external-resource-context
Skill39 starsChanged 10 days agoMITView on GitHub
Resolves and records one external evidence source required by a current design or verification decision. Use when repository and supplied evidence cannot determine that decision.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- shinpr/claude-code-workflowstheir own version, first seen Mar 23, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- shinpr/claude-code-workflows★ 712same 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 repository30 other files it gives its agents.
- ai-development-guideSkill
- coding-rulesSkill
- documentation-criteriaSkill
- implementation-approachSkill
- integration-e2e-testingSkill
- llm-friendly-contextSkill
- recipe-add-integration-testsSkill
- recipe-buildSkill
- recipe-designSkill
- recipe-diagnoseSkill
- recipe-front-adjustSkill
- recipe-front-buildSkill
- recipe-front-designSkill
- recipe-front-planSkill
- recipe-front-reviewSkill
- recipe-fullstack-buildSkill
- recipe-fullstack-implementSkill
- recipe-implementSkill
- recipe-outcome-watchSkill
- recipe-planSkill
- recipe-prepare-implementationSkill
- recipe-quality-profileSkill
- recipe-reverse-engineerSkill
- recipe-reviewSkill
- recipe-update-docSkill
- requirement-convergenceSkill
- reviewee-judgmentSkill
- subagent-delegationSkill
- subagents-orchestration-guideSkill
- testingSkill
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
- Distinctive: line 59
Ask for the selected axis, its stable access method, and the feature identifier when known.
- Very specific: line 68
Write docs/project-context/external-resources.md, creating docs/project-context/ as needed.
- Very specific: line 69
When a target UI Spec or Design Doc exists, update its External Resources Used section with project-tier labels plus feature-specific …
- Distinctive: line 70
If a write fails, return the error with the intended path and leave completion status unresolved.
- Very specific: line 77
Read the matching label from docs/project-context/external-resources.md.
- Distinctive: line 78
Read the matching feature identifier from the target UI Spec or Design Doc when present.
≈ “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
External Resource Context
Purpose
This skill resolves a concrete external evidence dependency for a current design or verification decision, records its stable access method, and lets later consumers reuse that evidence.
Potential resources include design origin, design system, API or database schema sources, IaC, and verification environments. A workflow selects only the resource axis needed by its current decision.
Scope Boundaries
In scope: resolving a named external evidence need, storage location, single-source ownership, and lookup of a known resource.
Freshness handling: record access methods and feature identifiers here. The consuming workflow checks current resource content at use time.
Storage Locations
| Tier | Location | Holds | Update Frequency |
| Project | docs/project-context/external-resources.md | Environment-stable facts: resource labels, presence, and access methods | When the project environment changes |
| Feature | ## External Resources Used section in the relevant UI Spec or Design Doc | Feature-specific identifiers that reference project-tier labels | Per feature |
Single Source Rule
The project tier owns environment facts such as URLs, MCP server names, file paths, commands, and secret-store locations. Feature-tier sections list feature-specific identifiers such as design node ids, API paths, schema names, or IaC module names, then reference the project-tier label.
Hearing Protocol
When to Hear
| Condition | Action |
| Repository or supplied evidence resolves the current decision | Continue without hearing |
| A recorded matching axis has a usable access method | Reuse it without hearing |
| A named axis required by the current decision is missing or stale | Ask only for that axis and the access method needed to inspect it |
State which decision or verification result the requested resource controls. Leave unrelated axes unrecorded. Use N/A only for a selected or inspected axis confirmed to be outside the project.
Domain Routing
Load the domain reference matching the current task:
| Task type | References to load |
| Frontend UI work | references/frontend.md |
| Backend or data work | references/backend.md |
| API contract work | references/api.md |
| Infrastructure or deployment | references/infra.md |
| Fullstack | Load each relevant domain reference |
Each domain reference defines candidate axes and question templates. Record only the axes selected for the current decision.
Focused Hearing
Ask for the selected axis, its stable access method, and the feature identifier when known. Accept MCP server name, URL, file path, command, repository-owned source, or existing implementation. One answer completes the hearing when it makes the named decision inspectable.
When the resource remains unavailable, return the missing evidence and the exact decision it leaves unsupported to the caller. The caller owns response selection within its outcome and authority, including omitting an unnecessary mechanism; this lookup does not create a requirement to preserve the current design or invent a fallback.
Storage Protocol
After hearing completes:
- Merge the selected axis into the project-tier content using references/template.md; preserve unrelated existing entries.
- Write
docs/project-context/external-resources.md, creatingdocs/project-context/as needed. - When a target UI Spec or Design Doc exists, update its
External Resources Usedsection with project-tier labels plus feature-specific identifiers. - If a write fails, return the error with the intended path and leave completion status unresolved.
- Report touched file paths to the calling workflow.
Lookup Protocol
Consumers resolve external context in this order:
- Read the matching label from
docs/project-context/external-resources.md. - Read the matching feature identifier from the target UI Spec or Design Doc when present.
- Fetch or inspect only the resource needed by the current decision.
Output Format
The project-tier file follows references/template.md. Feature-tier sections use the fixed heading External Resources Used; heading level follows the parent document structure.
Quality Checklist
- Every requested axis names the decision or verification result it controls
- Each requested axis has a usable access method or records the exact unsupported decision for its consuming workflow
- Project-tier file contains environment facts
- Feature-tier sections contain feature identifiers and project-tier labels
- Unrelated project-tier entries are preserved
References
- references/frontend.md
- references/backend.md
- references/api.md
- references/infra.md
- references/template.md
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.

