egdev6egdev6/discord-project-manager/skills/scoped-skill-resolver/SKILL.md

scoped-skill-resolver

Skill4 starsChanged 5 months agoMITView on GitHub

Trigger: effective skills, skill pack, global/category/channel scope, disabled skill, skill override. Resolve skills before workflow execution.

In this repository10 other files it gives its agents.
- brand-contextSkill
- content-ledgerSkill
- discord-approval-gateSkill
- discord-general-advisorSkill
- linkedin-weekly-plannerSkill
- on-demand-brief-plannerSkill
- openclaw-runtime-orchestratorSkill
- release-roadmap-hygieneSkill
- strategy-plannerSkill
- x-queue-plannerSkill

The file

We split this skill into the rules it gives an agent

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

≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
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

Very specific:
Use this skill when a Discord-originated request needs effective context, effective skill selection, effective capability resolution, …
line 12
Very specific:
Use the deterministic contract from docs/architecture/discord-scoped-skills-registry.md:
line 18
Distinctive:
Do not let workflow skills independently decide private profile bindings or capability permissions.
line 37
Distinctive:
Keep disabled skills excluded unless a reviewed override explicitly re-enables them.
line 50
Distinctive:
Never let category/channel workflow skills become global defaults by being merely synced into the workspace.
line 51
Very specific:
Keep discord-approval-gate mandatory for write-like outcomes.
line 52

≈ “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.

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

Files

SKILL.md

Activation Contract

Use this skill when a Discord-originated request needs effective context, effective skill selection, effective capability resolution, skill-pack explanation, or global/category/channel inheritance resolution.

This skill is a resolver contract. It does not perform the workflow itself and does not persist registry or private runtime changes.

Resolution Order

Use the deterministic contract from docs/architecture/discord-scoped-skills-registry.md:

effective_skills =
  selected global skills
  + category enabled skills
  + channel preferred skills
  - disabled skills
  + reviewed overrides

For write-like flows, add discord-approval-gate as mandatory even if a scoped registry draft omits it.

Resolve runtime output as one envelope:

effective_runtime = effective_context + effective_skills + effective_capabilities

Do not let workflow skills independently decide private profile bindings or capability permissions.

Skill Classification

Class	Skills	Rule
Runtime core	`openclaw-runtime-orchestrator`, `scoped-skill-resolver`, `discord-approval-gate`	Always available to the runtime surface.
Scoped workflow	`brand-context`, `content-ledger`, `strategy-planner`, `linkedin-weekly-planner`, `x-queue-planner`, `on-demand-brief-planner`	Use only when selected by global/category/channel scope.
Preserved protocol	Gentle-AI SDD assets under `.openclaw/skills`	Use only through the `gentle-sdd` backend boundary.

Hard Rules

Explain included and excluded context, skills, and capabilities.
Keep disabled skills excluded unless a reviewed override explicitly re-enables them.
Never let category/channel workflow skills become global defaults by being merely synced into the workspace.
Keep discord-approval-gate mandatory for write-like outcomes.
Distinguish capability availability from scoped permission/configuration.
Include provenance and reason for every included or excluded item.
Registry updates are write-like and require approve write through discord-approval-gate.

Output Contract

scope_layers:
  global: [<skill-or-context-ref>]
  category: [<skill-or-context-ref>]
  channel: [<skill-or-context-ref>]
  disabled: [<skill-or-context-ref>]
effective_context:
  included:
    - ref: <profile-or-context-ref>
      scope: <global|category|channel|thread-session>
      provenance: <source>
      reason: <why-included>
      content_policy: <reference-only-no-private-content|sanitized-summary>
  excluded:
    - ref: <profile-or-context-ref>
      provenance: <source>
      reason: <why-excluded>
effective_skills:
  included:
    - skill_name: <skill>
      class: <runtime-core|scoped-workflow|preserved-protocol>
      provenance: <source>
      reason: <why-included>
  excluded:
    - skill_name: <skill>
      provenance: <source>
      reason: <why-excluded>
effective_capabilities:
  included:
    - capability: <filesystem|browser|buffer|engram|github|image_generation|gentle_sdd>
      available: <true|false>
      permitted: <true|false>
      config_state: <not-required|private-config-required|configured-private|missing-private-config>
      provenance: <source>
      reason: <why-included>
  excluded:
    - capability: <capability>
      available: <true|false>
      permitted: false
      reason: <why-excluded-or-blocked>
mandatory_skills: [discord-approval-gate] # for write-like flows
approval_required: <true|false>
writes_attempted: false
resolution_notes: <one sentence>

References

docs/architecture/discord-scoped-skills-registry.md
docs/architecture/discord-effective-runtime-resolver.md
docs/architecture/discord-context-skill-packs.md
openclaw/config/skill-inventory.yaml
skills/discord-approval-gate/SKILL.md

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.

Check your setup, free