skill-installer
Install Codex skills into the canonical git source tree from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
58
67%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./Plugins/skill-factory/fixtures/budget-archive/2026-04-19/skills/infrastructure_ops/infrastructure_ops/skill-installer/SKILL.mdQuality
Discovery
100%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 skill description that clearly communicates its purpose, lists specific actions, includes natural trigger terms, and has an explicit 'Use when' clause. It occupies a distinct niche (skill installation/management) that minimizes conflict risk with other skills. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Install Codex skills into the canonical git source tree', 'list installable skills', 'install a curated skill', 'install a skill from another repo (including private repos)'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (install Codex skills from curated list or GitHub repo path) and 'when' (explicit 'Use when' clause covering listing skills, installing curated skills, and installing from repos including private ones). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'install', 'skills', 'curated list', 'GitHub repo', 'private repos', 'list installable skills'. These cover the main ways a user would phrase requests related to this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: installing Codex skills from specific sources. The triggers ('install skills', 'curated skill', 'install from repo') are unlikely to conflict with other skills since this is a meta-skill about skill management itself. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill has reasonable structure and good safety-conscious design (verification steps, anti-patterns, constraints), but critically lacks actionable content — no concrete commands, code examples, or executable instructions are provided. The workflow reads like an abstract process description rather than a skill Claude can follow. The output contract lists fields without examples or a schema definition.
Suggestions
Add the actual installer command(s) with concrete syntax and arguments, e.g., `codex install <skill-name>` or the equivalent shell/Python commands used to fetch and place skill files.
Provide a concrete example of the required output contract as a JSON block with realistic field values, not just field names.
Include a specific example of the list command and its expected output format so Claude knows exactly what to present to users.
Add explicit verification commands or checks for step 4 (e.g., `ls -la .codex/skills/<name>/SKILL.md` or equivalent) and specify what constitutes a failure and how to recover.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but has some redundancy — the 'Anti-Patterns to Avoid' and 'Constraints' sections largely duplicate each other (e.g., overwriting without confirmation, treating URLs as untrusted). The 'Core Philosophy' section is somewhat abstract and could be folded into the workflow or constraints. | 2 / 3 |
Actionability | No concrete commands, code examples, or executable guidance is provided. The workflow is described abstractly ('Run minimal installer helper command') without specifying what that command is, what arguments it takes, or what the output looks like. The 'required output contract' lists field names but provides no example values or schema. | 1 / 3 |
Workflow Clarity | Steps are listed in a clear sequence and include a verification step (step 4), but the steps are too abstract to be actionable — 'Run minimal installer helper command' doesn't specify the actual command. The validation step lacks specifics on what to check or how to recover from failures. | 2 / 3 |
Progressive Disclosure | References to install-flows.md, troubleshooting.md, and contract.yaml are well-signaled with clear 'read when' conditions, which is good structure. However, no bundle files were provided, so we cannot verify these references exist. The main content itself is thin enough that it's unclear whether the referenced files contain the critical actionable details that are missing from the body. | 2 / 3 |
Total | 7 / 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
d00c351
- 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.