spec-app-review
Skill1 starsChanged 6 months agoMITView on GitHub
Review an application-type spec for completeness against UI rendering requirements and golden-path structure.
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- agent-ix/quoinedited, first seen Jun 25, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- agent-ix/quoin★ 2089% same
Wrote their own version · 0
None found.
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 repository19 other files it gives its agents.
- spec-blueprintSkill
- spec-dependency-analysisSkill
- spec-evidence-analysisSkill
- spec-failure-domain-analysisSkill
- specifySkill
- spec-integrity-analysisSkill
- spec-matrixSkill
- spec-object-reviewSkill
- spec-reviewSkill
- spec-risk-complexity-analysisSkill
- spec-scope-boundary-analysisSkill
- spec-security-analysisSkill
- spec-to-planSkill
- spec-us-to-frSkill
- spec-write-frSkill
- spec-write-itSkill
- spec-write-nfrSkill
- spec-write-strSkill
- spec-write-usSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
After creating or updating an application spec
- Distinctive: line 13
Before submitting a spec for formal review
- Distinctive: line 14
When debugging why sections appear empty in the spec-editor-ui Application Detail view
- Very specific: line 18
Locate spec: Read spec/spec.md in the target repo.
- Distinctive: line 21
Fix or flag: If instructed to fix, apply corrections.
- Distinctive: line 51
Use a known well-formed application spec in your org as a comparison reference when reviewing.
≈ “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
Review Application Specification
Validate a component_type: application spec against what the spec-editor-ui actually renders and the structural requirements from specify.
When to Use
- After creating or updating an application spec
- Before submitting a spec for formal review
- When debugging why sections appear empty in the spec-editor-ui Application Detail view
Process
- Locate spec: Read
spec/spec.mdin the target repo. Verifycomponent_type: applicationin frontmatter. - Run checklist: Evaluate every item in references/checklist.md.
- Report findings: Group issues by severity (FAIL = will break UI, WARN = degraded display, INFO = quality improvement).
- Fix or flag: If instructed to fix, apply corrections. Otherwise, output the report.
Quick Reference
The spec-editor-ui ApplicationDetailPage has 7 tabs. Each tab extracts data from specific sections/artifacts:
| Tab | Data Source |
| Overview | Purpose, In Scope, Out of Scope, Operational Boundaries, API Endpoints, Components (catalog), Standards (frontmatter) |
| Architecture | Mermaid diagrams (tagged logical/deployment), FR diagrams, Aggregated Objects (catalog) |
| Integration | Artifacts with tags: [integration] in frontmatter |
| Security | Trust Boundaries table, artifacts with tags: [security], Standards |
| Requirements | StR/US/FR/NFR tables parsed from spec.md |
| Decisions | ADR artifacts (artifact_type: ADR) or inline ADR sections |
| Spec | Raw markdown rendering |
Key Parsing Rules (Quire Library)
These are the exact parser behaviors that determine whether content renders:
- Out of Scope:
parseDelegations()only recognizes(Handled by X)or(Delegated to X)patterns. Other parentheticals won't extract delegation targets. - In Scope:
parseBulletList()default pattern isbold-description(**Title** — Description). Plain bullets fall back to title-only. - Operational Boundaries:
parseBulletList({ pattern: 'bold-colon' })requires**Name**: detailformat. - Trust Boundaries:
parseTable()on section "Trust Boundaries" — expects 3 columns: Role, Capabilities, Restrictions. - Mermaid tags:
findDiagramByTag()matches%% @type: logicaland%% @type: deploymentcomments in mermaid blocks. - Integration tab: Filters artifacts by
tags: [integration]in YAML frontmatter (case-insensitive). - Security tab: Filters artifacts by
tags: [security]in YAML frontmatter.
Golden Reference
Use a known well-formed application spec in your org as a comparison reference when reviewing.
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.