CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

auto-claude-workspace

Auto-Claude workspace and git worktree management. Use when reviewing changes, merging builds, managing branches, or understanding isolation strategy.

Quality

77%

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/auto-claude-workspace/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

A well-structured, highly actionable reference dominated by concrete, executable commands with clear sequences and confirmation on the destructive discard path. It is held back by token-inefficient re-teaching of basic git worktree mechanics, duplicated conflict-resolution coverage, and a padded AI-merge section, all of which could be tightened or moved to reference files.

Suggestions

Trim the conciseness gaps: remove explanations of basic git worktree properties ('Own git index', 'Independent node_modules') and the generic 'Manual Worktree Operations' git tutorial Claude already knows, keeping only Auto-Claude-specific commands and paths.

Consolidate the duplicated merge-conflict guidance (Conflict Resolution > Manual Resolution vs. Troubleshooting > Merge Conflicts) into one section with an explicit validate → fix → re-run-merge feedback loop, and add a post-merge verification step (run tests, confirm build) to the After Merging checklist.

Replace the vague 'AI-Powered Merge' bullet list ('Detection: Identifies conflicting files, Analysis: Understands both versions...') with the concrete command to invoke it and what its output means, and link the Related Skills entries to actual skill paths so navigation is actionable.

DimensionReasoningScore

Conciseness

The body is command-focused and largely lean, but includes explanations Claude already knows ('Separate working directory, Own git index, Independent node_modules', generic git worktree/branch/prune tutorials), a padded 'AI-Powered Merge' bullet list, and duplicate merge-conflict coverage in both the Conflict Resolution and Troubleshooting sections.

3 / 5

Actionability

Concrete executable commands throughout (`python run.py --spec 001 --review/--merge/--discard`, `git worktree add ... -b experiment-branch`, `git diff main...auto-claude/001-feature`). Minor gaps: the `cd apps/backend` working directory is assumed, `python spec_runner.py --task` appears once without introduction, and run commands are placeholders ('or your project's run command').

4 / 5

Workflow Clarity

Clear sequences with most checkpoints present: 'Before Merging' (review → test → check conflicts), merge flow (checks conflicts → merges → AI resolver → cleanup), and the destructive discard path explicitly 'Asks for confirmation'. Not a 5 because manual conflict resolution and post-merge verification lack explicit validate→fix→retry feedback loops.

4 / 5

Progressive Disclosure

No bundle files exist; the skill is a single self-contained document with clean ##/### section organization and a Related Skills pointer at the end. At ~324 lines, generic manual worktree operations and troubleshooting could be split into reference files, and Related Skills names lack paths, so structure is good but not fully split.

4 / 5

Total

15

/

20

Passed

Description

78%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.

A strong description that clearly and explicitly states both what the skill does and when to use it, with concrete trigger phrases and a distinct Auto-Claude/worktree niche. Its only weakness is that the capability statement itself ('management') is generic, with specific actions surfacing only in the trigger clause.

DimensionReasoningScore

Specificity

Names the domain ('Auto-Claude workspace and git worktree management') but the capability verb is generic ('management'); concrete operations like 'reviewing changes, merging builds, managing branches' appear only as trigger contexts rather than an explicit capability list.

3 / 5

Completeness

Explicitly answers both 'what' ('Auto-Claude workspace and git worktree management') and 'when' ('Use when reviewing changes, merging builds, managing branches, or understanding isolation strategy') with four concrete trigger phrases.

5 / 5

Trigger Term Quality

'reviewing changes, merging builds, managing branches, isolation strategy' gives good natural keyword coverage; common synonyms and variations (e.g., combine, integrate, cleanup) are missing, so it falls short of comprehensive.

4 / 5

Distinctiveness Conflict Risk

'Auto-Claude' and 'git worktree' establish a clear niche with minimal conflict risk, but generic triggers like 'reviewing changes' and 'managing branches' could overlap general git or code-review skills.

4 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

fernandezbaptiste/Skrillz

Path

skills/auto-claude-workspace/SKILL.md

Revision

93ed392

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill