tdg-personal/opensource-pipeline
"Open-source pipeline: fork, sanitize, and package private projects for safe public release. Chains 3 agents (forker, sanitizer, packager). Triggers: '/opensource', 'open source this', 'make this public', 'prepare for open source'."
90
90%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
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 strong skill description that concisely communicates what the skill does (fork, sanitize, package for open-source release), how it works (3 chained agents), and when to use it (explicit trigger phrases). It uses third-person voice, avoids vague language, and occupies a clear niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'fork, sanitize, and package private projects for safe public release' and mentions chaining 3 agents (forker, sanitizer, packager). These are concrete, actionable descriptions of what the skill does. | 3 / 3 |
Completeness | Clearly answers both 'what' (fork, sanitize, and package private projects for public release using 3 chained agents) and 'when' (explicit triggers listed). The triggers section serves as an explicit 'Use when' equivalent. | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would actually say: '/opensource', 'open source this', 'make this public', 'prepare for open source'. These cover common variations of how a user would phrase this request. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — open-sourcing private projects is a very specific workflow unlikely to conflict with other skills. The trigger terms like '/opensource' and 'make this public' are clearly scoped to this particular use case. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with excellent workflow clarity including proper validation gates, retry loops with caps, and explicit safety constraints. Its main weakness is that it's somewhat long and monolithic — the detailed agent prompts and per-command protocols could benefit from being split into referenced files. The content is mostly efficient but has minor redundancies in the agent spawn blocks.
Suggestions
Consider extracting the detailed agent prompt templates into a separate AGENTS.md or PROMPTS.md file, keeping only a brief summary in the main skill
The 'When to Activate' section duplicates trigger information likely in the frontmatter — consider removing it to save tokens
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly well-structured but includes some verbosity that could be tightened — e.g., the full Agent() pseudo-invocations are repeated with similar boilerplate, and the 'When to Activate' section partially duplicates the frontmatter triggers. However, it doesn't over-explain concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides concrete, executable bash commands, specific agent spawn patterns with exact prompts, clear parameter resolution logic, and copy-paste-ready commands for GitHub publishing. Each step has specific, actionable instructions rather than vague descriptions. | 3 / 3 |
Workflow Clarity | The 7-step pipeline is clearly sequenced with explicit validation checkpoints — the sanitizer acts as a safety gate with a PASS/FAIL verdict, there's a retry loop capped at 3 attempts with fallback to manual intervention, and the workflow explicitly blocks progression on FAIL. The anti-patterns section reinforces safety constraints. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and a command table for navigation, but the entire skill is monolithic — the detailed agent prompts, staging layout, and individual command protocols could be split into referenced files. The only external reference is to 'security-review' skill at the end. For a skill of this length (~180 lines), some content should be offloaded. | 2 / 3 |
Total | 10 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
Reviewed
Table of Contents