conductor-revert

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

1.60x

Quality

68%

Does it follow best practices?

Impact

96%

1.60x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/conductor-revert/SKILL.md

The canonical home for this skill is conductor-revert in sickn33/agentic-awesome-skills

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.

A strongly actionable, well-sequenced operational guide with excellent validation and safety gates for a destructive workflow. Its weaknesses are generic filler sections that pad token cost and a dangling, poorly-signaled reference to a non-existent playbook file.

Suggestions

Remove or rewrite the generic "Use this skill when", "Do not use this skill when", and "Instructions" sections — they restate template boilerplate and waste context.

Fix the dangling reference: either create `resources/implementation-playbook.md` and move detailed UI templates/edge cases into it, or delete the pointer; currently the referenced path does not exist in the bundle.

Dimension	Reasoning	Score
Conciseness	The operational sections are lean and concrete, but three sections — "Use this skill when" ("Working on revert track tasks or workflows", "Needing guidance, best practices, or checklists"), "Do not use this skill when", and the generic "Instructions" bullets ("Clarify goals, constraints, and required inputs") — are boilerplate filler that adds no skill-specific value.	3 / 5
Actionability	Concrete executable commands throughout ("git log --oneline --grep=\"{trackId}\" --all-match", "git revert --no-edit {sha}"), exact confirmation protocol, and precise plan.md update rules; falls short of copy-paste-ready because commands carry placeholders ({trackId}, {N}) and some steps remain directives ("Determine task range for the phase by reading plan.md").	4 / 5
Workflow Clarity	A fully sequenced workflow (pre-flight checks → target selection → commit discovery → execution plan display → explicit 'YES' confirmation → ordered reverts → conflict halt → plan.md updates → verification) with explicit validation checkpoints, halt-on-error rules, and recovery guidance, matching the top anchor for destructive/batch operations.	5 / 5
Progressive Disclosure	Sections are well-organized and navigable, but the entire ~370-line skill is monolithic, the sole external pointer ("open `resources/implementation-playbook.md`") is buried in the filler Instructions section, and that file does not exist in the bundle — a dangling reference.	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.

A terse, domain-specific description that clearly states what the skill does, but it omits any "when to use" trigger guidance and misses the natural keywords (revert, rollback) users would most likely say. It is distinct from other skills but under-specified as a trigger.

Suggestions

Add an explicit 'Use when...' clause, e.g. "Use when the user asks to revert, roll back, or undo work by track, phase, or task in a Conductor-managed repository."

Include the natural trigger synonyms — "revert", "rollback", "undo commits/changes" — since 'revert' is the term used throughout the skill body yet missing from the description.

Optionally enumerate one or two more concrete actions (e.g. "creates revert commits and resets task status in plan.md") to raise specificity from one generic action to a fuller capability list.

Dimension	Reasoning	Score
Specificity	"Git-aware undo by logical work unit (track, phase, or task)" names the domain and granularity but offers only the single generic action "undo"; matches the anchor for naming the domain with 1-2 concrete actions rather than the several-action level above.	3 / 5
Completeness	The "what" is clear (git-aware undo at track/phase/task granularity) but there is no "Use when..." clause or equivalent trigger guidance, which per the judging guidelines caps this dimension at 3.	3 / 5
Trigger Term Quality	Keywords like "Git", "undo", "track", "phase", and "task" are natural user terms, but the most common phrasings users would actually say — "revert", "rollback", "undo changes/commits" — are absent, matching the anchor for some relevant keywords missing common variations and synonyms.	3 / 5
Distinctiveness Conflict Risk	The "(track, phase, or task)" scoping ties it to a Conductor-specific workflow system, making it mostly distinct with only minor overlap risk against general 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/conductor-revert/SKILL.md
Commit: 64adc55

Reviewed: 5 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.