conductor-revert
Git-aware undo by logical work unit (track, phase, or task)
50
55%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/conductor-revert/SKILL.mdQuality
Discovery
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 too terse and relies on domain-specific jargon (track, phase, task) without explaining what these mean or when the skill should be triggered. It lacks a 'Use when...' clause and doesn't enumerate the concrete git operations it performs, making it difficult for Claude to reliably select this skill from a pool of alternatives.
Suggestions
Add a 'Use when...' clause with natural trigger terms like 'undo git changes', 'revert commits', 'rollback work', 'undo last task'.
List specific concrete actions the skill performs, e.g., 'Reverts git commits, resets staged changes, and restores files grouped by logical work units such as tracks, phases, or tasks'.
Define or briefly explain what 'track', 'phase', and 'task' mean in this context so Claude can match user requests that may use different terminology.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (git undo) and mentions work units (track, phase, task), but doesn't list concrete actions like 'revert commits', 'reset staged changes', or 'restore files'. | 2 / 3 |
Completeness | Provides a partial 'what' (git-aware undo by logical work unit) but completely lacks a 'when' clause or explicit trigger guidance. Per rubric guidelines, missing 'Use when...' should cap completeness at 2, and the 'what' is also weak, so this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes 'git' and 'undo' which are natural terms, but 'track', 'phase', and 'task' are project-specific jargon that users may not naturally say. Missing common variations like 'revert', 'rollback', 'reset'. | 2 / 3 |
Distinctiveness Conflict Risk | The 'logical work unit' framing and specific terms (track, phase, task) provide some distinctiveness from generic git skills, but could overlap with other git workflow or undo-related skills. | 2 / 3 |
Total | 7 / 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 excellent workflow clarity and actionability — it provides concrete git commands, clear sequencing, explicit safety rules, and robust error handling with merge conflict and edge case coverage. The main weaknesses are moderate verbosity (boilerplate sections, verbose ASCII display templates) and a monolithic structure that could benefit from splitting detailed reference material into separate files. The safety rules and confirmation requirements are particularly strong.
Suggestions
Remove the generic boilerplate sections ('Use this skill when', 'Do not use this skill when', 'Limitations') which add ~15 lines of non-specific content that doesn't help Claude execute the task.
Consider moving edge cases, undo instructions, and detailed display templates into a referenced file (e.g., `resources/implementation-playbook.md` which is already mentioned) to reduce the main skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly detailed and well-structured, but includes some unnecessary sections like the generic 'Use this skill when / Do not use this skill when' boilerplate and the 'Limitations' section which are filler. The ASCII art banners and verbose display templates add bulk. However, most content is domain-specific and not explaining things Claude already knows. | 2 / 3 |
Actionability | The skill provides fully executable git commands, specific bash examples, concrete argument formats with examples (e.g., `auth_20250115:phase2`), exact grep patterns for commit discovery, and precise instructions for plan.md updates. The guidance is copy-paste ready and leaves little ambiguity. | 3 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced from pre-flight checks through target selection, commit discovery, execution plan display, confirmation, execution, plan updates, and verification. Explicit validation checkpoints exist at multiple stages: pre-flight git status checks, mandatory 'YES' confirmation, halt-on-conflict behavior, and post-revert verification steps with test commands. | 3 / 3 |
Progressive Disclosure | The skill references `resources/implementation-playbook.md` in the Instructions section but no bundle files are provided, making this reference unverifiable. The content is quite long and monolithic — sections like edge cases, undo instructions, and detailed display templates could potentially be split into separate reference files. However, the section headers provide reasonable navigation within the single file. | 2 / 3 |
Total | 10 / 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
f5dc9e3
- 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.