CLI Docs Guidelines
CelestoAI/celesto
Review or write CLI documentation. An agent skill from CelestoAI/celesto.
Assess and explain questions about mental health and neurocognitive conditions against DSM-5-TR diagnostic criteria, and guide evidence-based conversations for clinicians, patients, and family…
$ npx skills add magnus919/agent-skills --skill dsm5 -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install magnus919/agent-skills dsm5 --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/magnus919/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/dsm5 .claude/skills/dsm5 && 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 "dsm5" agent skill from https://github.com/magnus919/agent-skills/tree/main/dsm5 into .claude/skills/dsm5/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dsm5", 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/magnus919/agent-skills/tree/main/dsm5Type 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 magnus919/agent-skills --skill dsm5 -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install magnus919/agent-skills dsm5 --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/dsm5 .agents/skills/dsm5 && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "dsm5" agent skill from https://github.com/magnus919/agent-skills/tree/main/dsm5 into .agents/skills/dsm5/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dsm5", 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 magnus919/agent-skills --skill dsm5 -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install magnus919/agent-skills dsm5 --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/dsm5 .cursor/skills/dsm5 && 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 "dsm5" agent skill from https://github.com/magnus919/agent-skills/tree/main/dsm5 into .cursor/skills/dsm5/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dsm5", 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/magnus919/agent-skills.git --path dsm5--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 magnus919/agent-skills --skill dsm5 -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install magnus919/agent-skills dsm5 --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/dsm5 .gemini/skills/dsm5 && 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 "dsm5" agent skill from https://github.com/magnus919/agent-skills/tree/main/dsm5 into .gemini/skills/dsm5/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dsm5", 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 magnus919/agent-skills dsm5Installs 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 magnus919/agent-skills --skill dsm5 -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/dsm5 .github/skills/dsm5 && 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 "dsm5" agent skill from https://github.com/magnus919/agent-skills/tree/main/dsm5 into .github/skills/dsm5/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dsm5", 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 magnus919/agent-skills --skill dsm5 -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install magnus919/agent-skills dsm5 --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/dsm5 .opencode/skills/dsm5 && 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 "dsm5" agent skill from https://github.com/magnus919/agent-skills/tree/main/dsm5 into .opencode/skills/dsm5/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dsm5", 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.
dsm5Assess and explain questions about mental health and neurocognitive conditions against DSM-5-TR diagnostic criteria, and guide evidence-based conversations for clinicians, patients, and family…
Dsm5 is an agent skill from magnus919/agent-skills. Assess and explain questions about mental health and neurocognitive conditions against DSM-5-TR diagnostic criteria, and guide evidence-based conversations for clinicians, patients, and family members. Use when someone asks about symptoms, possible conditions, differential diagnoses, diagnostic criteria, prevalence, specifiers, or wants to understand or explain a mental health or neurological condition in plain language. Do not use for formal diagnosis, treatment decisions, crisis intervention, legal or insurance…
Its SKILL.md is about 5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 72 other files, including scripts and reference files (for example `README.md`, `evals/evals.json` and `references/00-overview-and-method.md`).
It sits in Writing & Content, covering Health and fitness tracking and Plain language and style rules. The repository describes itself as: Curated collection of AI agent skills for Hermes and other agent frameworks. The licence is MIT.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 22b4723. 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.
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
python3From 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.
Dsm5 loads about 5k tokens when it runs, and up to ~386k if it reads all its reference files. Until then it costs about 151 tokens; SKILL.md has 2,556 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); the scripts in this folder are not scanned.
The full file from magnus919/agent-skills at commit 22b4723, republished under its MIT licence (© magnus919). 2,556 words, ~5,007 tokens.
.claude/skills/dsm5/SKILL.md (or your agent's skills folder). This skill also uses 70 other files; get the full folder from GitHub.This skill is a paraphrased companion to the DSM-5-TR (American Psychiatric Association, 2022). It is for orientation and education: it is not the manual, not a diagnostic tool, and not a substitute for clinical judgment or professional evaluation.
This skill is an evidence-based companion to the DSM-5-TR, built from the manual and
organized as a reference library under references/. Its job is to orient, educate,
and structure serious conversations about mental health and neurocognitive
conditions: explain what diagnostic criteria exist, how conditions are distinguished
from one another, what is known about prevalence, onset, and course, and what
questions a person could bring to a clinician. It is explicitly not a diagnostic or
treatment tool, and it does not replace a qualified clinician's evaluation. Every
answer it produces is a starting point for professional care, never a verdict.
Use this skill when:
Do not use this skill when:
When the conversation crosses into any of these, state the boundary plainly and route the person to a qualified professional.
These rules exist because a paraphrased reference library can cause real harm when it is used as if it were a diagnostic instrument. Each rule includes the reason it exists.
