atelier
Skill5 starsChanged 36 days agoMITView on GitHub
Run or modify Atelier skills, routines, agents, tools, intent routing, and harness portability in this repo. Use for broad Atelier harness work or to adapt Claude `/hi` to native Codex `$hi`.
12 other projects use a version of this.
Adopted by
Most recently taken up by
- Mazalucas/El-DT-Lightweight-Armytheir own version, first seen Nov 13, 2026
- Caiollaz/ateliertheir own version, first seen Nov 8, 2026
- ksprashu/agent-skill-forgetheir own version, first seen Nov 1, 2026
- ask-marcel/ask-marcel-office-clitheir own version, first seen Oct 25, 2026
- simota/agent-skillstheir own version, first seen Oct 23, 2026
- robingst/skillstheir own version, first seen Oct 20, 2026
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- simota/agent-skills★ 99same name
- ask-marcel/ask-marcel-office-cli★ 9same name
- Wondermonger-daydreaming/claude-skills-library★ 7same name
- Mazalucas/El-DT-Lightweight-Army★ 4same name
- ksprashu/agent-skill-forge★ 3same name
- adamramadhn/atelier★ 2same name
- luminary19/atelier★ 2same name
- anshrajore/atelier-mcp★ 0same name
- Caiollaz/atelier★ 0same name
- remp0x/atelier-claude-plugin★ 0same name
2 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 repository38 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- autoevo-reviewSkill
- civSkill
- curateSkill
- daily-reflectionSkill
- decisionSkill
- digestSkill
- dineSkill
- hiSkill
- introspectSkill
- lintSkill
- prmSkill
- pushSkill
- readSkill
- reflectSkill
- reviewSkill
- triageSkill
- weeklySkill
- captureSkill
- readingSkill
- autoevo-reviewSkill
- civSkill
- curateSkill
- daily-reflectionSkill
- decisionSkill
- digestSkill
- dineSkill
- hiSkill
- introspectSkill
- lintSkill
- prmSkill
- pushSkill
- readSkill
- reflectSkill
- reviewSkill
- triageSkill
- weeklySkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 1 is distinctive, and 5 are very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use this skill when the user asks to run or modify Atelier workflows, components, or harness portability.
- Distinctive: line 14
Read AGENTS.md for the shared contract, runtime adaptations, and harness checklist.
- Very specific: line 16
Read protocols/runtime-adapters.md only when changing or debugging cross-runtime behavior.
- Very specific: line 24
Do not launch Codex recursively, and do not launch bot-invoked workflows such as autoevo-nightly from shorthand.
- Very specific: line 97
Follow the checklist in AGENTS.md and harness/README.md.
- Very specific: line 108
Before edits, read protocols/repo-conventions.md → Editing discipline for whole-feature budgets, approval thresholds, smoke scope, and cost …
“Common” is measured: kept by at least 6 in 10 of the 12 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
Atelier
Use this skill when the user asks to run or modify Atelier workflows, components, or harness portability. It is the one hand-written Codex edge file; it points at the canonical sources and adds only what is Codex-native.
Quick Start
- Read
AGENTS.mdfor the shared contract, runtime adaptations, and harness checklist. It is the single instruction source for Claude Code and Codex. - Read
protocols/runtime-adapters.mdonly when changing or debugging cross-runtime behavior. - Invoke known workflows through their explicit repo skills (
$hi,$weekly,$review,$triage,$lint, and so on). Each reads the matchingskills/<name>/SKILL.mdsource and runs it in the current thread. For$hi, classify the request againstscripts/intent_coverage.py catalogand read only the selected row'sprocedure. No fit is a semantic handoff throughintents.general, never implicit reflection. - Do not launch Codex recursively, and do not launch bot-invoked workflows
such as
autoevo-nightlyfrom shorthand. - Discover native roles under
.codex/agents/and inspect them with/agent.Agent(...)in a command means dispatch the matching project agent; if dispatch is unavailable, run the role sequentially fromagents/<role>.mdand disclose the downgrade. - For external launches,
scripts/atelier_runtime.pyresolves the committed Codex default fromharness/runtimes.toml, the gitignored local preference, and one-process overrides.
Codex-native notes
- Codex CLI slash input is reserved for built-in TUI commands; project commands
are
$nameskills withallow_implicit_invocation: false.$reflectruns$hi. Translate/namereferences to$name; never translate real Codex built-ins such as/hooksor/agent. Readis the local file,Grep/Globarergandrg --files,Bashis the local shell,AskUserQuestionis a native choice UI or a concise numbered question.- Type
$in the Codex composer for command discovery. Do not guess an unavailable command.
