foundation
Loaded by deliver skills for the delivery model and interaction posture. Consult model.md for the six phases, skill ↔ agent pairing, and cross-plugin context (how delivery consumes development and discovery artifacts). Consult guidelines.md for ongoing interaction posture: thinking partner, ground in reality, signals to surface, anti-patterns, cross-plugin fallbacks.
21
11%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./deliver/skills/foundation/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is essentially a set of internal cross-references to other files (model.md, guidelines.md) rather than a self-contained explanation of what the skill does or when to use it. It lacks any concrete actions, natural trigger terms, or explicit usage guidance, making it nearly impossible for Claude to correctly select this skill from a pool of options.
Suggestions
Replace the file references with a self-contained summary of what the skill actually does—list specific concrete actions (e.g., 'Guides delivery phase planning, manages skill-to-agent pairing, tracks delivery artifacts').
Add an explicit 'Use when...' clause with natural trigger terms a user might say (e.g., 'Use when the user asks about project delivery, phase planning, or coordinating delivery workflows').
Remove internal jargon and cross-file pointers from the description; the description should stand alone without requiring the reader to consult other documents.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language like 'delivery model and interaction posture' without listing any concrete actions. There are no specific capabilities described—no verbs indicating what the skill actually does. | 1 / 3 |
Completeness | The 'what' is extremely vague—it references consulting other files but never explains what the skill itself does. There is no 'when' clause or explicit trigger guidance whatsoever. | 1 / 3 |
Trigger Term Quality | The description contains internal jargon ('skill ↔ agent pairing', 'cross-plugin context', 'anti-patterns', 'cross-plugin fallbacks') that users would never naturally say. There are no natural trigger terms a user would use. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague and internally referential that it's unclear what domain it covers. Terms like 'delivery' and 'interaction posture' are generic enough to conflict with many other skills, and the lack of concrete scope makes it indistinguishable. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a thin index page that points to model.md and guidelines.md without providing any actionable content of its own. While the cross-references are clearly signaled, the body lacks any concrete guidance, workflows, or executable instructions. It reads more like a README placeholder than a functional skill that teaches Claude how to perform delivery tasks.
Suggestions
Add a concise 'Quick Start' or summary section that distills the most critical actionable guidance from model.md and guidelines.md so the skill provides standalone value without requiring file reads.
Include at least a high-level workflow or decision tree for how delivery skills consume upstream artifacts (e.g., 'When starting delivery: 1. Check for existing PRs/specs from develop plugin, 2. ...').
Add concrete examples of what 'reading upstream context' looks like in practice — e.g., which artifacts to look for, what commands or file paths to check.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is relatively short but includes some explanatory prose that doesn't add actionable value (e.g., 'Deliver does not yet model its own artifact graph — there are no per-type artifact writers here'). The note about what deliver does and doesn't do is mildly useful context but could be tighter. | 2 / 3 |
Actionability | The skill provides no concrete guidance, commands, code, or specific instructions. It is entirely descriptive and navigational — it tells Claude what exists but not what to do. There are no executable steps or actionable directives. | 1 / 3 |
Workflow Clarity | There is no workflow, sequence, or process described. The content is purely a pointer to other files with no steps, validation checkpoints, or operational guidance of any kind. | 1 / 3 |
Progressive Disclosure | The skill references two supporting files (model.md and guidelines.md) with clear one-level-deep links and brief descriptions of what each contains. However, no bundle files were provided to verify these references exist, and the SKILL.md itself contains almost no substantive content — it's essentially just a routing page with minimal overview value. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- audenaert/etak
- Commit
632c389
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.