resolve-repo

Resolve the correct repository for a task — detect VCS platform, match ticket to repo, clone if missing. Run this in a sub-agent to avoid filling main context.

Quality

72%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/resolve-repo/SKILL.md

Quality

Discovery

67%

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 strong on specificity and distinctiveness, clearly articulating a unique set of concrete actions around repository resolution. However, it lacks an explicit 'Use when...' clause and misses common natural-language trigger terms users would employ (e.g., 'git', 'GitHub', 'clone the repo'), which limits its effectiveness for skill selection.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user references a ticket, issue, or task and the correct repository needs to be identified or cloned.'

Include common natural trigger terms like 'git', 'GitHub', 'GitLab', 'Bitbucket', 'clone', 'checkout', 'pull request', 'issue number' to improve matching against user queries.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'detect VCS platform', 'match ticket to repo', 'clone if missing'. Also specifies execution context ('sub-agent').	3 / 3
Completeness	The 'what' is well-covered (resolve repo, detect VCS, match ticket, clone). However, there is no explicit 'Use when...' clause — the triggering conditions are only implied by the actions described, which caps this at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Includes some relevant terms like 'repository', 'VCS platform', 'ticket', 'repo', 'clone', but misses common user-facing terms like 'git', 'GitHub', 'GitLab', 'Bitbucket', 'checkout', or 'pull'. Users are more likely to say 'clone the repo' or 'find the GitHub repo' than 'resolve the correct repository'.	2 / 3
Distinctiveness Conflict Risk	This skill occupies a clear niche — repository resolution and ticket-to-repo matching — that is unlikely to conflict with other skills. The combination of VCS detection, ticket matching, and cloning is quite distinctive.	3 / 3
	Total	10 / 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 well-crafted skill with strong actionability and workflow clarity — the 6-step process is logically sequenced with concrete commands, clear decision points, and user confirmation gates. The main weaknesses are moderate redundancy between the 'Context Budget' and 'Important' sections, and the monolithic structure that could benefit from splitting platform-specific details into separate files. Overall, it provides clear, executable guidance that Claude can follow effectively.

Suggestions

Merge the 'Context Budget' constraints into the 'Important' section at the bottom to eliminate redundancy and save ~10 lines of repeated guidance.

Consider extracting platform-specific API query examples (GitLab vs GitHub) into a separate reference file to keep the main skill leaner and easier to scan.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes some unnecessary verbosity — e.g., the 'Context Budget' section restates constraints that are also covered in the 'Important' section at the bottom, and some explanatory text could be trimmed. However, it largely avoids explaining concepts Claude already knows.	2 / 3
Actionability	The skill provides fully executable bash commands for scanning repos, detecting VCS platforms, querying GitLab/GitHub APIs, and cloning. The scoring heuristics are concrete (prefix match, label match, keyword overlap), and output formats are clearly specified with copy-paste ready templates.	3 / 3
Workflow Clarity	The 6-step workflow is clearly sequenced with explicit decision points (local match → skip remote, ambiguous → proceed to remote, confirm before cloning). Each step has clear entry/exit conditions and the flow includes validation checkpoints like user confirmation before destructive actions (cloning).	3 / 3
Progressive Disclosure	The content is well-structured with clear sections and headers, but it's a fairly long monolithic document (~150 lines) with no references to external files. The platform-specific API commands and setup hints could be split into separate reference files, though for a standalone skill without bundle files this is acceptable.	2 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

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: AndreJorgeLopes/devflow
Commit: b0b1bb6

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.