Operations
- Local retrieval uses
scripts/semantic.py: Reflect's lexical index first, then the pinned QMD dependency.sources/semantic.mdowns setup, scopes, and the bounded JSON contract. Queries use cached models only; downloads require explicit initialization. - Vault title/rendering hygiene:
scripts/zk_audit.py; naming:protocols/repo-conventions.md. Linked ledger tasks usescripts/todos.py checkandsync --file <quarter>.md(preview;--applywrites); seeprotocols/local-first-architecture.md. - Wiki articles:
protocols/wiki-schema.mdgoverns creation, edits and metadata-driven localized titles;scripts/trust.pyreads canonical identities, bounded claims and evidence. Curator preserves identity and review history; Forgetter reads bounded claims. L1–L4 labels sync throughzk_audit.py --sync-reflect-levels;protocols/local-first-architecture.mdowns the contract. - Route context packs selected repository profiles and registered session logs
with pinned Repomix;
protocols/session-continuity.mdowns selection and ceilings. - Reflection's energy and exploration intents share
skills/daily-reflection/SKILL.mdwhile keeping their selected context. That procedure andprotocols/session-log.mdown the branches and compact logs. $digestusescollect --jsonthenwriteinto one Reflect-native note; the scheduleddaily-digestroutine uses configured CodexBar sources and compact quota tables. The shared command owns setup, offline boundaries, approval before a rewrite, and the three-edition overdue TODO limit; never sync during a run.- Reading feedback connects Curate, Read, Introspect, and explicit policy evaluation through
protocols/decision-ledger.md→ Reading feedback loop. Use its typeddecisions.pyhelpers for compact event batches and stored policy IDs; load Offline reading evaluation only for policy experiments. - Dispatch inputs and completion reporting live in
protocols/agent-handoff.md; load its common sections and the selected payload contract. The procedure owns calls;protocols/agent-handoff.mdalso owns responsibilities and voice legs. Reader owns the shared reading behavior; Scholar keeps only its role settings and the shared-contract pointer. - Native observation and routine reports:
sources/runtimes/observability.md. Direct API calls are unlogged. - For runtime capability maintenance, read
sources/runtimes/README.mdand the registry's references; CLI discovery does not prove activation. - Local scheduled routines: validate declarations with
uv run --frozen python scripts/routine_prefect.py validate --jsonand read recent Prefect state withuv run --frozen python scripts/routine_status.py.scripts/cron_spec.pyuses Prefect's cron engine for health-check dates and cadence. The transfer procedure is inscripts/launchd/README.md: stop every source scheduler before loading the Prefect deployment service. Sandbox path handling lives inscripts/routine_adapter.py; runtime ownership followsprotocols/runtime-adapters.md. Artifact evidence and shared receipt validation live inprotocols/remote-routines.md. Connector discovery before reporting missing inputs followsroutines/_adapters/archived-prompt/PROCEDURE.md. Autoevo drafts only in its isolated workspace; the trusted parent owns its plain-file vault writes and structured result; notes require applied changes or fresh triage (protocols/autoevo.md). - Private routine mappings, tools, routines, digest declarations, and skills
stay under their registered
$OVroots. Classification and activation live inprotocols/components.md; remote execution and digest context live inprotocols/remote-routines.md. $civloads framework definitions from the private source referenced by the profile.
Harness Changes
Follow the checklist in AGENTS.md and harness/README.md. The registries
are harness/skills.toml, harness/agents.toml, harness/intents.toml,
harness/models.toml, harness/capabilities.toml, harness/retrieval.toml, harness/paths.toml, and
harness/runtimes.toml, and routines/registry.toml; edit them, never the
generated runtime edges. Run python3 scripts/harness_lint.py before finishing and
scripts/harness_smoke.py after helper or registry edits. Keep runtime edges
thin: they point to canonical sources and do not copy workflow bodies.
Public configuration shape lives in harness/registry.schema.json; lint uses
the pinned validator in the project .venv. Setup and error codes are documented
in harness/README.md; lint never installs missing dependencies itself.
Before edits, read protocols/repo-conventions.md → Editing discipline for
whole-feature budgets, approval thresholds, smoke scope, and cost reporting.
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.

