ritual
Skill16 starsChanged 7 days agoMITView on GitHub
Author a new Asimi ritual or edit an existing one in .agents/rituals.yaml. Use when the user says "create a ritual", "add a ritual", "new ritual", "edit ritual", or similar.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- all-source-os/all-sourcetheir own version, first seen Nov 15, 2026
- ritual-foundation/ritual-dapp-skillstheir own version, first seen Oct 26, 2026
- haliphax-ai/skillstheir own version, first seen Mar 26, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- all-source-os/all-source★ 4same name
- haliphax-ai/skills★ 0same name
- ritual-foundation/ritual-dapp-skills★ 0same name
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 repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- gh-issue-syncSkill
- write-ritualsSkill
- write-testsSkill
- releaseSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. 0 are common, 3 are distinctive, and 14 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
14
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Before writing YAML, clarify with the user:
- Very specific: line 25
If $ARGUMENTS already provides enough detail, skip the questions and proceed.
- Very specific: line 29
Add the ritual to .agents/rituals.yaml (create the file if it doesn't exist).
- Very specific: line 32
Every ritual needs name, description, and steps
- Very specific: line 33
Use inputs for parameters the ritual accepts
- Very specific: line 34
Use background to pre-load context shared across multiple steps
- Very specific: line 35
Use ritual-level then for outcomes the whole ritual produces
- Very specific: line 39
Use act for the prompt — write clear, specific instructions
- Very specific: line 40
Use given to pass context variables (e.g.
- Very specific: line 41
Use "!command" in given to inject shell command output (e.g.
- Very specific: line 42
Use then to declare what a step produces
- Very specific: line 44
Use on_failure: retry, on_failure: goto (with on_failure_target), or on_failure: zhengming
- Very specific: line 69
Keep act prompts focused — one clear task per step
- Very specific: line 70
Use max_retries at the ritual level (default: 1, typical: 2-3)
- Distinctive: line 75
After writing the ritual:
- Distinctive: line 76
Verify the YAML is valid
- Very specific: line 77
Check that all on_failure_target references point to real step names
“Common” is measured: kept by at least 6 in 10 of the 3 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
You are authoring an Asimi ritual. The user's request is: $ARGUMENTS
Gather Requirements
Before writing YAML, clarify with the user:
- Goal — What should this ritual accomplish?
- Steps — What ministers are involved and in what order? Available ministers:
chancellor— coordinates, reports status, requests guidancestrategist— analyzes requirements, produces plansforge— implements changes, writes codejudge— runs tests, verifies correctnesssage— reviews code quality, records precedents
- Inputs — Does it need parameters (edict_id, file path, etc.)?
- Trigger — Should it activate on an event (e.g.
court_started) or be manual (no trigger)? - Failure handling — Should failing steps retry, goto an earlier step, or request zhengming?
If $ARGUMENTS already provides enough detail, skip the questions and proceed.
Write the Ritual
Add the ritual to .agents/rituals.yaml (create the file if it doesn't exist). Follow these rules:
Structure
- Every ritual needs
name,description, andsteps - Use
inputsfor parameters the ritual accepts - Use
backgroundto pre-load context shared across multiple steps - Use ritual-level
thenfor outcomes the whole ritual produces
Steps
- Each step needs a unique
nameand aminister - Use
actfor the prompt — write clear, specific instructions - Use
givento pass context variables (e.g.the manifests,the verdicts,the earth status) - Use
"!command"ingivento inject shell command output (e.g."!just test") - Use
thento declare what a step produces - Steps execute sequentially in array order
- Use
on_failure: retry,on_failure: goto(withon_failure_target), oron_failure: zhengming
Context Variables
Available variables for given and templates:
the edict/the edict details— current edictthe manifests— file changesthe borderlands— unstaged changesthe middle kingdom— staged changesthe capital— committed changesthe verdicts— test resultsthe earth status— full git status (expands to.earth_borderlands,.earth_middle_kingdom,.earth_capital)manifests for the borderlands— diffs for unstaged changesthe court status— minister statusthe unsealed edicts— edicts awaiting approvala heaven's snapshot— heaven's statethe project metadata— language, structure info
Patterns
- Forge/Judge/Sage loop — forge implements, judge tests, sage reviews. On failure, loop back to forging.
- Strategist first — add a planning step before forging for medium-complexity work.
- Fork/Join — for parallel work over a list of items. Use
fork: { over: step-name, batch_size: N }with awork:block containing sub-steps. Access current item with{{ .item }}. - System steps — omit
ministerfor runtime-handled checks (e.g. sandbox health, version checks).
Style
- Step names should be gerunds (forging, judging, censoring) or descriptive nouns
- Keep
actprompts focused — one clear task per step - Use
max_retriesat the ritual level (default: 1, typical: 2-3) - Reference template variables with
{{ .variable_name }}
Validate
After writing the ritual:
- Verify the YAML is valid
- Check that all
on_failure_targetreferences point to real step names - Show the user the complete ritual and ask for confirmation before finalizing
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.