Follow these steps in order. Steps 1 and 2 gate everything else.
references/01-safety-and-boundaries.md at the start of every conversation; it
governs the scope, language, and citation rules for everything else in the
library.python3 scripts/lookup.py "<keyword>" and read the
file it recommends.references/40-cross-cutting-differentials.md and the per-chapter differential sections. Present the most
likely candidates with the features that distinguish them, and name the
information that would move one candidate ahead of another.Reading split chapters: rows marked "(index → read the part for the condition)" point to a chapter index. Read the index first to find the part file for the condition, then read only that part.
| When the question is about... | Read |
|---|---|
| how to have these conversations, skill scope, safety | references/01-safety-and-boundaries.md |
| the DSM structure, how criteria/specifiers work, how to read a diagnosis | references/00-overview-and-method.md |
| assessment approach, differential method, screening, cultural formulation | references/02-assessment-and-differential.md and references/32-assessment-measures-and-cultural-formulation.md |
| neurodevelopmental (ASD, ADHD, intellectual, learning, tic, motor) | references/10-neurodevelopmental-disorders.md (index → read the part for the condition) |
| schizophrenia/psychotic | references/11-schizophrenia-spectrum-and-other-psychotic.md (index → read the part for the condition) |
| bipolar | references/12-bipolar-and-related-disorders.md (index → read the part for the condition) |
| depression | references/13-depressive-disorders.md (index → read the part for the condition) |
| anxiety | references/14-anxiety-disorders.md (index → read the part for the condition) |
| OCD and related | references/15-obsessive-compulsive-and-related-disorders.md (index → read the part for the condition) |
| trauma/PTSD/acute stress/adjustment | references/16-trauma-and-stressor-related-disorders.md (index → read the part for the condition) |
| dissociation | references/17-dissociative-disorders.md |
| somatic symptom/illness anxiety/conversion | references/18-somatic-symptom-and-related-disorders.md |
| feeding and eating | references/19-feeding-and-eating-disorders.md (index → read the part for the condition) |
| elimination (enuresis/encopresis) | references/20-elimination-disorders.md |
| sleep-wake | references/21-sleep-wake-disorders.md (index → read the part for the condition) |
| sexual dysfunctions | references/22-sexual-dysfunctions.md (index → read the part for the condition) |
| gender dysphoria | references/23-gender-dysphoria.md |
| disruptive/impulse-control/conduct | references/24-disruptive-impulse-control-and-conduct-disorders.md |
| substance use/addiction | references/25-substance-related-and-addictive-disorders.md (index → read the part for the condition) |
| delirium, dementia, mild cognitive impairment, neurological conditions | references/26-neurocognitive-disorders.md (index → read the part for the condition) |
| personality disorders | references/27-personality-disorders.md (index → read the part for the condition) |
| paraphilic disorders | references/28-paraphilic-disorders.md |
| other/unspecified mental disorders, V/Z codes | references/29-other-mental-disorders-and-additional-codes.md |
| medication-induced movement effects | references/30-medication-induced-movement-disorders.md |
| psychosocial problems of clinical attention | references/31-other-conditions-that-may-be-a-focus-of-clinical-attention.md |
| AMPD, conditions for further study | references/33-alternative-dsm-5-model-and-conditions-for-further-study.md (index → read the part for the condition) |
| overlapping symptoms across conditions | references/40-cross-cutting-differentials.md (index → read the part for the condition) |
If there is any indication of risk of harm to self or others — current intent, a plan, means, a recent attempt, or statements such as "everyone would be better off without me" — the diagnostic conversation stops. Immediately:
Read references/01-safety-and-boundaries.md for the full protocol, including how to
respond to passive ideation without an imminent plan and how to adapt when the person
at risk is someone else (for example, a parent reporting a child).
The reference library was built from the DSM-5-TR (American Psychiatric Association, 2022) — specifically the user's text-revision copy — and paraphrases and summarizes the manual for orientation and education. This skill is an independent companion, not an official APA product. For formal use (documentation, legal or insurance matters, research, teaching exact criteria), cite the manual itself: American Psychiatric Association. Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, Text Revision (DSM-5-TR). Washington, DC: APA, 2022. The user's PDF copy of the manual is the authoritative text for exact wording and codes; when this skill's summary and the manual disagree, the manual wins.
A complete answer follows this structure, in order:
This is the shape every complete answer follows, regardless of audience. Clinician answers keep the same structure with criteria language and more detail; patient and family answers use plain language with the same six parts.
The response is complete when all of the following hold:
If any of these is missing, the response is not finished — complete the missing part before delivering it.
Do not read every reference file at once; that spends context the workflow does not need.
references/01-safety-and-boundaries.md (scope,
crisis protocol, calibrated language, citation rules).references/00-overview-and-method.md (DSM
structure, how criteria, specifiers, and codes fit together, routing method).references/40-cross-cutting-differentials.md.references/32-assessment-measures-and-cultural-formulation.md and
references/02-assessment-and-differential.md.references/33-alternative-dsm-5-model-and-conditions-for-further-study.md.python3 scripts/lookup.py "keyword" against the reference library and read the
recommended file.Large-file handling: reference files are sized to be read in a single call (each
part ≤ ~40,000 characters; indexes ≤ ~10,000). If a tool reports a file as truncated,
re-read it in chunks with an offset, or use python3 scripts/lookup.py to find the
specific part file instead of reading a whole chapter.
