CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

58

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/resolve-repo/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

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

The body is well-structured, highly actionable with executable code, and has a clear sequenced workflow with appropriate validation checkpoints for the destructive clone operation. Minor redundancy between the Important section and earlier content, and a slightly monolithic inlining of scoring/output rules, keep it just short of top marks.

DimensionReasoningScore

Conciseness

Mostly lean with directly relevant code blocks and terse directives; the 'Important' section restates local-first, scoping, and name+description-only rules already covered above, which could be trimmed.

4 / 5

Actionability

Provides executable bash loops, concrete glab/gh CLI commands, and an exact machine-checked output template; mostly copy-paste ready, with the only gap being the offloaded lib functions whose internals are intentionally external (and justified).

4 / 5

Workflow Clarity

Clear 6-step sequence with validation checkpoints (ask user on no repos, branch to step 3 on ambiguity, confirm before cloning, CLI-fallback); the destructive clone step has explicit user confirmation so the cap-3 does not apply, with only a minor gap around retry on a failed clone.

4 / 5

Progressive Disclosure

Single-file skill with well-organized sections and a clearly signaled one-level-deep external reference (the determinism lib / CONTRACT.md); not a 5 because inlined scoring rules and output templates could be separated, and it is well over 50 lines.

4 / 5

Total

16

/

20

Passed

Description

58%Weight 40%Scale 1-5

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 clearly states what the skill does with concrete actions and sits in a distinct niche, but it lacks an explicit 'Use when...' trigger clause and is missing several natural user-facing trigger terms, capping completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when a ticket or task doesn't name which repository to work on, or when you need to find the right repo for a Jira/Linear/GitHub issue.'

Broaden trigger terms with natural user phrasings like 'find the right repo', 'which repository', and ticket-type keywords (Jira, Linear, GitHub issue).

Lead with the what/when pair in the first sentence and move the sub-agent operational note to a secondary clause so the capability description stays primary.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'detect VCS platform', 'match ticket to repo', 'clone if missing' — giving comprehensive coverage of the skill's capabilities; not a 5 because the 'Run this in a sub-agent' clause is operational guidance rather than a capability.

4 / 5

Completeness

Has a clear 'what' (detect platform, match ticket, clone) but no explicit 'when' / 'Use when...' clause; per the rubric a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Includes relevant keywords like 'Resolve the correct repository' and 'match ticket to repo', but is missing common natural phrasings a user would actually say (e.g. 'which repo', 'find the right repo') and ticket-type synonyms.

3 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (ticket-to-repo resolution with platform detection and cloning) with distinct triggers and minimal overlap with related git skills; not a 5 only because trigger phrasing is not maximally distinct.

4 / 5

Total

14

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
AndreJorgeLopes/devflow
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.