define-docs-norms
Skill8 starsChanged 2 months agoMITView on GitHub
Create or update docs/ARTIFACT_NORMS.md from an approved proposal and establish project docs norms as canonical rules.
In this repository77 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- archive-milestoneSkill
- assess-product-opportunitySkill
- automate-testsSkill
- bump-versionSkill
- capture-work-itemsSkill
- commit-workSkill
- competitive-researchSkill
- consume-nats-messageSkill
- decontextualize-textSkill
- deep-researchSkill
- define-missionSkill
- define-north-starSkill
- define-roadmapSkill
- define-strategic-pillarsSkill
- define-visionSkill
- deliver-featureSkill
- design-strategic-goalsSkill
- eli5Skill
- establish-delivery-workflowSkill
- execute-delivery-workflowSkill
- generate-agent-entrySkill
- generate-github-workflowSkill
- generate-standard-readmeSkill
- inspect-artifact-stateSkill
- integrate-branchesSkill
- manage-secretSkill
- map-item-dependenciesSkill
- market-researchSkill
- orchestrate-code-reviewSkill
- orchestrate-governance-stepSkill
- orchestrate-repair-loopSkill
- orchestrate-repair-requirements-loopSkill
- orchestrate-roadmap-planningSkill
- plan-milestonesSkill
- plan-nextSkill
- policy-researchSkill
- ponytailSkill
- prepare-presales-responseSkill
- prepare-version-notesSkill
- prioritize-backlogSkill
- product-opportunity-analysisSkill
- promote-roadmap-itemsSkill
- publish-nats-messageSkill
- record-milestone-achievementSkill
- redeploy-localSkill
- refine-skill-designSkill
- review-architectureSkill
- review-codebaseSkill
- review-diffSkill
- review-dotnetSkill
- review-error-surfacingSkill
- review-functional-designSkill
- review-goSkill
- review-implementation-alignmentSkill
- review-javaSkill
- review-observabilitySkill
- review-orm-usageSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Primary goal: create or update the project norms file safely and auditably.
- Very specific: line 62
Read the proposal (usually from docs/calibration/docs-norms-proposal.md)
- Very specific: line 63
Check whether an older docs/ARTIFACT_NORMS.md exists
- Distinctive: line 69
Write a manual-confirmation note for any low-confidence rule (where there is one)
- Distinctive: line 100
Stop and ask for confirmation when the input proposal is ambiguous
- Distinctive: line 101
Must not mark an unresolved conflicting rule as settled
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skill: Define Docs Norms
Purpose
Fix a reviewed norms proposal into docs/ARTIFACT_NORMS.md and make it the canonical rule set for the project's documentation governance.
Core Objective
Primary goal: create or update the project norms file safely and auditably.
Success criteria (all of them must hold):
- ✅ The input proposal is unambiguous and ready to write
- ✅ The norms file structure matches the project schema and conventions
- ✅ The change notes are clear (rules added, modified, removed)
- ✅ The only write target is
docs/ARTIFACT_NORMS.md - ✅ The output can be consumed directly by runtime / linter / CI tooling (per
rules/doc-health-criteria.md)
Acceptance test: can the norms file serve directly as the basis for path/naming/front-matter validation, and be parsed reliably by other skills?
Scope Boundaries
This skill owns:
- Creating or updating
docs/ARTIFACT_NORMS.md - Merging existing norms with a new proposal (configurable strategy)
- Emitting the change summary and migration notes
This skill does not own:
- Discovering and deriving norms (a person or the AgentFabric runtime takes that)
- Repository tidying and file migration (per
rules/repo-structure-hygiene.md, carried out by the AgentFabric runtime or by a person) - Compliance audit and readiness scoring (runtime / linter / CI tooling takes that)
Handoff point: once the norms are written, structural cleanup and compliance checking are carried out by runtime / linter / CI tooling per rules/repo-structure-hygiene.md and rules/doc-health-criteria.md.
Use Cases
- A new project establishing
ARTIFACT_NORMSfor the first time - An existing project promoting a proposal into formal rules
- Iterating on the norms (paths, naming, field policy)
Behavior
Stage 1: confirm the input
- Read the proposal (usually from
docs/calibration/docs-norms-proposal.md) - Check whether an older
docs/ARTIFACT_NORMS.mdexists - Confirm the write strategy:
create | merge | replace
Stage 2: assemble the norms
- Assemble the path mapping, the naming policy and the front-matter standard
- Write a manual-confirmation note for any low-confidence rule (where there is one)
- Validate format consistency and parseability
Stage 3: write and summarize
- Write
docs/ARTIFACT_NORMS.md - Emit the change summary for this pass (added/modified/removed)
- Emit the suggested next steps: the runtime tidies up per
rules/repo-structure-hygiene.md, plus compliance checking perrules/doc-health-criteria.md
Input and Output
Input
- The reviewed norms proposal
- Optionally an existing
docs/ARTIFACT_NORMS.md - Optionally a merge strategy (
create|merge|replace)
Output
docs/ARTIFACT_NORMS.md- The change summary
Restrictions
Hard Boundaries
- Writing the norms file is the only write allowed; no repository restructuring is performed
- Stop and ask for confirmation when the input proposal is ambiguous
- Must not mark an unresolved conflicting rule as settled
Skill Boundaries
Do not do these (other skills own them):
- Discovery and derivation: a person or the AgentFabric runtime
- Compliance scoring: runtime / linter / CI tooling (per
rules/doc-health-criteria.md) - File tidying: the runtime, per
rules/repo-structure-hygiene.md
Self-Check
- A rule input ready to write was received
docs/ARTIFACT_NORMS.mdwas written correctly- The rule change summary was emitted
- No write outside the norms file was performed
Examples
Example 1: creating norms from a proposal
- Input:
docs/calibration/docs-norms-proposal.md - Behavior:
create - Output:
docs/ARTIFACT_NORMS.md
Example 2: an incremental update to existing norms
- Input: the old norms + the new proposal
- Behavior:
merge - Output: the updated norms file + the change summary
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.

