CtrlK
BlogDocsLog inGet started
Tessl Logo

cross-repo-release-preflight

Fail fast when a release workflow depends on credentials or access to a second repository.

41

Quality

41%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.squad/skills/cross-repo-release-preflight/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides solid conceptual guidance for cross-repo release workflow validation with good pattern/anti-pattern coverage and concrete real-world examples. However, it lacks executable code snippets (GitHub Actions YAML, shell commands) that would make it immediately actionable, and the multi-step workflow is presented as unordered bullets rather than a clear sequenced process with validation checkpoints.

Suggestions

Add executable GitHub Actions YAML snippets showing the preflight job with secret validation (e.g., a job step that checks `if: env.PLUGINS_REPO_TOKEN == ''` and fails with a clear message).

Restructure the Patterns section into a numbered workflow sequence with explicit validation checkpoints, e.g., '1. Preflight: validate secret → 2. Validate repo access → 3. Check sync gate → 4. Clone and update → 5. Validate version match → 6. Push'.

Add a concrete shell or Actions step example for the reachability check (e.g., `gh api repos/owner/repo --jq .full_name` using the PAT).

Consider referencing or including a template workflow file for progressive disclosure, even if no bundle is provided, to signal where detailed implementation lives.

DimensionReasoningScore

Conciseness

The content is reasonably efficient and doesn't over-explain basic concepts, but some bullet points are somewhat verbose and could be tightened. Phrases like 'Add a dedicated preflight job before the first cross-repo checkout' are clear but could be more concise. The patterns section has some redundancy between related bullets.

2 / 3

Actionability

The skill provides specific patterns and anti-patterns with concrete examples referencing real workflow files and repos, but lacks any executable code—no YAML workflow snippets, no shell commands for secret validation, no copy-paste-ready GitHub Actions job definitions. The guidance is directional rather than executable.

2 / 3

Workflow Clarity

The patterns implicitly describe a sequence (preflight → validate secret → validate reachability → sync gate → publish), but this is spread across unordered bullet points rather than presented as a clear numbered workflow. There's no explicit validation checkpoint structure or feedback loop for error recovery, despite the skill involving potentially destructive cross-repo operations.

2 / 3

Progressive Disclosure

The content is organized into logical sections (Context, Patterns, Examples, Anti-Patterns) which provides decent structure. However, with no bundle files and no references to supporting documents for detailed implementation (e.g., a template workflow YAML or a detailed setup guide), the skill is somewhat monolithic for its complexity level.

2 / 3

Total

8

/

12

Passed

Description

32%

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 is narrowly focused on a single behavior (failing fast on credential/access dependencies in release workflows) without explaining when Claude should select this skill. It lacks a 'Use when...' clause and misses common user-facing trigger terms, making it difficult for Claude to reliably choose this skill from a large pool.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when a user is setting up or debugging a release workflow that requires cross-repo access, deploy tokens, or shared credentials.'

Include natural trigger terms users would say, such as 'CI/CD', 'GitHub Actions', 'deploy', 'access token', 'cross-repo dependency', 'permissions error'.

Expand the 'what' portion to list additional concrete actions beyond 'fail fast', such as 'validates credential availability, checks repository access permissions, and surfaces clear error messages before the workflow proceeds.'

DimensionReasoningScore

Specificity

The description names a specific domain (release workflows) and a concrete action ('fail fast'), but it only describes one narrow behavior rather than listing multiple concrete actions or capabilities.

2 / 3

Completeness

The description addresses 'what' (fail fast on credential/access dependencies) but completely lacks an explicit 'when should Claude use it' clause or trigger guidance, which per the rubric caps completeness at 2, and the 'what' itself is also quite narrow, pushing this toward 1.

1 / 3

Trigger Term Quality

Includes some relevant terms like 'release workflow', 'credentials', and 'second repository', but misses common user variations such as 'CI/CD', 'deploy', 'access token', 'cross-repo', 'permissions', or 'GitHub Actions'.

2 / 3

Distinctiveness Conflict Risk

The combination of 'release workflow' and 'credentials or access to a second repository' is fairly specific, but without clearer trigger terms it could overlap with general CI/CD or credential management skills.

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
sbroenne/mcp-server-excel
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.