skill
Skill4 starsChanged todayMITView on GitHub
[oh-my-agy] Author, scaffold, validate, and manage Antigravity skills: list, init, add, edit, remove, search, info, sync, setup, scan, validate, test, eval, and extract SKILL.md folders across project, shared (.agents/skills.json), and user scopes with progressive-disclosure references/ and scripts/ bundles. Use for $skill <command> or when creating, scaffolding, validating, sharing, or capturing a repeatable workflow as a SKILL.md skill.
66 other projects use a version of this.
Adopted by
Most recently taken up by
- nmamano/isomuxtheir own version, first seen Nov 15, 2026
- Qson8/topicscouttheir own version, first seen Nov 15, 2026
- mlk010173/sitejacktheir own version, first seen Nov 15, 2026
- Yeachan-Heo/oh-my-claudecodetheir own version, first seen Nov 9, 2026
- thenavidm/skill-buildertheir own version, first seen Nov 8, 2026
- HelloRuru/claude-teams-gotheir own version, first seen Nov 8, 2026
Used with
Projects with it also use visual-verdict, commands and 3 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
LucasCooperBeySkillvisual-verdict
Structured visual QA verdict for screenshot-to-reference comparisons. Returns JSON scores driving edit iterations. Use after any UI implementation to verify visual fidelity.
Also in 3 projects that use this
0x-ShashiSkillcommands
Structured command patterns for invoking audit capabilities through slash commands. Use when triggering /audit, /scan, /checklist, /report, /severity, /patterns, or other slash commands that map to underlying skills and load the correct context for each workflow.
Also in 3 projects that use this
woosikkimSkilldeepinit
Generate hierarchical AGENTS.md codebase maps for agent context
Also in 3 projects that use this
zephyrpersonalSkillultrawork
Obsessive task completion mode (Sisyphus Mode) - activates maximum intensity work with todo continuation enforcement
Also in 3 projects that use this
LangChainSkillremember
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture learnings.
Also in 5 projects that use this
Other versions66 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 66
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- Yeachan-Heo/oh-my-codex★ 34ksame name
- tradecatlabs/vibe-coding-cn★ 18ksame name
- tukuaiai/vibe-coding-cn★ 18ksame name
- liyue-aigc/female-portrait-director★ 1.6ksame name
- sundial-org/skills★ 151same name
- build23w/fdv.lol★ 128same name
- builders-toronto/fdv.lol★ 128same name
- redf0x1/camofox-mcp★ 124same name
56 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- rules/AGENTS.mdAGENTS.md
- ai-slop-cleanerSkill
- analyzeSkill
- askSkill
- autopilotSkill
- cancelSkill
- code-reviewSkill
- deep-interviewSkill
- deep-researchSkill
- doctorSkill
- hudSkill
- loftSkill
- modernizeSkill
- performance-goalSkill
- prSkill
- ralplanSkill
- releaseSkill
- teamSkill
- threat-modelSkill
- ultragoalSkill
- ultraqaSkill
- visual-ralphSkill
- wikiSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 1 is distinctive, and 9 are very specific to this project.
0
Common
Most of the 48 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
9
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Create, scaffold, validate, evaluate, and maintain self-contained Antigravity SKILL.md directories with $skill.
- Very specific: line 28
Every skill is a directory <root>/<name>/ whose entrypoint is SKILL.md:
- Very specific: line 66
SDO Workflow-Summary Guard: never put -> step-chain arrows or full step recipes in description (models skip reading SKILL.md when …
- Very specific: line 87
Zero auxiliary clutter: never place README.md, CHANGELOG.md, INSTALLATION_GUIDE.md, QUICK_REFERENCE.md, CREATION-LOG.md, test-*.md, …
- Distinctive: line 89
Rejected-Change Impact Ledger: when trimming or consolidating an existing skill, record pruned rules, replacement coverage, and …
- Very specific: line 96
Ask what an agent executing those examples repeatedly would otherwise rewrite or rediscover each run: deterministic code belongs in …
- Very specific: line 101
Use --scope shared to scaffold under tools/agents/skills/<skill-name>/ and idempotently register { "path": "tools/agents/skills" } in …
- Very specific: line 103
Keep YAML frontmatter lean (name and description.
- Very specific: line 117
Budget & Link Hygiene: keep SKILL.md <= 19,000 bytes (< 20,000 B hard cap), use brace notation .omagy/{artifacts,plans,specs} when …
- Very specific: line 122
Cache exclusion: never write bytecode or tool caches into skill folders (PYTHONDONTWRITEBYTECODE=1), and exclude __pycache__/, …
“Common” is measured: kept by at least 6 in 10 of the 48 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skill Authoring & Management
Create, scaffold, validate, evaluate, and maintain self-contained Antigravity SKILL.md directories with $skill.
