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

Content

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, actionable skill with a well-defined multi-step workflow, concrete executable commands, and clear decision logic. Its main weakness is moderate verbosity — some constraints are stated twice (Context Budget + Important sections), and the document could benefit from tighter editing. The lack of external reference files is acceptable given the skill's scope but the inline length pushes against ideal progressive disclosure.

Suggestions

Consolidate the 'Context Budget' and 'Important' sections into a single constraints block to eliminate redundancy and save tokens.

Consider extracting platform-specific API query examples (GitLab vs GitHub) into a separate reference file if the skill grows further.

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 prose could be trimmed. However, it mostly avoids explaining things Claude already knows and stays focused on the task.	2 / 3
Actionability	The skill provides fully executable bash commands for scanning repos, querying GitLab/GitHub APIs, and cloning. Scoring heuristics are concrete (prefix match, keyword overlap, label match), 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 → fetch remote, remote match → confirm before cloning). Validation checkpoints include user confirmation before destructive actions (cloning) and fallback paths for ambiguous or no-match scenarios.	3 / 3
Progressive Disclosure	The content is well-structured with clear sections and headers, but it's a fairly long monolithic document with no references to external files. Some content like the platform-specific API commands or the scoring heuristics could be split into separate reference files for cleaner navigation, though the lack of bundle files means this is the only file available.	2 / 3
	Total	10 / 12 Passed

Description

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 does a good job of listing specific concrete actions and occupying a clear niche, making it distinctive. However, it lacks an explicit 'Use when...' clause and could benefit from more natural trigger terms that users would actually say (e.g., 'git', 'GitHub', 'find the right repo'). The sub-agent instruction is a useful operational detail but doesn't help with skill selection.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user provides a ticket/issue ID and the correct repository needs to be identified, or when a task requires locating and cloning the right repo.'

Include more natural trigger terms users would say, such as 'git', 'GitHub', 'GitLab', 'find repo', 'which repository', 'checkout', replacing or supplementing the jargon 'VCS platform'.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'detect VCS platform', 'match ticket to repo', 'clone if missing'. Also includes an operational instruction about running in a sub-agent.	3 / 3
Completeness	The 'what' is well-covered (detect VCS platform, match ticket to repo, clone if missing), but there is no explicit 'Use when...' clause. The description implies when to use it but doesn't explicitly state trigger conditions like 'Use when the user provides a ticket ID' or 'Use when a repository needs to be identified'.	2 / 3
Trigger Term Quality	Includes some relevant terms like 'repository', 'VCS platform', 'ticket', 'repo', 'clone', but misses common user-facing variations like 'git', 'GitHub', 'GitLab', 'Bitbucket', 'checkout', or 'pull'. 'VCS platform' is somewhat jargon-heavy compared to what users would naturally say.	2 / 3
Distinctiveness Conflict Risk	The combination of VCS platform detection, ticket-to-repo matching, and conditional cloning is a very specific niche. It's unlikely to conflict with general git skills or code review skills due to its focused scope on repository resolution.	3 / 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: 8d872bf

Reviewed: 1 day 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.