github-operations
**WORKFLOW SKILL** — Full GitHub contribution lifecycle: branches, conventional commits, issues, PRs, Actions, releases. gh CLI-first with MCP fallback. WHEN: "commit", "push", "open PR", "create branch", "create issue", "cut release", "GitHub operation". DO NOT USE FOR: Azure infrastructure, Bicep/Terraform code, architecture decisions. INVOKES: gh CLI (primary), GitHub MCP (fallback).
66
78%
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 ./.github/skills/github-operations/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 an excellent skill description that hits all the key criteria. It provides specific concrete actions, natural trigger terms in an explicit WHEN clause, clear tooling details, and even negative boundaries to prevent misuse. The structured format (WORKFLOW SKILL label, WHEN, DO NOT USE FOR, INVOKES) makes it highly scannable and unambiguous for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: branches, conventional commits, issues, PRs, Actions, releases. Also specifies tooling (gh CLI-first with MCP fallback), giving a clear picture of what the skill does. | 3 / 3 |
Completeness | Clearly answers both 'what' (full GitHub contribution lifecycle with specific actions) and 'when' (explicit WHEN clause with trigger terms). Also includes a 'DO NOT USE FOR' clause which adds further clarity on boundaries. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'commit', 'push', 'open PR', 'create branch', 'create issue', 'cut release', 'GitHub operation'. These are all terms users would naturally use when requesting these tasks. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit boundary-setting via the 'DO NOT USE FOR' clause (Azure infrastructure, Bicep/Terraform, architecture decisions). The GitHub-specific triggers and tooling (gh CLI, GitHub MCP) create a clear niche unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%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 workflow skill with strong progressive disclosure and clear organization across reference files. Its main weaknesses are the lack of executable command examples for core operations (actual gh CLI invocations for the happy path) and missing explicit error recovery/feedback loops for destructive or multi-step operations like commits and PR creation. Some content redundancy (repeated gh-vs-MCP guidance, duplicate reference links) slightly inflates the token cost.
Suggestions
Add a concrete, executable example for the core happy path (e.g., `gh pr create --base main --title 'feat(skills): add X' --body '...' --squash`) so Claude can copy-paste rather than infer command syntax.
Add explicit error recovery steps: what to do when commitlint rejects a commit, when pre-push hooks fail, or when `gh pr create` returns an error — even brief inline guidance would improve workflow clarity.
Remove the duplicate Smart PR Flow quick reference table or consolidate it into the Issues & PRs section to reduce redundancy, since the full details are already referenced via smart-pr-flow.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables and quick references, but some redundancy exists — the Smart PR Flow section repeats information already covered in Issues & Pull Requests, and the rules section restates the gh-vs-MCP preference multiple times. The reference index at the bottom duplicates links already provided inline throughout the document. | 2 / 3 |
Actionability | Provides concrete branch naming conventions, commit format, and global flags, but lacks executable command examples for the core workflow steps (e.g., actual `gh pr create` commands, `git branch -m` rename sequences). The workflow steps are listed as text rather than copy-paste-ready commands, and detailed commands are deferred entirely to a reference file. | 2 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced and step 4 in the rules includes a validation checkpoint (branch name validation before commit/PR). However, there are no explicit validation/feedback loops for the commit stage (what if commitlint fails?), no error recovery guidance for failed pushes or PR creation, and the pre-push hook validation is mentioned but not shown with recovery steps. | 2 / 3 |
Progressive Disclosure | Excellent structure with a concise overview in the main file and well-signaled one-level-deep references to 5 specific reference files. The reference index table at the bottom provides clear navigation, and each section includes inline quick references before pointing to detailed docs. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- jonathan-vella/azure-agentic-infraops
- Commit
05d7617
- 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.