This skill bundles one script; there are no others to discover.
| Script | Purpose | Invocation |
|---|---|---|
scripts/lookup.py | Searches this skill's references/ library for a keyword or phrase and recommends the file(s) to read. Run it whenever the routing table does not obviously cover the condition, when locating a topic without knowing its chapter, or to find the specific part file of a split chapter instead of reading a whole one. | python3 scripts/lookup.py "<keyword>" |
Useful flags: --json (machine-readable output), --list (list every reference file with its H1 title), --max N (cap matches shown per file, default 10), -q (print only recommended file names).
lookup.py requires no third-party packages.references/ directory — the script searches that local library and nothing else.© magnus919, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 70 other files (scripts, references) in dsm5 of magnus919/agent-skills.
Open the folder on GitHubat commit 22b4723
Dsm5 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 |
|---|---|---|---|---|---|---|
| Dsm5 this skillmagnus919/agent-skills | 115 | — | ~5k | Automated safety check: Pass | MIT | |
| CLI Docs GuidelinesCelestoAI/celesto | 1k | — | ~805 | Automated safety check: Pass | Apache-2.0 | |
| Aqua Evaluationoracle/accelerated-data-science | 125 | — | ~1.6k | Automated safety check: Pass | UPL-1.0 | |
| Routine From Chatrome-os/rome | 743 | — | ~3.8k | Automated safety check: Pass | MIT | |
| Asd Ste100danyuchn/asd-ste100-skill | 4.3k | — | ~4.1k | Automated safety check: Pass | MIT | |
| Ponytail AuditDietrichGebert/ponytail | 160k | — | ~1.4k | Automated safety check: Pass | MIT |
CelestoAI/celesto
Review or write CLI documentation. An agent skill from CelestoAI/celesto.
oracle/accelerated-data-science
Evaluate LLM model quality using BERTScore, ROUGE, Perplexity, and Text Readability metrics on OCI AI Quick Actions (AQUA).
rome-os/rome
Turn a plain-language "do this automatically" request into a routine — either event-triggered ("text me when I get an email from my landlord") or scheduled ("remind me every Friday at 9am").
danyuchn/asd-ste100-skill
A skill your agent uses when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and…
DietrichGebert/ponytail
Quality audit of a whole repo: bugs, security holes, what breaks under real load, risky code without tests, slow paths, and what to delete, merge or split.
cursor/plugins
Applies four layers of technical-writing rules to docs, RFCs, readmes, PR descriptions and commit messages so a tired engineer follows them on the first read.
magnus919/agent-skills
Organize durable agent research outputs as summaries, analysis, and evidence dossiers.
magnus919/agent-skills
Build portable, first-person colored ASCII city engines and small GIS-derived city packs.
magnus919/agent-skills
Manage color workflows with ICC profiles, working spaces, gamut mapping, and color science.
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…
magnus919/agent-skills
Use Docker Compose to define, run, debug, and harden multi-container applications.
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.
Assess and explain questions about mental health and neurocognitive conditions against DSM-5-TR diagnostic criteria, and guide evidence-based conversations for clinicians, patients, and family…. Dsm5 is an agent skill from magnus919/agent-skills. Assess and explain questions about mental health and neurocognitive conditions against DSM-5-TR diagnostic criteria, and guide evidence-based conversations for clinicians, patients, and family members.
Dsm5 fits situations like: someone asks about symptoms; possible conditions; differential diagnoses; diagnostic criteria.
Run `npx skills add magnus919/agent-skills --skill dsm5 -a claude-code`. Or copy the skill folder (dsm5 in magnus919/agent-skills) into .claude/skills/dsm5 in your project. Claude Code loads it when a task matches its description.
Run `npx skills add magnus919/agent-skills --skill dsm5 -a codex`. Or copy the skill folder (dsm5 in magnus919/agent-skills) into .agents/skills/dsm5 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 magnus919/agent-skills --skill dsm5 -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dsm5, .gemini/skills/dsm5, .github/skills/dsm5 and .opencode/skills/dsm5 in your project.
Going by SKILL.md and its folder, Dsm5 needs the command-line tools its instructions call (python3). Our summary lists: Python 3.
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Dsm5 is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5k tokens (SKILL.md is roughly 20k 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 381k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Dsm5: CLI Docs Guidelines (CelestoAI/celesto, 1k stars), Aqua Evaluation (oracle/accelerated-data-science, 125 stars), Routine From Chat (rome-os/rome, 743 stars) and Asd Ste100 (danyuchn/asd-ste100-skill, 4.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
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.