agentleFS
alfredxwalfredxw/denova/skills/configuration/SKILL.md

configuration

Skill990 starsChanged 4 months agoApache-2.0View on GitHub

Use when a Project Agent reads or changes lore indexes and group memberships, managed presets, game modules, automations, Skills, or Agent profiles through config_read and config_apply.

10 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use logging, error-handling and 2 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.
  • diego-tobalinaSkill

    logging

    Logging best practices for Java (SLF4J/Logback) and Node.js (Winston/Pino). Use for structured logging, log levels, and avoiding sensitive data exposure.

    Also in 4 projects that use this

  • MicrosoftSkill

    error-handling

    统一错误处理系统。在添加 API 端点、修改错误处理、添加前端 API 调用、编写错误相关测试时使用。

    Also in 4 projects that use this

  • NVIDIASkill

    testing

    Run Python and Rust tests for physicsnemo-curator using uv + pytest with coverage reporting via pytest-cov, and cargo-nextest for Rust tests. Includes benchmark workflows with pytest-benchmark and criterion.

    Also in 5 projects that use this

  • AnthropicSkill

    architecture

    Create or evaluate an architecture decision record (ADR). Use when choosing between technologies (e.g., Kafka vs SQS), documenting a design decision with trade-offs and consequences, reviewing a system design proposal, or designing a new component from requirements and constraints.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call config_read(operation=list) to resolve the exact ID and scope.

    line 17
  2. Very specific:

    Read exactly the relevant reference below with read({"path":"skill://configuration/references/<file>.md"}).

    line 18
  3. Very specific:

    Follow that resource's mutation semantics.

    line 19

“Common” is measured: kept by at least 6 in 10 of the 6 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Configuration

Manage every supported configuration resource through the stable config_read and config_apply tools. Never edit Denova configuration files or internal JSON storage directly.

When the latest [Configuration Page Context] supplies resource, use that exact tool resource name and its resource_id for the selected item when present. origin identifies the UI page, not a tool resource. Prefer the latest selection over earlier page context. If no exact resource name is supplied, discover it with config_read(operation=describe) without resource; do not guess from UI names.

Required workflow

  1. For an unfamiliar resource, call config_read with operation=describe. Omit resource to discover all registered kinds, or provide one kind for its contract.
  2. Call config_read(operation=list) to resolve the exact ID and scope. Catalogs use items plus next_cursor; continue with the identical request and returned cursor until truncated=false when the full catalog matters. Before an update or delete, call config_read(operation=get) for the exact ID and retain its latest revision.
  3. Read exactly the relevant reference below with read({"path":"skill://configuration/references/<file>.md"}). Do not infer a value shape from another resource.
  4. Follow that resource's mutation semantics. Call config_apply for exactly one create, update, or delete and use only names returned by describe.
  5. For update and delete, copy the latest revision from config_read; never guess, copy an example placeholder, or reuse a stale revision. Preserve every field or layer section the user did not ask to change.

get accepts any number of IDs. A mixed batch succeeds with existing items, explicit missing_ids, and per-ID failures; an entirely unsuccessful completed batch fails. Large exact reads also return next_cursor. Never treat truncated=true as a complete read.

A single oversized item occupies its own page. If the tool returns an artifact path with a bounded preview, use read on that path and follow its next_offset and next_byte_offset until the complete page is recovered. The page's next_cursor continues the configuration request; the file read offsets continue only that saved page. A preview is not a complete resource. Before a complete-replacement update, recover the entire original value and use the revision from that same snapshot; preserve all unrequested fields. If the revision is stale, reread and reconcile instead of attaching a newer revision to an older value.

  1. config_apply returns only a compact persistence receipt (resource, operation, id, revision). Read the changed item again and compare the requested fields plus preservation-sensitive fields. Report success only when the effective result matches.

Deletion must be explicitly requested by the user. If a stale-revision conflict occurs, read the current item again, reconcile the requested change with that value, and retry once with the new revision. Do not silently overwrite concurrent changes.

Mutation semantics

ResourcesUpdate behavior
narrative_style, game_planning, event_package, rule_system, state_system, image_presetComplete editable-resource replacement. Start from get, change only requested fields, and submit the complete editable value. Omitted arrays and objects are cleared or defaulted.
automationSparse patch. Omitted fields stay unchanged; a present triggers array replaces the whole trigger list. target is create-only and immutable.
agent_profileFixed Agents use sectional layered updates. A custom_agent mutation is user-only and replaces its complete independent definition; General SubAgent and custom SubAgent mutations follow the resource reference.
skillComplete replacement of one root SKILL.md or one supporting reference file. The root revision covers the whole Skill directory.
style_referenceCreate writes one document; update replaces its complete Markdown content.
lore_indexWorkspace singleton index. Update replaces the complete guide: introduction, ordered custom groups and automatic-group detail overrides. Removing a group backs up the collection and clears only its associations.
lore_index_membershipOne existing lore item by ID. Update replaces only its complete index_memberships array; [] restores automatic grouping. Apply independently per item, preserving unrelated associations.

Fields returned for inspection such as path, custom, builtin_overridden, invalid, error, timestamps, resolved snapshots, run history, and secrets are host-owned unless the resource reference explicitly says otherwise. Never add an unknown field: configuration values reject unknown keys.

Examples use REVISION_FROM_GET as a visible placeholder. Always replace it with the exact current revision returned for the same resource, ID, and scope.

Reference routing

  • style_reference → skill://configuration/references/style-reference.md
  • narrative_style → skill://configuration/references/narrative-style.md
  • Selected preset imports → skill://configuration/references/narrative-import.md
  • game_planning → skill://configuration/references/game-planning.md
  • event_package → skill://configuration/references/event-package.md
  • rule_system → skill://configuration/references/rule-system.md
  • state_system → skill://configuration/references/state-system.md
  • image_preset → skill://configuration/references/image-preset.md
  • automation → skill://configuration/references/automation.md
  • skill → skill://configuration/references/skill.md
  • agent_profile → skill://configuration/references/agent-profile.md
  • lore_index, lore_index_membership → skill://configuration/references/lore-index.md

For lore index organization, use these configuration resources. For creating or editing lore bodies, use query_lore_items with detail=full and write_lore_items when available. Do not pass index fields to write_lore_items or edit the backing JSON directly. Index management applies to the current project in both writing and game configuration pages; it does not enable configuration mutations during game play.

These are references, not sub-Skills. Do not pass a sub_skill argument or invoke another Skill name.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.