conductor-revert

Git-aware undo by logical work unit (track, phase, or task)

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/conductor-revert/SKILL.md

Quality

Content

70%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 content is a strongly actionable, safety-minded revert workflow with excellent validation and feedback loops, but it carries generic filler and a broken external reference that hurt conciseness and progressive disclosure.

Suggestions

Trim the boilerplate in Instructions, Use-this-skill-when, Do-not-use, and Limitations (e.g. "Clarify goals, constraints, and required inputs") since Claude already knows to do this.

Fix or remove the reference to resources/implementation-playbook.md, which does not exist in the skill bundle.

Move the large ASCII display templates (execution plan, conflict, verification boxes) into a separate reference file and link to it, keeping SKILL.md as an overview.

Dimension	Reasoning	Score
Conciseness	The core workflow uses tight, specific git commands, but the Instructions, Use-this-skill-when, and Limitations sections contain generic filler ("Clarify goals, constraints...", "Apply relevant best practices...") and the large ASCII display boxes are token-heavy.	3 / 5
Actionability	Provides concrete, executable git log/revert commands with example SHAs and unit formats covering task, phase, and track reverts, with minor gaps such as underspecified plan.md task-range parsing.	4 / 5
Workflow Clarity	Destructive batch operation with explicit validation checkpoints (pre-flight checks, full plan display, explicit 'YES' gate), a halt-on-conflict feedback loop, and a post-revert verification checklist plus safety rules.	5 / 5
Progressive Disclosure	Well-sectioned with clear headers, but the body is a monolithic inlining of display templates and edge cases, and the one external reference ("resources/implementation-playbook.md") points to a file that does not exist in the bundle.	3 / 5
	Total	15 / 20 Passed

Description

53%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 is concise and specific about what the skill does and its scope, but it omits any explicit "when to use" trigger guidance and lacks common synonyms like "revert". It is reasonably distinct within the Conductor domain.

Suggestions

Add a "Use when..." clause naming concrete triggers, e.g. "Use when you need to revert or undo Conductor work by track, phase, or task."

Include natural synonyms such as "revert" and "rollback" so the description matches phrasing users actually say.

Consider naming one or two more concrete actions (e.g. "revert commits and reset plan.md task status") to lift specificity above a single verb.

Dimension	Reasoning	Score
Specificity	Names the git domain and one concrete action ("undo") with the granularity of work units (track, phase, or task), but does not enumerate multiple distinct actions, so it is not comprehensive.	3 / 5
Completeness	Has a clear "what" (git-aware undo by work unit) but no "Use when..." or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Includes relevant terms ("git", "undo", "track", "phase", "task") but misses common synonyms a user would say such as "revert" or "rollback".	3 / 5
Distinctiveness Conflict Risk	Tied to the Conductor track/phase/task niche, making it mostly distinct with only minor overlap risk against generic git-undo skills.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/conductor-revert/SKILL.md
Commit: 1f67c44

Reviewed: about 15 hours 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.