<Purpose>
Deliver concise, high-signal, deterministic skills across project, VCS-shared, and user scopes without context bloat, auxiliary clutter, or fragile ad-hoc instructions.
</Purpose><Use_When>
- The user invokes
$skillor asks to list, initialize (init), add, edit, remove, search, inspect (info), sync, set up, scan, validate, pressure-test (test), evaluate (eval), or extract skills. - A repeatable, codebase-specific workflow or domain playbook should be packaged as a
SKILL.mdfolder with optionalscripts/,references/,assets/, orresources/. - A team wants to share repository skills via Antigravity's
.agents/skills.jsonmanifest (entriesandinherits). </Use_When>
<Do_Not_Use_When>
- Bundling skills together with hooks, subagents, rules, and sidecars as an installable plugin: use Antigravity's built-in
pluginskill. - Saving a one-line user preference or session correction: suggest the
/learnslash command oromagy_wiki/agreements.md. - Diagnosing broken plugin hooks, Node runtime health, or stale
.omagy/state/files: use$doctor. </Do_Not_Use_When>
Scopes, Discovery Priority, and Team Sharing (.agents/skills.json)
Every skill is a directory <root>/<name>/ whose entrypoint is SKILL.md:
- project:
.agents/skills/<name>/SKILL.mdat the repository root (.agent/,_agents/, and_agent/are also recognized by Antigravity). - shared (declared via VCS):
tools/agents/skills/<name>/SKILL.md(or another repo folder) registered in.agents/skills.jsonusing top-levelentriesandinheritsarrays ({ "path": "tools/agents/skills", "include_only": ["^release-"], "exclude": ["^wip-"] }). - user:
~/.gemini/config/skills/<name>/SKILL.md(overridable in CLI tests viaOMAGY_USER_SKILLS_DIR). - plugin (read-only by default):
<plugin>/skills/<name>/SKILL.md. Modify plugin skills only when the user explicitly targets the plugin repository.
Collision priority: project > declared (.agents/skills.json) > user (global) > built-in. Always warn before creating or syncing a skill whose name shadows another active scope.
Command Contract
| Command | Deterministic Contract |
$skill list | Scan project, declared .agents/skills.json, and user roots (plus plugins read-only), parse frontmatter, and report name, scope, byte size, and path. |
$skill init <name> | Scaffold an SDO-compliant skill folder via sh <plugin>/hooks/run.sh skill-init <name> [--scope project|shared|user] [--dir <parent>] [--resources references,scripts,assets,resources] [--description <text>] [--force] --json and verify immediately with --strict validation. |
$skill add [name] | Run the 6-step authoring workflow: gather concrete trigger examples, triage resources, scaffold via skill-init, author SKILL.md, and pass skill-validate --strict. |
$skill edit <name> | Locate the target skill, inspect its current frontmatter and resource budget, apply focused edits, and re-run skill-validate --strict. |
$skill remove <name> | Show scope, metadata, and bundled files, confirm deletion via ask_question, and remove only the confirmed skill directory. |
$skill search <query> | Case-insensitive search across name, description, and body; rank metadata matches ahead of body matches. |
$skill info <name> | Show parsed metadata, scope, byte size, bundled resource inventory, and SKILL.md summary; suggest $skill search if missing. |
$skill sync | Diff user vs project / shared skills (only-left, only-right, diverged), exclude caches, and confirm every copy or overwrite. |
$skill setup | Ensure target skill roots exist, run an inventory scan, and offer guided init/add, validate, sync, or exit. |
$skill scan | Non-interactive inventory + structural summary across project, declared .agents/skills.json, and user skill roots. |
$skill validate [path] [--scope project|shared|user|all] | Run sh <plugin>/hooks/run.sh skill-validate [path | --scope project|shared|user|all] --strict --json (--scope and positional [path] are mutually exclusive) to enforce frontmatter (optional license), byte ceilings, SDO triggers, 1-level links, anti-clutter, symlink containment, supply-chain checks (trojan_unicode, prompt_injection_comment, unpinned_remote_exec), asset checks (asset_exceeds_5mb, invalid_png_header, script_syntax_error), and manifest schema without mutating files. |
$skill test <name> | Execute the blind 3-pressure subagent behavioral loop (RED baseline vs GREEN compliance + 5-rep micro-tests) in testing-and-sdo.md, writing .omagy/artifacts/skill-test-<name>-<UTC>.md. |
$skill eval | Run deterministic TF-IDF routing, cosine-collision (>= 0.75 error), and negative owner-survival checks via sh <plugin>/hooks/run.sh skill-eval --min-rank1 95 --json (testing-and-sdo.md). |
$skill extract [name] | Distill a repeatable workflow proven across >= 2 concrete runs into a sanitized SKILL.md (<= 19,000 B, zero secrets or personal paths) and validate with skill-validate --strict. |
With an explicit subcommand, execute directly; with bare $skill, present the guided setup menu.
