community Guides this skillmagnus919/agent-skills115—~3kAutomated safety check: PassMIT
Privacy Data SecurityJoelLewis/finance_skills206—~11kAutomated safety check: PassMIT
OpenMAIC Setup and ExtensionTHU-MAIC/OpenMAIC40k—~1.7kAutomated safety check: NotesMIT
Codebase to Coursezarazhangrui/codebase-to-course5.7k—~4.4kAutomated safety check: PassNone
AI Engineering Project Tutorrohitg00/ai-engineering-from-scratch67k—~1.6kAutomated safety check: PassMIT
Hung-Yi Lee Teaching Stylevoidful/hung-yi-lee-skill1.3k—~13kAutomated safety check: PassNone

Similar skills

  • Privacy Data Security

    JoelLewis/finance_skills

    Design and operate privacy and data security programs for SEC-registered firms under Reg S-P, Reg S-ID, and SEC cybersecurity expectations.

    206 GitHub stars~11k tokensUpdated 2 mo ago
    EducationAuto-check passed
  • Guides setup, classroom generation and secondary development for OpenMAIC, the multi-agent interactive classroom, one confirmed phase at a time.

    40k GitHub stars~1.7k tokensUpdated today
    EducationAuto-check: notes
  • Codebase to Course

    zarazhangrui/codebase-to-course

    Turns a codebase into an interactive single-page HTML course for non-technical learners, with scroll modules, animated diagrams, quizzes and plain-English code translations.

    5.7k GitHub stars~4.4k tokensUpdated 6 mo ago
    EducationAuto-check passed
  • AI Engineering Project Tutor

    rohitg00/ai-engineering-from-scratch

    Tutors a learner through one stage of a hands-on AI engineering project per session: lesson, prediction, code, grader run and reflection, with hints but never full solutions.

    67k GitHub stars~1.6k tokensUpdated today
    EducationAuto-check passed
  • Hung-Yi Lee Teaching Style

    voidful/hung-yi-lee-skill

    Explains machine learning, LLMs, AI agents and speech modeling in a Hung-Yi Lee-inspired teaching style, drawing on a knowledge base built from his lectures and research references.

    1.3k GitHub stars~13k tokensUpdated 2 mo ago
    EducationAuto-check passed
  • Claude Code Self-Assessment Advisor

    lhfer/claude-howto-zh-cn

    Quizzes you on Claude Code in a quick or deep mode, scores your level across 10 topics and recommends what to learn next, in Chinese.

    2.3k GitHub stars~1.7k tokensUpdated 2 mo ago
    EducationAuto-check passed

More from magnus919/agent-skills

All 131 skills in this repo
  • Artifact Pyramids

    magnus919/agent-skills

    Organize durable agent research outputs as summaries, analysis, and evidence dossiers.

    119 GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Ascii City Engine

    magnus919/agent-skills

    Build portable, first-person colored ASCII city engines and small GIS-derived city packs.

    119 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Color Management

    magnus919/agent-skills

    Manage color workflows with ICC profiles, working spaces, gamut mapping, and color science.

    119 GitHub stars~2.6k tokensUpdated today
    Auto-check: notes
  • Data Scientist

    magnus919/agent-skills

    A skill your agent uses for PhD-level expertise in data science, statistics, and machine learning: rigorous statistical analysis, experimental design, causal inference, advanced modeling, research…

    119 GitHub stars~4.1k tokensUpdated today
    Auto-check passed
  • Docker Compose

    magnus919/agent-skills

    Use Docker Compose to define, run, debug, and harden multi-container applications.

    119 GitHub stars~2k tokensUpdated today
    Auto-check: notes
  • Fpga Development

    magnus919/agent-skills

    Design, review, simulate, and verify FPGA logic using explicit RTL contracts, clock and reset models, CDC analysis, timing constraints, and reproducible implementation evidence.

    119 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

Questions about Community Guides

What does Community Guides do?

Create, adapt, or revise practical community guides with locally grounded activities, participant worksheets, facilitator instructions, and maintenance plans. Community Guides is an agent skill from magnus919/agent-skills. Create, adapt, or revise practical community guides with locally grounded activities, participant worksheets, facilitator instructions, and maintenance plans.

When should I use Community Guides?

Community Guides fits situations like: neighborhood preparedness; shared projects; community learning programs; promotional brochures.

How do I install Community Guides in Claude Code?

Run `npx skills add magnus919/agent-skills --skill community-guides -a claude-code`. Or copy the skill folder (community-guides in magnus919/agent-skills) into .claude/skills/community-guides in your project. Claude Code loads it when a task matches its description.

How do I install Community Guides in Codex?

Run `npx skills add magnus919/agent-skills --skill community-guides -a codex`. Or copy the skill folder (community-guides in magnus919/agent-skills) into .agents/skills/community-guides in your project. Codex loads it when a task matches its description.

Can I use Community Guides 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 magnus919/agent-skills --skill community-guides -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/community-guides, .gemini/skills/community-guides, .github/skills/community-guides and .opencode/skills/community-guides in your project.

What does Community Guides need to run?

Going by SKILL.md and its folder, Community Guides needs the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Community Guides 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 Community Guides 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Community Guides use?

Community Guides is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Community Guides use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.4k tokens, read only when the agent opens those files.

What are the alternatives to Community Guides?

Skills that share tags, products or a category with Community Guides: Privacy Data Security (JoelLewis/finance_skills, 206 stars), OpenMAIC Setup and Extension (THU-MAIC/OpenMAIC, 40k stars), Codebase to Course (zarazhangrui/codebase-to-course, 5.7k stars) and AI Engineering Project Tutor (rohitg00/ai-engineering-from-scratch, 67k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Community Guides?

magnus919 (a GitHub user) maintains it in magnus919/agent-skills, which has 115 GitHub stars. The repository holds 131 skills in this directory. The repository was last updated on October 10, 2026.

Source: magnus919/agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.