skillify
Capture a completed Codex workflow as a reusable SKILL.md package by analyzing session context plus optional session-collector evidence, interviewing the user with structured prompts, and writing a validated skill artifact. Use when the user asks to skillify or operationalize a repeatable process.
47
50%
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 ./Plugins/skill-factory/fixtures/budget-archive/2026-04-19/skills/scaffolding_templates/scaffolding_templates/skillify/SKILL.mdQuality
Discovery
85%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 is a well-crafted description that clearly defines a specific niche (creating SKILL.md files from Codex workflows) with concrete actions and explicit trigger guidance. Its main weakness is that the trigger terms could be broader to capture more natural user phrasings beyond 'skillify' and 'operationalize'. The description uses proper third-person voice and avoids vague language.
Suggestions
Expand trigger terms to include more natural user phrasings like 'create a skill', 'save as skill', 'make a skill file', 'package this workflow', or 'turn this into a skill'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'analyzing session context plus optional session-collector evidence', 'interviewing the user with structured prompts', and 'writing a validated skill artifact'. These are distinct, concrete steps in a workflow. | 3 / 3 |
Completeness | Clearly answers both what ('Capture a completed Codex workflow as a reusable SKILL.md package by analyzing session context...interviewing the user...writing a validated skill artifact') and when ('Use when the user asks to skillify or operationalize a repeatable process') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some natural trigger terms like 'skillify' and 'SKILL.md', but 'operationalize a repeatable process' is somewhat jargon-heavy. Missing common variations a user might say like 'create a skill', 'save as skill', 'make a skill file', or 'package workflow'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — creating SKILL.md files from Codex workflows is a very specific task unlikely to conflict with other skills. Terms like 'skillify', 'SKILL.md package', and 'session-collector evidence' are unique identifiers. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
14%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 stub that delegates all meaningful content to a single referenced file without providing any actionable overview, workflow steps, or concrete guidance in the body itself. The description promises a rich process (analyzing sessions, interviewing users, writing validated artifacts) but the body delivers none of it. It fails on actionability and workflow clarity because there is simply no substantive content to evaluate.
Suggestions
Add a concrete multi-step workflow in the body: e.g., 1) Analyze session context, 2) Interview user with specific prompts (list them), 3) Draft skill using template, 4) Validate output against criteria.
Include at least one concrete example of a structured interview prompt and expected skill output format directly in the SKILL.md body.
Add validation/verification steps—e.g., a checklist for what makes a valid skill package before finalizing.
Provide a brief overview of what the referenced skill-template.md contains so the reader understands the skill's structure without needing to navigate away.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is very brief (only 3 lines of actual instruction), which is lean, but it's so sparse that it's hard to say every token earns its place—the first line restates the title, and the reference line could be more informative. | 2 / 3 |
Actionability | There is no concrete guidance, no steps, no code, no examples, and no commands. The entire skill delegates everything to a referenced file with no actionable content in the body itself. | 1 / 3 |
Workflow Clarity | This is a multi-step process (analyze session, interview user, write skill artifact) but no steps, sequence, or validation checkpoints are provided. The description mentions structured prompts and validation but the body contains none of this. | 1 / 3 |
Progressive Disclosure | The skill references './references/skill-template.md' but no bundle files were provided, meaning the reference is unverifiable. More critically, the SKILL.md body contains essentially zero overview content—it's an empty shell pointing to a single file rather than a structured overview with well-signaled references. | 1 / 3 |
Total | 5 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- jscraik/Agent-Skills
- Commit
4c78f98
- 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.