3-Level Progressive Disclosure & 3-Bucket Resource Triage
Skills share the context window with conversation history, rules, and workspace files. Partition every skill across three loading tiers:
- Level 1 — YAML Metadata (
name+description, ~100 words, always loaded):name: kebab-case^[a-z0-9]+(?:-[a-z0-9]+)*$(1..64chars) matching the parent folder name.description:50..1,024chars in the third person stating what the skill does and explicit trigger conditions (Use when...,Use for...,Triggers on...).- Critical Routing Rule: Antigravity exposes only
nameanddescriptionprior to skill activation. Trigger conditions placed solely in body sections (## When to Use) are invisible during skill selection. - SDO Workflow-Summary Guard: never put
->step-chain arrows or full step recipes indescription(models skip readingSKILL.mdwhendescriptionsummarizes the steps), and never include HTML/XML tags or unbalanced</>(balanced CLI metavariables like<command>or<slug>are allowed).
- Level 2 —
SKILL.mdBody (<= 19,000 Bwarning /< 20,000 Bhard ceiling,<= 500lines, loaded on activation):- Imperative workflow steps, decision trees, command tables, and links to Level 3 files.
- Level 3 — Bundled Resources (loaded or executed strictly on demand):
scripts/*: deterministic Node/POSIX scripts executed via shell (node ./scripts/run.mjs) for fragile validation, parsing, or transformations without spending tokens reading code into context.references/*.md: deep domain schemas, rubrics, and edge-case catalogs (< 40,000 Beach). Keepreferences/strictly 1 level deep fromSKILL.md(never nestreferences/sub/doc.md), and include a top Table of Contents (>= 2##ATX headings) in every reference file over100lines.assets/*andresources/*: boilerplate files, templates, or static assets copied or filled into outputs without loading into context.
Degrees-of-Freedom Calibration
Match instruction specificity to task fragility rather than writing uniform prose:
| Freedom Tier | When to Choose | Authoring Pattern |
| High Freedom (heuristics & principles) | Multiple valid designs exist and the right choice depends on live codebase signals (e.g., architectural tradeoff reviews, code cleanup passes). | Concise principles, ranked priorities, and stop conditions; avoid rigid boilerplate that fights local conventions. |
| Medium Freedom (parameterized templates & conditional workflows) | A preferred structure or branching workflow exists, with bounded adaptation to project specifics (e.g., PR assembly, conditional create-vs-update flows). | Explicit decision tree (If creating -> follow Path A; if auditing -> follow Path B) plus strict or flexible output templates (testing-and-sdo.md). |
Low Freedom (exact CLI / scripts/* commands, zero freelancing) | Operations are fragile, stateful, or security-sensitive where small deviations corrupt state or bypass gates (e.g., skill-validate --strict, manifest schema validation, hash receipts). | Exact copy-pasteable commands, deterministic flags, expected exit codes (0|1|2), and fail-closed error handling. |
Anti-Clutter & Context-Economy Rules
- Default assumption: the model is already capable of general software engineering. Challenge every sentence: "Does this add domain-specific constraints, non-obvious procedures, or project invariants the model cannot infer?" Prefer one concrete input/output example over verbose exposition.
- Zero auxiliary clutter: never place
README.md,CHANGELOG.md,INSTALLATION_GUIDE.md,QUICK_REFERENCE.md,CREATION-LOG.md,test-*.md,example.py, unresolved`TODO:`markers,__pycache__/, or.skillzip archives inside a skill directory (skill-validatefails closed on all of them). - Write the Procedure, Not the Workaround: capture portable invariants and deterministic CLI checks rather than machine-specific hacks or 5-step ad-hoc grep chains (testing-and-sdo.md).
- Rejected-Change Impact Ledger: when trimming or consolidating an existing skill, record pruned rules, replacement coverage, and verification gates per testing-and-sdo.md.
