skill-builder
Use this skill when hardening an existing Codex skill or plugin for release. It produces focused audits, eval coverage, safety gates, and packaging/install handoff evidence.
65
80%
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/2026-04-21/deferred-store/skills/code_quality_review/skill-builder/SKILL.mdQuality
Discovery
75%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description has good completeness with an explicit 'Use when' clause and a distinctive niche that minimizes conflict risk. However, the specific capabilities listed are somewhat abstract (e.g., 'focused audits', 'handoff evidence') and could benefit from more concrete action verbs. The trigger terms lean toward internal jargon rather than natural user language.
Suggestions
Replace abstract nouns with concrete actions, e.g., 'Audits skill code for security vulnerabilities, generates eval test suites, adds safety gate checks, and produces packaging manifests and install instructions' instead of 'produces focused audits, eval coverage, safety gates, and packaging/install handoff evidence'.
Add natural user-facing trigger terms such as 'prepare for release', 'publish a skill', 'quality check', 'pre-release review', or 'ship a plugin' to improve keyword coverage beyond technical jargon.
Use third-person voice ('Produces focused audits...') instead of second-person imperative ('Use this skill when...') for the capability portion to align with style guidelines.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('hardening an existing Codex skill or plugin') and lists some actions ('audits, eval coverage, safety gates, packaging/install handoff evidence'), but these are somewhat abstract and not fully concrete—e.g., 'focused audits' and 'handoff evidence' are vague about what specifically is produced. | 2 / 3 |
Completeness | The description explicitly answers both 'what' (produces audits, eval coverage, safety gates, packaging/install handoff evidence) and 'when' ('when hardening an existing Codex skill or plugin for release'). The 'Use this skill when...' clause is present and explicit. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'hardening', 'skill', 'plugin', 'release', 'audits', 'eval coverage', 'safety gates', and 'packaging', but many of these are technical jargon. A user might say 'prepare my skill for release' or 'review my plugin before publishing' which aren't well covered. | 2 / 3 |
Distinctiveness Conflict Risk | The niche is quite specific—hardening Codex skills/plugins for release—which is unlikely to overlap with other skills. The combination of 'Codex skill', 'plugin', 'hardening', and 'release' creates a distinct trigger profile. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured hardening skill with strong actionability through specific CLI commands and a clear deliverable schema, excellent progressive disclosure via 'Read when:' signposts, and a robust workflow with validation checkpoints and fail-fast behavior. The main weakness is moderate verbosity—some constraints and principles are stated in multiple places (redaction appears twice, context-preservation philosophy is restated across sections), and the inline reference paths are long. Overall it is a high-quality skill body that effectively guides an agent through a complex multi-step hardening process.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably structured but contains some redundancy (e.g., constraints around redaction are stated twice, the philosophy section restates principles that appear again in constraints/anti-patterns). Some sections like 'Gotchas' and 'Anti-patterns' overlap. The references to agent-native and OpenAI-style contracts are verbose with full path repetition. | 2 / 3 |
Actionability | Provides specific, executable validation commands (e.g., `./bin/ask skills audit <target-skill-path> --level strict --json`), a clear ordered workflow, concrete deliverable schema fields, and explicit pass/fail/blocked outcome expectations. The examples section gives concrete trigger phrases. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (9 numbered steps), includes explicit validation gates with fail-fast behavior, feedback loops (fix one failure class then rerun), and a defined escalation path (stop at first failed gate, fix, rerun focused + broader gate). Failure modes and cap on retries are explicitly stated. | 3 / 3 |
Progressive Disclosure | Excellent use of 'Read when:' signposts pointing to five clearly named reference files for governance, quality tools, iteration/testing, advanced workflow, and discovery. The main SKILL.md stays as a map while deep policy is delegated to references. Navigation is one level deep and well-signaled. The See Also table provides clear routing to sibling skills. | 3 / 3 |
Total | 11 / 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 |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 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.