6-Step Skill Authoring Lifecycle ($skill init / $skill add / $skill edit)
- Gather Concrete Trigger & Near-Miss Examples:
- Collect
3–4concrete user prompts that must trigger the skill plus2near-miss prompts that belong to sibling skills. Confirm scope (project,shared, oruser) viaask_questiononly when not already specified.
- Collect
- Triage Reusable Contents into
scripts/,references/, andassets/:- Ask what an agent executing those examples repeatedly would otherwise rewrite or rediscover each run: deterministic code belongs in
scripts/, detailed reference docs (> 100lines with TOC) belong 1-level deep inreferences/, and output boilerplates belong inassets/orresources/. Leave unneeded subdirectories uncreated.
- Ask what an agent executing those examples repeatedly would otherwise rewrite or rediscover each run: deterministic code belongs in
- Scaffold Cleanly with
skill-init:sh <plugin>/hooks/run.sh skill-init <skill-name> --scope project --resources references,scripts --json- Use
--scope sharedto scaffold undertools/agents/skills/<skill-name>/and idempotently register{ "path": "tools/agents/skills" }in.agents/skills.json(entries).skill-initrefuses to overwrite non-empty folders unless--forceis passed.
- Use
- Author SDO Frontmatter, Conditional Workflow, and Output Pattern:
- Keep YAML frontmatter lean (
nameanddescription; optionallicense,allowed-tools,metadata,compatibilitywhen required). - Structure
SKILL.mdwith imperative verbs, explicit conditional branches when the skill handles multiple modes, and either a strict output template (for compliance/API contracts) or a flexible template + input/output examples (testing-and-sdo.md).
- Keep YAML frontmatter lean (
- Run Deterministic Structural & Routing Validation:
sh <plugin>/hooks/run.sh skill-validate <skill-dir-or-.agents/skills.json> --strict --json- Fix every reported error or
--strictwarning (>= 20,000 Bhard /> 19,000 Bstrict warning,references/*.md >= 40,000 B, nestedreferences/, broken.md#anchororscripts/*links,\backslashes,->or HTML tags indescription,trojan_unicodeinvisibles/bidi chars,prompt_injection_commentHTML comments outside fenced code blocks,unpinned_remote_execunpinnednpx -yor shell pipe installer specs,asset_exceeds_5mb/invalid_png_header/script_syntax_error, banned clutter, invalid.agents/skills.jsonregexes, or symlink escapes). When editing plugin skills, also runsh <plugin>/hooks/run.sh skill-eval --min-rank1 95 --json.
- Fix every reported error or
- Iterate from Real Execution Evidence:
- Exercise the skill on real tasks (or run
$skill test <name>for gate/discipline skills). Observe where the agent hesitates, over-reads, or rationalizes a shortcut, then tightendescription, move bulky tables toreferences/, or extract repeated shell logic intoscripts/.
- Exercise the skill on real tasks (or run
Extracting Reusable Skills ($skill extract [name])
- Repeatability Gate (
>= 2verified runs): extract only workflows proven across>= 2real tasks that are (a) non-trivial beyond baseline model recall, (b) repeatable across future sessions, and (c) grounded in verified execution evidence. - Sanitize & Genericize: strip secrets/tokens, internal hostnames, and personal OS home paths (
/<Users-or-home>/<username>/...), replacing them with<workspace>,<plugin>, or$HOME. - Budget & Link Hygiene: keep
SKILL.md <= 19,000bytes (< 20,000B hard cap), use brace notation.omagy/{artifacts,plans,specs}when documenting workflow artifact paths, and verify withskill-validate --strict.
Symlink Containment & Sync Hygiene
- Canonical containment:
skill-validateinspects every path segment withfs.lstatSyncandfs.realpathSync, rejecting dangling symlinks and any symlink escaping the canonical skill directory (in multi-skill collections, bounded../<sibling>/...links are allowed only when<parent>/<sibling>/SKILL.mdexists inside the same canonical collection root). - Cache exclusion: never write bytecode or tool caches into skill folders (
PYTHONDONTWRITEBYTECODE=1), and exclude__pycache__/,.pytest_cache/,.ruff_cache/,.mypy_cache/,.DS_Store,Thumbs.db, and*.pycduring$skill sync.
✗ Error: <exact diagnostic code and path>
→ Suggestion: <concrete remediation command or edit>Exit Contract
End every $skill operation with one concise line: ✓ + affected skill path, scope, byte size, and skill-validate --strict result, or ✗ + exact error code and remediation step. Newly scaffolded skill directories take effect on the next conversation (or after reloading skills in Antigravity).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

